CN116863127A - Method for acquiring region of interest and related equipment - Google Patents
Method for acquiring region of interest and related equipment Download PDFInfo
- Publication number
- CN116863127A CN116863127A CN202210313658.2A CN202210313658A CN116863127A CN 116863127 A CN116863127 A CN 116863127A CN 202210313658 A CN202210313658 A CN 202210313658A CN 116863127 A CN116863127 A CN 116863127A
- Authority
- CN
- China
- Prior art keywords
- detection
- region
- node
- sub
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 176
- 238000001514 detection method Methods 0.000 claims abstract description 1011
- 238000004891 communication Methods 0.000 claims abstract description 25
- 230000015654 memory Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 26
- 230000001788 irregular Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 8
- 239000004973 liquid crystal related substance Substances 0.000 claims 2
- 238000004364 calculation method Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 42
- 238000013461 design Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 12
- 230000009286 beneficial effect Effects 0.000 description 7
- 238000005192 partition Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000005484 gravity Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000011022 operating instruction Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012946 outsourcing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method for acquiring a region of interest and related equipment. The method comprises the following steps: the first node clusters a plurality of detection units included in the sub-detection area to obtain a clustering result, and the clustering result indicates a first region of interest corresponding to the sub-detection area; sending first indication information to a second node, wherein the first indication information comprises a clustering result; and the second node performs clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain a second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region. The data volume processed by the second node in the process of global clustering is reduced, so that the communication volume between the second node and the first node is reduced, and the calculation volume of the second node is also reduced.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method for acquiring a region of interest and related devices.
Background
Various devices running in the space can generate data, along with the continuous development of big data technology, the data generated in the space can be collected, the interested region in the space region is identified, people can be helped to find the region with special service value in the space in time, and further service problems in the interested region are solved or semantic value in the interested region is mined. For example, in a network anomaly monitoring scenario, an operator would like to be able to identify the spatial region in which the anomaly occurred and to resolve network problems occurring in that spatial region in time.
Specifically, the whole detected space region can be divided into a plurality of non-overlapping regular grids, and as the data volume generated by the whole detected space is large, the plurality of regular grids can be grouped, different groups correspond to different slave nodes, namely, the data generated by the space region corresponding to the different groups are sent to different slave nodes. And each slave node performs clustering operation according to the acquired data, namely, clustering is performed on the local space in the whole detection space, so as to obtain a plurality of local clustering results, and each local clustering result indicates a local region of interest. And then converging the local clustering results to a master node for global clustering.
However, at present, the master node needs to use data generated in a rule grid corresponding to all local clustering results in the global clustering process, so that the communication between the slave node and the master node is high, and the calculation amount of the master node occupied in the global clustering process is large.
Disclosure of Invention
The embodiment of the application provides a method for acquiring a region of interest and related equipment, wherein in the global clustering process, identification information of detection units in each first region of interest and identification information of detection units on boundaries between different sub-detection regions are adopted, so that the data volume processed by a second node in the global clustering process is greatly reduced, the communication volume between the second node and the first node is reduced, and the calculation volume of the second node is also reduced.
In order to solve the technical problems, the embodiment of the application provides the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for acquiring a region of interest, which may be used in the field of big data in computer technology. The method is applied to an acquisition system of the region of interest, the system comprises a plurality of first nodes and second nodes, the method is used for determining the region of interest from a detection region, the detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region comprises a plurality of detection units, and the 'detection units' refer to minimum space regions when the detection region is subjected to data statistics, namely minimum monitoring units in the process of identifying the region of interest in the detection region.
The acquisition method of the region of interest comprises the following steps: each first node clusters a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest includes detection units of a target class. Each first node sends first indication information to the second node, wherein the first indication information comprises a clustering result. The clustering result may include identification information of each first region of interest, identification information of a detection unit of a target class within each first region of interest, and a mapping relationship between the detection unit of the target class and the first region of interest.
And the second node executes clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region. The category of the target detection unit is a target category and is positioned on the boundary between different sub-detection areas in the detection area; it should be noted that, the first region of interest and the second region of interest each include detection units of a target class, and the difference is that the first region of interest is a local region of interest obtained by clustering a plurality of detection units in a sub-detection region, and the second region of interest is a global region of interest corresponding to the entire detection region.
In the implementation manner, the detection unit in each first region of interest (namely the region of interest obtained by clustering the local region) and the target detection unit positioned on the boundary between different sub-detection regions in the detection region are adopted in the process of global clustering of the second node, so that the data volume processed by the second node in the process of global clustering is greatly reduced, the communication volume between the second node and the first node is reduced, and the calculation volume of the second node is also reduced; further, in the scheme, the calculation amount of the second node in the clustering process is small, so that the method can also support the adoption of a streaming mode to determine the region of interest in the detection region in real time.
In one possible implementation manner of the first aspect, the method further includes: the second node transmits second indication information to each first node, the second indication information including a proximity relation between a plurality of different detection units within the detection area; the detection units with proximity relation in the embodiment of the application may include detection units with coverage areas contacting each other (i.e. adjacent to each other); optionally, the detection units having a proximity relation may further include a detection unit having a distance less than a distance threshold.
Each first node determines a target detection unit corresponding to the boundary of the sub-detection area according to the detection unit of the target category in the sub-detection area and second indication information, wherein the first indication information is also used for indicating the target detection unit.
In the implementation manner, each first node generates the identification information of the target detection unit corresponding to the boundary of the sub-detection area, and sends the identification information of the target detection unit corresponding to the boundary of the sub-detection area to the second node, and the second node performs the summarizing operation, so that the calculation amount executed by the second node is further reduced; and the different first nodes work in parallel, so that the time consumed by the whole calculation process is reduced, and the efficiency of the acquisition process of the region of interest is improved.
In a possible implementation manner of the first aspect, the second indication information is obtained based on a graph model corresponding to the detection area, a vertex of the graph model represents a plurality of detection units in the detection area, and an edge of the graph model indicates a proximity relation between a plurality of different detection units in the detection area. Wherein each detection unit is embodied as any one of the following: the spatial region corresponding to the regular network, the spatial region corresponding to the irregular polygonal grid or the spatial region determined based on the position information of the entity equipment in the detection region.
As an example, for example, search behavior information on each terminal device in the detection area is obtained to obtain an area in the detection area that is interested in a specific application, where the second node may divide the entire detection area into a plurality of rule networks and count the data obtained in each detection unit (i.e., the spatial area corresponding to each rule grid). As another example, if the network abnormal area in the detection area is located based on a measurement report reported by a base station in the detection area, the location information of a plurality of communication devices in the detection area and the network signal strength of the communication devices may be obtained based on the measurement report, and in the foregoing application scenario, the second node may divide the detection area based on an administrative division, a traffic autonomous domain or other rules in the detection area, so that each detection unit may be specifically represented as a spatial area corresponding to an irregular polygon mesh. As another example, for example, the detection area includes a plurality of entity devices distributed therein in the form of discrete points, and the second node may further determine a spatial area of the detection unit corresponding to each entity device in the detection area based on the location information of the entity device.
Further, in the case where the first detecting unit (i.e., any one of the detecting units within the detecting area) is embodied as a regular grid, a center point of the first detecting unit or a center of gravity point of the first detecting unit may be regarded as a vertex representing the first detecting unit. In case the first detection unit is embodied as an irregular polygonal mesh, the second node may take the center of gravity point of the first detection unit as a vertex representing the first detection unit. In case the first detection unit is embodied as a spatial region determined based on the physical devices within the detection region, the second node may take the location point of the physical device within each detection unit as the vertex of the first detection unit. If the two detection units have a proximity relation, the two detection units are connected by the edge of the graph model; if the two detection units do not have a proximity relation, the two detection units are not connected by the edges of the graph model.
In this implementation manner, a plurality of detection units in the whole detection area are abstracted into a graph model, the vertices of the graph model represent the plurality of detection units in the detection area, edges of the graph model indicate the proximity relations among the plurality of different detection units in the detection area, and each detection unit is specifically expressed as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region. Namely, under the condition that the detection unit is embodied in various forms, abstract modeling can be carried out on the detection area, so that more application scenes can be covered, and the implementation flexibility of the scheme is improved.
In one possible implementation manner of the first aspect, the first node and the second node are both deployed with a stream processing engine, and data obtained from the sub-detection area is real-time data. In the implementation manner, the streaming processing engines are deployed on the first node and the second node, so that real-time data in the detection area can be processed, and timeliness of a positioning process of the region of interest in the detection area is improved.
In a possible implementation manner of the first aspect, the second node performs a clustering operation on the first region of interest according to the clustering result and the target detection unit, to obtain at least one second region of interest corresponding to the detection region, including: the second node determines a first region of interest to be combined from a plurality of first regions of interest included in the detection region according to the clustering result and the target detection unit; and the second node determines at least one second region of interest corresponding to the detection region according to the first regions of interest which are required to be combined.
In the implementation manner, a first region of interest to be combined is determined from a plurality of first regions of interest included in a detection region, and different first regions of interest are combined to obtain a second region of interest corresponding to the detection region; the global clustering process is a merging process of different first regions of interest, and is simple to operate and easy to implement.
In a possible implementation manner of the first aspect, the data obtained from the sub-detection area includes any one of the following data: data transmitted by the base station in the sub-detection area, position information of the communication device in the sub-detection area, or data acquired by the sensor in the detection area. In the implementation mode, various application scenes of the embodiment of the application are provided, and the implementation flexibility of the scheme is improved.
In a second aspect, an embodiment of the present application provides a method for acquiring a region of interest, which may be used in the field of big data in computer technology. The method is applied to an acquisition system of an interested region, the system comprises a plurality of first nodes and second nodes, the detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region comprises a plurality of detection units, and the method comprises the following steps: each first node clusters a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest includes detection units of a target class; each first node sends first indication information to the second node, wherein the first indication information comprises a clustering result, the first indication information is used for indicating the first node to execute clustering operation on the first region of interest by using the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, and the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
The steps executed by the first node in each possible implementation manner of the first aspect may also be executed by the first node provided in the second aspect of the embodiment of the present application, and for the specific implementation steps of the second aspect of the embodiment of the present application and each possible implementation manner of the second aspect of the embodiment of the present application, and the beneficial effects brought by each possible implementation manner of the second aspect of the embodiment of the present application, reference may be made to descriptions in each possible implementation manner of the first aspect, which are not repeated herein.
In a third aspect, an embodiment of the present application provides a method for acquiring a region of interest, which may be used in the field of big data in computer technology. The method is applied to an acquisition system of an interested region, the system comprises a plurality of first nodes and second nodes, the detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region comprises a plurality of detection units, and the method comprises the following steps: the second node receives first indication information sent by each first node, wherein the first indication information comprises a clustering result, the clustering result indicates at least one first interested region in a sub-detection region corresponding to the first node, and the first interested region comprises a detection unit of a target class; and the second node performs clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
The steps executed by the second node in each possible implementation manner of the first aspect may also be executed by the second node provided by the third aspect of the embodiment of the present application, and for the specific implementation steps of the third aspect of the embodiment of the present application and each possible implementation manner of the third aspect, and the beneficial effects brought by each possible implementation manner, reference may be made to descriptions in each possible implementation manner of the first aspect, which are not described in detail herein.
In a fourth aspect, an embodiment of the present application provides a method for acquiring a region of interest, which may be used in the field of big data in computer technology. The method is applied to an acquisition system of an interested region, the system comprises a plurality of first nodes and second nodes, the first nodes and the second nodes are respectively provided with a stream processing engine, a detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection regions comprise a plurality of detection units, and the method comprises the following steps: each first node clusters a plurality of detection units included in the sub-detection area in a stream processing mode based on real-time data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first interested area corresponding to the sub-detection area, and the first interested area comprises detection units of a target class; each first node sends first indication information to the second node, wherein the first indication information comprises a clustering result; and the second node executes clustering operation on the first region of interest according to the clustering result to obtain at least one second region of interest corresponding to the detection region.
In a possible implementation manner of the fourth aspect, the second node performs a clustering operation on the first region of interest according to a clustering result, including: and the second node executes clustering operation on the first region of interest according to the clustering result and the target detection unit, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection areas in the detection area.
The first node provided in the fourth aspect of the embodiment of the present application may further perform the steps performed by the first node in each possible implementation manner of the first aspect, and the second node may further perform the steps performed by the second node in each possible implementation manner of the first aspect, where for the specific implementation steps of each possible implementation manner of the fourth aspect and the fourth aspect of the embodiment of the present application, and the beneficial effects brought by each possible implementation manner, reference may be made to descriptions in each possible implementation manner of the first aspect, and will not be repeated herein.
In a fifth aspect, an embodiment of the present application provides a system for acquiring a region of interest, which may be used in the field of big data in computer technology. The acquisition system of the region of interest comprises a plurality of first nodes and second nodes, the detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, and the sub-detection region comprises a plurality of detection units; each first node is used for clustering a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest includes detection units of a target class; each first node is further configured to send first indication information to the second node, where the first indication information includes a clustering result; and the second node is used for performing clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
The first node provided in the fifth aspect of the embodiment of the present application may further perform the steps performed by the first node in each possible implementation manner of the first aspect, and the second node may further perform the steps performed by the second node in each possible implementation manner of the first aspect, and for the specific implementation steps of the fifth aspect of the embodiment of the present application and each possible implementation manner of the fifth aspect, and the beneficial effects brought by each possible implementation manner, reference may be made to descriptions in each possible implementation manner of the first aspect, which are not repeated herein.
In a sixth aspect, an embodiment of the present application provides an apparatus for acquiring a region of interest, which may be used in the field of big data in computer technology. The method and the device for acquiring the region of interest are applied to a first node in a system for acquiring the region of interest, the system comprises a plurality of first nodes and a plurality of second nodes, a detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region is divided into a plurality of detection units, and the device comprises: the clustering module is used for clustering a plurality of detection units included in the sub-detection area based on the data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest comprises the detection units of the target class; the sending module is used for sending first indication information to the second node, wherein the first indication information comprises a clustering result, the first indication information is used for indicating the first node to execute clustering operation on the first region of interest by using the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, and the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
The step performed by the first node in each possible implementation manner of the first aspect may also be performed by the device for acquiring a region of interest provided by the sixth aspect of the embodiment of the present application, and for the specific implementation steps of the sixth aspect of the embodiment of the present application and each possible implementation manner, and the beneficial effects brought by each possible implementation manner, reference may be made to descriptions in each possible implementation manner of the first aspect, which are not described in detail herein.
In a seventh aspect, an embodiment of the present application provides a method and apparatus for acquiring a region of interest, which may be used in the field of big data in computer technology. The method and the device for acquiring the region of interest are applied to a second node in a system for acquiring the region of interest, the system comprises a plurality of first nodes and second nodes, a detection region comprises a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region is divided into a plurality of detection units, and the method and the device for acquiring the region of interest comprise the following steps: the receiving module is used for receiving first indication information sent by each first node, the first indication information comprises a clustering result, the clustering result indicates at least one first interested area in the sub-detection area corresponding to the first node, and the first interested area comprises a detection unit of a target class; and the clustering module is used for performing clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
The step performed by the second node in each possible implementation manner of the first aspect may also be performed by the acquiring device for a region of interest provided by the seventh aspect of the embodiment of the present application, and for the specific implementation steps of the seventh aspect of the embodiment of the present application and each possible implementation manner, and the beneficial effects brought by each possible implementation manner, reference may be made to descriptions in each possible implementation manner of the second aspect, which are not described in detail herein.
In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, which when executed on a computer, causes the computer to perform the method for acquiring a region of interest according to any one of the first to fourth aspects.
In a ninth aspect, an embodiment of the present application provides a computer program product comprising a program which, when run on a computer, causes the computer to perform the method for acquiring a region of interest according to any one of the first to fourth aspects above.
In a tenth aspect, an embodiment of the present application provides a first node, which may include a processor, where the processor is coupled to a memory, and the memory stores program instructions, and the memory causes a computer to execute the steps executed by the first node in the method for acquiring a region of interest according to any one of the first to fourth aspects.
In an eleventh aspect, an embodiment of the present application provides a second node, which may include a processor, where the processor is coupled to a memory, and the memory stores program instructions, and the memory causes a computer to execute the steps executed by the second node in the method for acquiring a region of interest according to any one of the first to fourth aspects.
In a twelfth aspect, an embodiment of the present application provides a circuit system, including a processing circuit configured to perform the method for acquiring a region of interest according to any one of the first to fourth aspects.
In a thirteenth aspect, embodiments of the present application provide a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, transmitting or processing data and/or information involved in the above method. In one possible design, the chip system further includes a memory for holding program instructions and data necessary for the server or the communication device. The chip system can be composed of chips, and can also comprise chips and other discrete devices.
Drawings
FIG. 1 is a system architecture diagram of an acquisition system for a region of interest according to an embodiment of the present application;
Fig. 2 is a schematic flow chart of a method for acquiring a region of interest according to an embodiment of the present application;
fig. 3a is a schematic diagram of a detection unit in the method for acquiring a region of interest according to an embodiment of the present application;
fig. 3b is a schematic diagram of a detection unit in the method for acquiring a region of interest according to an embodiment of the present application;
fig. 3c is a schematic diagram of a detection unit in the method for acquiring a region of interest according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of generating a graph model corresponding to a detection region in the method for acquiring a region of interest according to the embodiment of the present application;
FIG. 5 is a schematic flow chart of generating a graph model corresponding to a detection region in the method for acquiring a region of interest according to the embodiment of the present application;
FIG. 6 is a schematic flow chart of generating a graph model corresponding to a detection region in the method for acquiring a region of interest according to the embodiment of the present application;
fig. 7 is a schematic diagram of second indication information in the method for acquiring a region of interest according to the embodiment of the present application;
FIG. 8 is a schematic diagram of a plurality of sub-detection regions in a method for acquiring a region of interest according to an embodiment of the present application;
fig. 9 is a schematic diagram of a detection unit of a target class in the method for acquiring a region of interest according to an embodiment of the present application;
Fig. 10 is a schematic diagram of first indication information and second indication information in a method for acquiring a region of interest according to an embodiment of the present application;
FIG. 11 is a schematic diagram of a set M and a set N in a method for acquiring a region of interest according to an embodiment of the present application;
fig. 12 is a schematic diagram of a second region of interest in the method for acquiring a region of interest according to an embodiment of the present application;
fig. 13 is a schematic diagram of a second region of interest in the method for acquiring a region of interest according to an embodiment of the present application;
fig. 14 further provides a method for acquiring a region of interest according to an embodiment of the present application;
FIG. 15 is a schematic structural diagram of an acquisition system for a region of interest according to an embodiment of the present application;
fig. 16 is a schematic structural diagram of an acquiring device for a region of interest according to an embodiment of the present application;
fig. 17 is a schematic structural diagram of an acquiring device for a region of interest according to an embodiment of the present application;
fig. 18 is a schematic structural diagram of a computing node according to an embodiment of the present application.
Detailed Description
The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.
The embodiment of the application can be applied to the field of big data of computer technology, in particular to the identification of the region of interest in the detection region according to the data acquired from the detection region, wherein the specific expression form of the region of interest is determined by a specific application scene, and the specific expression form refers to a space region which meets the target rule set by a user in the whole detection region.
As an example, in the field of communication, for example, a network anomaly area within a detection area may be identified based on data transmitted by a base station within the detection area, and "network anomaly area" is one example of an area of interest. The data sent by the base stations in the detection area may be session data reported by the base stations in the detection area, measurement reports (measurement report, MR) reported by the base stations in the detection area, or other types of data.
As another example, in the intelligent traffic field, for example, position information of vehicles in a detection area may be acquired, and an area in the detection area where the vehicles are dense (i.e., one example of an area of interest) may be identified to achieve more efficient traffic scheduling.
As another example, in the area of smart cities, for example, an online taxi service may be provided to a user, and location information of a communication device issuing a taxi request within a detection area (i.e., an area providing the online taxi service) may be acquired to determine an area where the communication devices are dense (i.e., one example of an area of interest) from within the detection area, thereby deploying taxis within the city.
As another example, for example, in the smart city field, various types of sensors may be provided in the detection area to collect environmental data in the detection area, and identify an area of interest in the detection area based on the environmental data acquired from the detection area, where the area of interest may be an area of poor comprehensive environmental quality, an area of good comprehensive environmental quality, or an area satisfying a monitoring condition, or the like, in the detection area.
In all of the above-mentioned scenarios, there is a need to locate a region of interest within the entire detection area based on data acquired from the detection area. It should be noted that the foregoing examples are merely for convenience of understanding the application scenario of the embodiments of the present application, and are not intended to be exhaustive of the application scenario of the embodiments of the present application.
In the embodiment of the application, various application scenes of the embodiment of the application are provided, and the implementation flexibility of the scheme is improved.
Based on the above description, the embodiment of the application provides a method for acquiring a region of interest. Before describing the method for acquiring the region of interest according to the embodiment of the present application in detail, a description is first given of a system for acquiring the region of interest according to the embodiment of the present application with reference to fig. 1. Referring to fig. 1, fig. 1 is a system architecture diagram of a system for acquiring a region of interest according to an embodiment of the present application. The acquisition system of the region of interest comprises a plurality of first nodes 101 and second nodes 102, wherein the first nodes 101 and the second nodes 102 are connected through wired or wireless communication. Wherein the first node 101 may also be referred to as a slave node, and the second node 102 may also be referred to as a master node; each node in the acquisition system 100 of the region of interest may be a physical machine or a virtual machine.
As shown in fig. 1, S1, each first node 101 clusters a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area, to obtain a clustering result, and the clustering result indicates at least one first region of interest corresponding to the sub-detection area. S2, each first node 101 sends first indication information to the second node 102, wherein the first indication information comprises a clustering result. S3, the second node 102 performs clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is located on the boundary between different sub-detection regions in the detection region.
In the embodiment of the application, the detection unit in each first interested area and the target detection unit positioned on the boundary between different sub-detection areas in the detection area are adopted in the process of global clustering of the second node, so that the data volume processed by the second node in the process of global clustering is greatly reduced, the communication volume between the second node and the first node is reduced, and the calculation volume of the second node is also reduced; in addition, the calculation amount of the second node in the clustering process is small in the scheme, so that the method and the device are beneficial to determining the region of interest in the detection region in real time.
The detailed description of the specific implementation flow of the method for acquiring the region of interest provided by the embodiment of the present application is provided below, and it should be noted that, in the system for acquiring the region of interest provided by the embodiment of the present application, the method for acquiring the region of interest provided by the embodiment of the present application is explained only by taking the interaction flow between one of the plurality of first nodes and the second node as an example in the subsequent embodiment, because the steps executed by different first nodes are similar. Specifically, referring to fig. 2, fig. 2 is a schematic flow chart of a method for acquiring a region of interest according to an embodiment of the present application, where the method for acquiring a region of interest according to the embodiment of the present application may include:
201. The second node acquires second indication information corresponding to the detection area, and divides the detection area into a plurality of sub-detection areas, wherein the second indication information comprises the close relation among a plurality of different detection units in the detection area.
In the embodiment of the application, before the second node locates the region of interest in the detection region, the second node needs to acquire a plurality of detection units included in the detection region, so as to acquire second indication information corresponding to the detection region.
The second node partitions the whole detection area to divide the whole detection area into N sub-detection areas corresponding to the N first nodes one by one, and generates a mapping relation between the detection units in each sub-detection area and each first node.
In many application scenarios, the amount of raw data acquired from the detection area is huge, and the whole detection area is generally required to be divided into a plurality of detection units in the spatial dimension, and then the region of interest in the detection area is located, where a "detection unit" refers to a minimum spatial area when the detection area is subjected to data statistics, that is, a minimum monitoring unit in the process of identifying the region of interest in the detection area.
The second indication information includes a proximity relationship between a plurality of different detection units within the detection area. The detection units with proximity relation in the embodiment of the application may include detection units with coverage areas contacting each other (i.e. adjacent to each other); optionally, the detection units having a proximity relation may further include a detection unit having a distance less than a distance threshold.
For the procedure of "acquiring a plurality of detection units included in the detection area". One detection unit in the embodiment of the application can be specifically expressed as any one of the following: the spatial region corresponding to the regular network, the spatial region corresponding to the irregular polygonal mesh, the spatial region determined based on the location information of the entity device in the detection region, or other types of detection units, etc., are not meant to be exhaustive herein.
In some application scenarios, the second node may divide the entire detection area into a plurality of rule networks, and the spatial area corresponding to each rule network is regarded as one detection unit in the detection area.
As an example, in an application scenario, for example, search behavior information on each terminal device in the detection area is acquired to obtain an area in the detection area that is interested in a specific application program, where the second node may divide the entire detection area into a plurality of rule networks and count the data acquired in each detection unit (i.e. the spatial area corresponding to each rule grid), it should be understood that this is only for convenience of understanding the present solution, and is not limited to this solution.
For a more visual understanding of the present solution, the following describes the form of the detection unit in the embodiment of the present application with reference to fig. 3a to 3 c. Referring to fig. 3a, fig. 3a is a schematic diagram of a detection unit in a method for acquiring a region of interest according to an embodiment of the present application. The detection units in the regular grid shape are shown in fig. 3a, and different rule networks (i.e. different detection units) are not overlapped with each other, so that statistics or aggregation can be performed on data corresponding to each rule grid, and it should be understood that the example in fig. 3a is only for facilitating understanding of the present solution, and is not limited to the present solution.
In other application scenarios, the second node may acquire a plurality of detection units included in the entire detection area, where each detection unit is specifically represented by a spatial area corresponding to an irregular polygonal mesh.
As an example, in another application scenario, if the network abnormal area in the detection area is located based on the measurement report reported by the base station in the detection area, the location information of the plurality of communication devices in the detection area and the network signal strength of the communication devices may be obtained based on the measurement report, and in the foregoing application scenario, the second node may divide the detection area based on the administrative division, the traffic autonomous domain (traffic autonomous zone, TAZ) or other rules in the detection area, so that each detection unit may be specifically represented as a spatial area corresponding to an irregular polygon mesh.
With continued reference to fig. 3b, fig. 3b is a schematic diagram of a detection unit in the method for acquiring a region of interest according to an embodiment of the present application. The detection units in the shape of an irregular polygonal mesh are shown in fig. 3b, each detection unit has an irregular closed space boundary, and different detection units are not overlapped with each other, so that statistics or aggregation can be performed on data corresponding to each detection unit, and it should be understood that the example in fig. 3b is only for convenience in understanding the present solution, and is not limited to the present solution.
In other application scenarios, the detection area includes a plurality of entity devices, where the plurality of entity devices are distributed in the detection area in the form of discrete points, and the second node may further determine, based on location information of each entity device in the detection area, a spatial area of a detection unit corresponding to the entity device.
Specifically, the determining, by the second node, the spatial region of the detection unit corresponding to the entity device may include: the second node determines the Thiessen polygon corresponding to each entity device as a space region of the detection unit corresponding to the entity device; or the second node determines the space area of the detection unit corresponding to each entity device according to the actual coverage area of the entity device; or, the second node determines, according to other rules, a spatial area of the detection unit corresponding to the entity device, and so on, which is not exhaustive herein.
Among them, the Thiessen polygon has a graph (Voronoi diagram), which may be called Feng Luo Noil, which is a continuous polygon consisting of a set of perpendicular bisectors of straight lines connecting two adjacent points; i.e., abstracting each physical device within the detection area as a point within the detection area, and determining a Thiessen polygon corresponding to each point (i.e., each physical device) based on the plurality of points within the detection area.
Referring to fig. 3c again, fig. 3c is a schematic diagram of a detection unit in the method for acquiring a region of interest according to an embodiment of the present application. The detection unit shown in fig. 3c is a spatial area determined based on the location information of the entity devices in the detection area, and the plurality of entity devices are distributed in the detection area in the form of discrete points, and in fig. 3c, the detection unit corresponding to the entity device is determined as a detection unit corresponding to the entity device by taking a tawsen polygon corresponding to the entity device in the detection area as an example, it should be noted that the detection unit corresponding to the entity device may also be determined based on other manners, which is not exhaustive herein.
The process of "acquiring the second instruction information corresponding to the detection area" is directed. The second node may model all detection areas within the detection area to construct a Graph (Graph) model corresponding to the detection area, and generate second indication information based on the Graph model.
Wherein vertices of the graph model represent a plurality of detection units within the detection area, and edges of the graph model indicate proximity relationships between a plurality of different detection units within the detection area. That is, if two detection units have a proximity relationship, the two detection units are connected by the edge of the graph model; if the two detection units do not have a proximity relation, the two detection units are not connected by the edges of the graph model.
The second indication information may be embodied in a form of a table, an array, a graph model or other data form, which is not exhaustive herein. As an example, if the second indication information is represented in the form of a table, the foregoing table may include two columns, where the first column is used to record the identification information of each detection unit in the detection area, and the second column is used to record the identification information of all detection units having a proximity relationship with each detection unit, and the foregoing example is merely for convenience in understanding the present solution, and is not intended to limit the present solution.
Because one detection unit can be a regular grid, an irregular polygonal grid or a space region determined based on entity equipment in a detection region, the methods for constructing the graph model corresponding to different types of detection units are different.
Specifically, after determining the coverage area of each detection unit in the detection area, the second node may use, for any one detection unit in the detection area (hereinafter referred to as "first detection unit" for convenience of description), the center point of the first detection unit or the center of gravity point of the first detection unit as a vertex representing the first detection unit in the case where the first detection unit is embodied as a regular grid.
In case the first detection unit is embodied as an irregular polygonal mesh, the second node may take the center of gravity point of the first detection unit as a vertex representing the first detection unit. In case the first detection unit is embodied as a spatial region determined based on the physical devices within the detection region, the second node may take the location point of the physical device within each detection unit as the vertex of the first detection unit.
The second node performs the above operation on each detection unit within the detection area, thereby obtaining all points in the graph model corresponding to the detection area.
The second node determines a plurality of detection units in direct contact with the coverage area of the first detection unit as detection units having a proximity relation to the first detection unit. Optionally, the second node may further calculate a target distance between a point of the first detection unit and any point in the graph model, and if the target distance is less than or equal to the distance threshold, the second node determines that the first detection unit has a proximity relationship with the detection unit represented by the target point; if the target distance is greater than the distance threshold, the second node determines that the first detection unit and the detection unit represented by the target point have no proximity relation; the second node performs the foregoing operation on each point in the graph model to screen out detection units having a proximity relation with the first detection unit from among a plurality of detection units included in the detection area. After determining all the detection units having a proximity relation to the first detection unit, the second node may set an edge between the first detection unit and all the detection units having a proximity relation.
Through the mode, the second node can obtain the proximity relation of each detection unit in the detection area, so that a graph model corresponding to the whole detection area is constructed.
In order to more intuitively understand the present solution, the implementation manner of constructing the graph model corresponding to the detection area, the second indication information and the multiple sub-detection areas is described below with reference to fig. 4 to fig. 8, and fig. 4 is a schematic flow diagram of generating the graph model corresponding to the detection area in the method for acquiring the region of interest according to the embodiment of the present application. In fig. 4, each detection unit is embodied as a regular grid, where D1, the second node uses the center point of the regular network (i.e., the detection unit) as the vertex of the graph representing the detection unit, so as to abstract the multiple detection units in the detection area as vertices of the graph model.
D2, the second node regards the detection units in contact with the spatial extent of the detection unit No. 7 (i.e. one example of the first detection unit) (i.e. the spatial extent is contiguous) as detection units having a proximity relation to the first detection unit, i.e. detection units No. 2, 6, 8 and 12 in the figure. The second node regards all detection units which are not adjacent to the detection unit 7 but have a distance smaller than the distance threshold value as detection units which have a proximity relation with the first detection unit, namely detection units 1, 3, 11 and 13 in the illustration, and detection units 1, 2, 3, 6, 8, 11, 12 and 13 which have a proximity relation with the detection unit 7 are obtained through synthesis. The second node performs the foregoing operation on each detection unit in the detection area, and obtains a graph model corresponding to the entire detection area. It should be understood that the example in fig. 4 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
Referring to fig. 5, fig. 5 is a schematic flow chart of generating a graph model corresponding to a detection region in the method for acquiring a region of interest according to an embodiment of the present application. In fig. 5, each detection unit is embodied as an irregular polygonal mesh, where the E1 and the second node take the center of gravity point of the irregular polygonal network (i.e. the detection unit) as the vertex of the graph representing the detection unit, so as to abstract all the detection units in the detection area as the vertices of the graph model. The manner in which E2 and the second node determine the proximity relation of the detection unit is similar to that described in the corresponding embodiment of fig. 4, and will not be described here again. It should be understood that the example in fig. 5 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
Referring to fig. 6, fig. 6 is a schematic flow chart of generating a graph model corresponding to a detection region in the method for acquiring a region of interest according to the embodiment of the application. In fig. 6, taking a Thiessen polygon determined by each detection unit including the location information of the entity devices in the detection area as an example, the F1 and the second node take the location point of the entity devices in the detection unit as the vertex of the graph model. The manner in which the F2 and the second node determine the proximity relation of the detection unit is similar to that described in the corresponding embodiment of fig. 4, and will not be described herein. It should be understood that the example in fig. 6 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
In the embodiment of the application, a plurality of detection units in the whole detection area are abstracted into a graph model, vertexes of the graph model are used for representing the plurality of detection units in the detection area, edges of the graph model are used for indicating the adjacent relation among the plurality of different detection units in the detection area, and each detection unit is specifically expressed as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region. Namely, under the condition that the detection unit is embodied in various forms, abstract modeling can be carried out on the detection area, so that more application scenes can be covered, and the implementation flexibility of the scheme is improved.
With continued reference to fig. 7, fig. 7 is a schematic diagram of second indication information in the method for acquiring a region of interest according to an embodiment of the present application. Fig. 7 includes left and right sub-schematic diagrams. The left sub-schematic diagram of fig. 7 shows a plurality of detection units within the detection area, including detection units represented by A1, A2, A3, A4, B1, B2, B3, B4, B5, C1, C2, C3, and C4. The right sub-schematic diagram of fig. 7 shows the second indication information corresponding to the detection area, and it should be understood that the example of fig. 7 is only for convenience of understanding the present solution, and is not limited to the present solution.
With continued reference to fig. 8, fig. 8 is a schematic diagram of a plurality of sub-detection regions in the method for acquiring a region of interest according to an embodiment of the present application. Fig. 8 includes left and right sub-schematic diagrams. The left sub-schematic diagram of fig. 8 shows a diagram model formed by a plurality of detection units in the detection area, the right sub-schematic diagram of fig. 8 shows 3 sub-detection areas included in the detection area, namely, a sub-detection area a, a sub-detection area B and a sub-detection area C, respectively, the sub-detection area a includes detection units represented by A1, A2, A3 and A4, the sub-detection area B includes detection units represented by B1, B2, B3, B4 and B5, and the sub-detection area C includes detection units represented by C1, C2, C3 and C4, and it should be understood that the example in fig. 8 is only for facilitating understanding of the scheme and is not intended to limit the scheme.
202. The second node transmits second indication information to the first node.
In some embodiments of the present application, the second node may send the second indication information to each first node, and the meaning and the concrete form of the second indication information may refer to the description in step 201.
203. The first node determines a detection unit of the target class from a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area.
In the embodiment of the present application, each first node may be configured with a target rule for determining whether the first node is a region of interest, and based on data obtained from the sub-detection regions, determine whether any detection unit (for convenience of description, hereinafter referred to as "first detection unit") in the sub-detection regions meets the target rule according to the target rule, and if the first node determines that the first detection unit meets the target rule, the first detection unit is determined to be a detection unit of a target class, that is, the first detection unit is a detection unit in the first region of interest; if the first node determines that the first detection unit does not meet the target rule, the first detection unit is not a detection unit of the target class, i.e. the first detection unit is not a detection unit in the first region of interest.
After the first node performs the above operation on each detection unit in the responsible sub-detection area, the first node may perform a clustering operation according to the detection units of the target class in the sub-detection area, to obtain at least one first region of interest corresponding to the sub-detection area, where each detection unit of each first region of interest is a detection unit of the target class.
The "data obtained from the sub-detection area" may be sent directly to the first node by the communication device in the sub-detection area; the communication device in the sub-detection area may be forwarded to the first node by the second node after being sent to the second node.
Further, in one implementation manner, the "data obtained from the sub-detection area" may be real-time data, and then each first node and each second node need to be deployed with a stream processing engine, and each first node may divide the real-time data corresponding to the first detection unit into different time windows by using a "time window" technology, so as to determine whether the first detection unit meets the target rule according to the real-time data obtained in the same time window.
Furthermore, in some scenarios, after the first node divides the real-time data corresponding to the first detection unit into different time windows, the first node needs to aggregate the real-time data in the same time window, and determine, based on the aggregated data, whether the first detection unit meets the target rule.
In other scenarios, after the first node divides the real-time data corresponding to the first detection unit into different time windows, the first node may also determine whether the first detection unit meets the target rule directly according to the obtained real-time data.
As an example, for example, "real-time data obtained from the sub-detection area" includes real-time voice system data transmitted by base stations in the sub-detection area, one base station corresponds to one detection unit, and since the voice system data itself is statistical data in the coverage area of the base station, it is not necessary to perform the aggregation. "region of interest" refers to a network anomaly region within a sub-detection region; the "target rule for determining whether the network is an abnormal area" may be composed of a time window and a threshold corresponding to a certain performance index in the session data.
For any base station (for convenience of description, hereinafter referred to as "target base station") in the sub-detection area, the first node divides the received voice system data received at different times into different time windows according to the arrival time of the voice system data sent by the target base station, and determines whether the target base station belongs to an abnormal base station according to a target rule, that is, determines whether the category of the detection unit corresponding to the target base station is a target category.
For further understanding of the present solution, the following description will be made in connection with actual data, for example, the target rule may be "the value of the performance report field determined based on the system data acquired within 5 minutes is less than 1", and the base station in the detection unit that satisfies the target rule is determined to be the base station that is abnormal, taking the sub-detection area as the sub-detection area a as an example, where the identification information of the four detection units included in the sub-detection area a is A1, A2, A3, and A4, respectively. The data statistics corresponding to A1, A2, A3 and A4 are shown in table 1 below.
| Identification of detection units | Time stamp | Value of performance report field | Judgment result |
| A1 | 2020-01-01 00:05:00 | -1 | Abnormality of |
| A2 | 2020-01-01 00:05:00 | -3 | Abnormality of |
| A3 | 2020-01-01 00:05:23 | 1 | Normal state |
| A4 | 2020-01-01 00:05:23 | 2 | Normal state |
TABLE 1
Referring to table 1 above, it can be seen that the base station in the two detection units A1 and A2 is an abnormal base station, and the base station in the two detection units A3 and A4 is a normal base station, that is, the two detection units A1 and A2 are determined as the detection units of the target class, it should be understood that the examples in table 1 are only for convenience in understanding the present scheme.
In the embodiment of the application, the streaming processing engines are deployed on the first node and the second node, so that real-time data in the detection area can be processed, and timeliness of a positioning process of the region of interest in the detection area is improved.
In another implementation, the "data obtained from the sub-detection area" may also be not real-time data (i.e., may be offline data), and then the offline data obtained from the first detection unit may be divided into a plurality of time periods, so as to determine whether the first detection unit meets the target rule according to the data in one time period.
For a more intuitive understanding of the present solution, please refer to fig. 9, fig. 9 is a schematic diagram of a detection unit of a target class in the method for acquiring a region of interest according to an embodiment of the present application. As shown in fig. 9, A1 and A2 are detection units of the target class in the sub-detection area a, B1, B2 and B4 are detection units of the target class in the sub-detection area B, and C1 and C4 are detection units of the target class in the sub-detection area C, it should be understood that the example in fig. 9 is only for convenience of understanding the present solution, and is not intended to limit the present solution.
204. And the first node executes clustering operation according to the detection unit of the target category in the sub-detection area to obtain a clustering result, and the clustering result indicates at least one first region of interest corresponding to the sub-detection area.
In the embodiment of the present application, after each first node determines a detection unit of a target class from a plurality of detection units included in a sub-detection area, a clustering operation may be performed to obtain a clustering result, where the clustering result indicates at least one first region of interest corresponding to the sub-detection area.
Optionally, if step 202 is executed, the second node may further generate identification information of each sub-detection area, and allocate the identification information of the sub-detection area to which each detection unit belongs to each detection unit, so as to establish a target mapping relationship between each sub-detection area and a plurality of detection units, where the second node sends the target mapping relationship to each first node. In the process of executing the clustering operation, each first node may further determine, according to the detection units of the target categories in the sub-detection areas and the second indication information, a target detection unit corresponding to a boundary of the sub-detection areas, and send identification information of the target detection unit corresponding to the boundary of the sub-detection areas to the first node. The category of the target detection unit is a target category and is located on the boundary between different sub-detection areas in the detection area.
Specifically, in order to ensure that the recognition result of the local region of interest generated by each first node may be combined between different sub-detection regions, redundant routing may be performed on the detection units of each target class in the detection region before the first node performs the clustering operation. Aiming at any one target type detection unit (hereinafter referred to as a second detection unit for convenience of description) in a sub-detection area in which a first node is responsible, the first node acquires identification information of a sub-detection partition to which the second detection unit belongs, and records a corresponding relationship between the identification information of the second detection unit and the identification information of the sub-detection partition to which the second detection unit belongs; the first node acquires all detection units with a proximity relation with the second detection unit from the second indication information.
For any one of all the detection units (hereinafter referred to as "target neighboring units" for convenience of description) having a proximity relation with the second detection unit and being of the target class, if the identification information of the sub-detection partition to which the target neighboring unit belongs and the identification information of the sub-detection partition to which the second detection unit belongs are identical, skipping.
If the identification information of the sub-detection partition to which the target adjacent unit belongs is inconsistent with the identification information of the sub-detection partition to which the second detection unit belongs, the first node may perform any one or more of the following operations: transmitting the identification information of the second detection unit to a node for processing the target adjacent unit to instruct the node for processing the target adjacent unit to record the correspondence between the identification information of the second detection unit and the identification information of the sub-detection area to which the target adjacent unit belongs;
or, the node for processing the target adjacent unit is requested for the identification information of the target adjacent unit, and the corresponding relation between the identification information of the sub-detection area to which the second detection unit belongs and the identification information of the target adjacent unit is recorded.
In order to more intuitively understand the present solution, taking the detection unit B1 of the target class as an example, according to the second indication information, it is known that the detection units having the proximity relationship with the detection unit B1 include B2, B5, A1 and A4, and since the detection unit B2 and the detection units B5 and B1 all belong to the sub-detection area B, the first node responsible for the sub-detection area B skips the detection unit B2 and the detection unit B5. Since the detection units A1 and A4 belong to the sub-detection area a, and the sub-detection area a and the sub-detection area B belong to different sub-detection areas, the detection unit B1 is determined to be a detection unit of a target class located on the boundary of the sub-detection area a and the sub-detection area B.
The first node responsible for the sub-detection area B may send the detection unit B1 identification information and the sub-detection area B to the first node responsible for the sub-detection area a, where the foregoing information may be in the form of binary data.
The first node responsible for sub-detection area B performs the above-described operation on the detection units of each target class within sub-detection area B to complete redundant routing of the detection units of all target classes within sub-detection area B.
After each first node in the whole acquisition system of the region of interest completes the redundant routing operation, the data in the first node responsible for each sub-detection area in fig. 9 can be as follows in table 2.
| Identification of sub-detection areas | Results of redundant routing |
| A | (A，A1)(A，A2)(A，B1)(A，B2)(A，C1) |
| B | (B，B1)(B，B2)(B，B4)(B，A1)(B，C1) |
| C | (C，C1)(C，C4)(C，A1)(C，A2)(C，B2) |
TABLE 2
The A, B and C are the identification information of the sub-detection area a, the sub-detection area B and the sub-detection area C, the detection units corresponding to the "redundant routing result" are all detection units of the target class, the first node responsible for the sub-detection area a can obtain the data of the second row in table 2, the first node responsible for the sub-detection area B can obtain the data of the third row in table 2, and the first node responsible for the sub-detection area C can obtain the data of the fourth row in table 2, which should be understood that the example in table 2 is only for facilitating understanding the scheme and is not limited to the scheme.
A process of clustering operations is performed for the first node. And each first node can execute the clustering operation according to the acquired redundant routing result, and in the clustering process, the identification information of the target detection units in the sub-detection area is generated.
Specifically, when each first node identifies a new first region of interest, generating identification information of the new first region of interest, and performing clustering operation by taking a local target class detection unit as a starting point to obtain at least one first region of interest in a sub-detection region; the identification information of each first region of interest and the identification information of each detection unit included in each first region of interest are obtained.
Taking the identification of the local interested area in the sub-detection area B of the first node as an example, the redundant routing result obtained by the first node in charge of the sub-detection area B takes the identification information of the sub-detection area B as a key, and the form may be a binary group (B, the identification information of the detection unit), so that B' is the identification information of the sub-detection unit to which the detection unit belongs. When B and B' are consistent, the detection unit is a local detection unit; otherwise, the detection unit is not a local detection unit (also may be referred to as a non-local detection unit).
Optionally, during the clustering operation performed by the first node, it may be determined whether each first region of interest within the sub-detection regions belongs to a region of interest to be merged or to a global region of interest. If all the detection units in a certain first region of interest are local detection units, the first region of interest belongs to a global region of interest, and if a target detection unit exists in a certain first region of interest, the first region of interest belongs to a region of interest to be combined.
A process of determining identification information of the target detection unit for the first node. Specifically, for any one detection unit (hereinafter referred to as "third detection unit" for convenience of description) in the redundant routing result obtained by the first node, if there is a non-local detection unit in the detection units having a proximity relation with the third detection unit, or the third detection unit is a non-local detection unit, it is indicated that the third detection unit is a detection unit located at a boundary of a different sub-detection area, that is, the third detection unit is a target detection unit in the sub-detection area.
The first node may record a piece of target information, where the target information includes identification information of the different sub-detection areas, identification information of the first region of interest to which the target detection unit belongs, and identification information of the target detection unit.
The first node traverses each detection unit in the result of the redundant routing, may obtain the multi-entry label information, and sends the multi-entry label information to the second node. As an example, for example, an item of target information may be embodied as (a-B, a_1, A1), the aforementioned target information indicating that the detection unit A1 is located on the boundary between the sub-detection area a and the sub-detection area B, and the identification information of the first region of interest to which the detection unit A1 belongs is a_1, it should be understood that the aforementioned example is merely for convenience of understanding the present solution, and is not intended to limit the present solution.
It should be noted that, in the actual execution process, the "process of the first node performing the clustering operation" and the "process of the first node generating the fourth indication information" may be performed in a crossing manner, which is not limited herein.
In the embodiment of the application, each first node generates the identification information of the target detection unit corresponding to the boundary of the sub-detection area, and sends the identification information of the target detection unit corresponding to the boundary of the sub-detection area to the second node, and the second node performs the summarizing operation, so that the calculation amount executed by the second node is further reduced; and the different first nodes work in parallel, so that the time consumed by the whole calculation process is reduced, and the efficiency of the acquisition process of the region of interest is improved.
205. The first node sends first indication information to the second node, wherein the first indication information comprises a clustering result.
In the embodiment of the present application, after each first node obtains at least one first region of interest corresponding to a responsible sub-detection region, the first node sends first indication information to the second node, where the first indication information at least includes a clustering result. Optionally, the first indication information sent by each first node may be further used to indicate the target detection unit corresponding to the boundary of the sub-detection area that each first node is responsible for, that is, the first indication information sent by each first node may further include identification information of each target detection unit, identification information of the first region of interest to which each target detection unit belongs, and identification information of two different sub-detection areas corresponding to each target detection unit.
Correspondingly, the second node can receive the first indication information sent by each first node, so that a plurality of first interested areas in the whole detection area can be determined, and identification information of all target class detection units in the whole detection area can be obtained. Optionally, the second node may also acquire new identities of all target detection units in the entire detection area.
Optionally, each first node may also inform the second node whether each first region of interest belongs to a region of interest to be merged or to a global region of interest.
206. And the second node determines a target detection unit according to the clustering result.
In some embodiments of the present application, if the first indication information is not used for indicating the target detection units, the second node may further determine information of the target detection units according to the received clustering result, where the information of the target detection units is used for positioning the target detection units, and the information of the target detection units may include identification information of a first region of interest to which each target detection unit belongs and identification information of two different sub-detection regions corresponding to each target detection unit.
Specifically, the second node may generate the information of the target detection unit according to the first indication information, the identification information of the detection units of all target categories in each sub-detection area, and the identification information of each sub-detection area. The specific implementation manner of the second node to execute the foregoing operation may refer to the specific implementation manner of the "first node generates the target information", which is not described herein in detail.
To further understand the "clustering result and information of the target detection unit", the following description is made with reference to table 3 and fig. 10.
TABLE 3 Table 3
Referring to table 3, the identification information of the four first regions of interest is a_1, b_1, c_1, and c_2, where a_1, b_1, and c_1 are the first regions of interest to be combined, and after obtaining the clustering result, the second node may obtain the identification information of the detection unit in each first region of interest. After the information of the target detection units is obtained, the identification information of each target detection unit and the identification information of the first region of interest to which each target detection unit belongs are known, wherein each target detection unit is located on the boundary of which two sub-detection regions.
Referring to fig. 10, fig. 10 is a schematic diagram of first indication information and second indication information in a method for acquiring a region of interest according to an embodiment of the present application. Included in the left sub-schematic of fig. 10 are detection units within the first region of interest in each sub-detection unit. It can be seen intuitively in the right sub-schematic diagram of fig. 10, which first regions of interest are to be combined, which first regions of interest are not to be combined, and the example in fig. 10 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
207. And the second node executes clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region.
In the embodiment of the present application, since the entire detection area is divided into a plurality of sub-detection areas, each first node can only obtain a local region of interest (i.e., a first region of interest) in the sub-detection area, and in order to combine the first regions of interest segmented in different sub-detection areas, after determining the clustering result and the target detection unit, the second node may perform a clustering operation on the first regions of interest to obtain at least one second region of interest corresponding to the entire detection area, where each second region of interest includes a detection unit of the target class.
Specifically, the second node may determine, according to the clustering result and the target detection unit, a first region of interest to be combined from a plurality of first regions of interest included in the detection region, and determine how to combine from the plurality of first regions of interest to be combined. And further determining identification information of the detection unit included in each second region of interest corresponding to the detection region.
More specifically, after the second node obtains the information of the target detection unit, the set M and the set N may respectively accommodate the data records from two different first regions of interest, where a series of binary tuples are stored in each of the set M and the set N, and two fields of the binary tuples are respectively the identification information of the detection unit and the identification information of the first region of interest to which the detection unit belongs. And respectively placing the multi-item label information in the second indication information into the corresponding sets to finish the initialization of the set M and the set N.
In order to understand the present solution more intuitively, please refer to fig. 11, fig. 11 is a schematic diagram of a set M and a set N in the method for acquiring a region of interest according to an embodiment of the present application. FIG. 11, as will be understood in conjunction with Table 3 above, the left sub-schematic of FIG. 11 represents a set M for placing the corresponding doublet of detection cells in the first region of interest A_1; the left sub-schematic diagram of fig. 11 represents a set N for placing the doublet corresponding to the detection unit in the first region of interest b_1.
The second node pair searches the same detection unit (i.e., A1) from the set N for the detection unit (A1 in the drawing as an example) in any record in the set M, and records the first region of interest a_1 and the first region of interest b_1 and forms a link pair (a_1, b_1), i.e., the first region of interest a_1 and the first region of interest b_1 need to be combined because A1 also exists in the set N.
By way of example in connection with the above description of fig. 10 and table 3, the first region of interest a_1 and the first region of interest b_1 need to be merged, and the first region of interest a_1 and the first region of interest c_1 need to be merged, that is, the first region of interest a_1, the first region of interest b_1 and the first region of interest c_1 need to be merged. It should be understood that the examples herein are for ease of understanding the present solution only and are not intended to limit the present solution.
The second node performs merging operation on the first regions of interest to be merged to obtain a new second region of interest corresponding to the detection region, and generates identification information of the new second region of interest. To further understand the "second region of interest", the following description is provided in connection with table 4.
| First region of interest requiring merging | Detection unit | A second region of interest |
| A_1 | {A1，A2} | G_1 |
| B_1 | {B1，B2，B4} | G_1 |
| C_1 | {C2} | G_1 |
TABLE 4 Table 4
As shown in table 4, the first region of interest a_1, the first region of interest b_1 and the first region of interest c_1 are combined into a new second region of interest, and the identification information of the second region of interest is g_1, which is to be understood that this is only for convenience of understanding the present solution and is not to be used for limiting the present solution.
The second node may also directly determine the global first region of interest as the second region of interest. For a more visual understanding of the present solution, the following description will be made with reference to table 5 and fig. 12, and the following description will refer to the following table 5.
| A second region of interest | Detection unit |
| G_1 | {A1，A2，B1，B2，B4，C2} |
| C_2 | {C4} |
TABLE 5
Referring to fig. 12, fig. 12 is a schematic diagram of a second region of interest in the method for acquiring a region of interest according to the embodiment of the present application. The left sub-schematic of fig. 12 can be understood in conjunction with the description of fig. 11, and the right sub-schematic of fig. 12 is a schematic diagram of two second regions of interest corresponding to the detection regions. It should be understood that the example in fig. 12 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
In the embodiment of the application, a first region of interest to be combined is determined from a plurality of first regions of interest included in a detection region, and different first regions of interest are combined to obtain a second region of interest corresponding to the detection region; the global clustering process is a merging process of different first regions of interest, and is simple to operate and easy to implement.
In the embodiment of the present application, after obtaining the detection unit included in each second region of interest corresponding to the detection region, the second node further determines the coverage range of each second region of interest.
Specifically, the second node may use the spatial convergence operator to combine each detection unit in the same second region of interest one by one, so as to form an outsourcing geometric range of the region of interest, and obtain a range covered by each second region of interest.
For a more intuitive understanding of the present solution, please refer to fig. 13, fig. 13 is a schematic diagram of a second region of interest in the method for acquiring a region of interest according to an embodiment of the present application. The left sub-graph of fig. 13 shows the location points of the detection units within the two second regions of interest, and the right sub-graph of fig. 13 shows the coverage of the two second regions of interest. It should be understood that the example in fig. 13 is merely for facilitating understanding of the present solution, and is not intended to limit the present solution.
In the embodiment of the application, the detection unit in each first region of interest (namely the region of interest obtained by clustering the local region) and the detection unit positioned on the boundary between different sub-detection regions in the detection region are adopted in the process of global clustering of the second node, so that the data volume processed by the second node in the process of global clustering is greatly reduced, the communication volume between the second node and the first node is reduced, and the calculation volume of the second node is also reduced; further, in the scheme, the calculation amount of the second node in the clustering process is small, so that the method can also support the adoption of a streaming mode to determine the region of interest in the detection region in real time.
Referring to fig. 14, fig. 14 further provides a method for acquiring a region of interest according to an embodiment of the present application, where the method for acquiring a region of interest according to the embodiment of the present application may include:
1401. the second node divides the detection area into a plurality of sub-detection areas.
In the embodiment of the present application, the specific implementation manner of step 1401 may refer to the description of step 201 in the corresponding embodiment of fig. 2, which is not repeated here.
1402. The first node clusters a plurality of detection units included in the sub-detection area in a stream processing mode based on real-time data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest comprises detection units of a target class.
1403. The first node sends first indication information to the second node, wherein the first indication information comprises a clustering result.
In the embodiment of the present application, the specific implementation manner of steps 1402 and 1403 may refer to the descriptions in steps 203 to 205 in the corresponding embodiment of fig. 2, which are not described herein.
1404. And the second node determines a target detection unit according to the clustering result, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection areas in the detection area.
In the embodiment of the present application, the specific implementation manner of step 1404 may be referred to as description in step 206 in the corresponding embodiment of fig. 2, which is not repeated herein.
1405. And the second node executes clustering operation on the first region of interest according to the clustering result to obtain at least one second region of interest corresponding to the detection region.
In the embodiment of the present application, step 1404 is an optional step, and if step 1404 is performed or if the first indication information carries information of the target detection unit, step 1405 may include: and the second node executes clustering operation on the first region of interest according to the clustering result and the target detection unit. The specific implementation may be described in step 207 in the corresponding embodiment of fig. 2, which is not described herein.
If step 1404 is not performed and the first indication information does not carry information of the target detection unit, step 1405 may include: the second node acquires identification information of the detection units in each first region of interest, and clusters the detection units in the plurality of first regions of interest again in a stream processing mode based on real-time data obtained from the detection units in each first region of interest, so that at least one second region of interest corresponding to the detection region is obtained, wherein the second region of interest comprises detection units of a target class.
In the embodiment of the application, the streaming processing engines are deployed on the first node and the second node, so that real-time data in the detection area can be processed, and timeliness of a positioning process of the region of interest in the detection area is improved.
In order to better implement the above-described scheme of the embodiment of the present application on the basis of the embodiments corresponding to fig. 1 to 14, a related apparatus for implementing the above-described scheme is further provided below. Referring to fig. 15 in detail, fig. 15 is a schematic structural diagram of a system for acquiring a region of interest according to an embodiment of the present application, where the system 1500 for acquiring a region of interest may include a plurality of first nodes 1501 and second nodes 1502, and a detection area includes a plurality of sub-detection areas, each of the sub-detection areas corresponds to one of the first nodes 1501, and the sub-detection areas include a plurality of detection units.
Each first node 1501 is configured to cluster, based on data obtained from the sub-detection areas, a plurality of detection units included in the sub-detection areas to obtain a clustering result, where the clustering result indicates at least one first region of interest corresponding to the sub-detection areas, and the first region of interest includes a detection unit of a target class; each first node 1501 is further configured to send first indication information to the second node 1502, where the first indication information includes a clustering result. And a second node 1502, configured to perform a clustering operation on the first region of interest according to the clustering result and the target detection unit, to obtain at least one second region of interest corresponding to the detection region, where a category of the target detection unit is a target category and is located on a boundary between different sub-detection regions in the detection region.
In one possible design, the second node 1502 is further configured to send second indication information to each of the first nodes 1501, where the second indication information includes proximity relations between a plurality of different detection units within the detection area; each first node 1501 is further configured to determine a target detection unit corresponding to a boundary of the sub-detection area according to the detection unit of the target class in the sub-detection area and the second indication information, where the first indication information is further configured to indicate the target detection unit.
In one possible design, the second indication information is obtained based on a graph model corresponding to the detection area, the vertex of the graph model representing a plurality of detection units within the detection area, and the edge of the graph model indicating a proximity relationship between a plurality of different detection units within the detection area; wherein each detection unit is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
In one possible design, the first node 1501 and the second node 1502 each have a stream processing engine disposed thereon, and the data obtained from the sub-detection area is real-time data.
In one possible design, the second node 1502 is specifically configured to: determining a first region of interest to be combined from a plurality of first regions of interest included in the detection region according to the clustering result and the target detection unit; and determining at least one second region of interest corresponding to the detection region according to the first regions of interest which are required to be combined.
In one possible design, the data obtained from the sub-detection areas includes any of the following: data transmitted by the base station in the sub-detection area, position information of the communication device in the sub-detection area, or data acquired by the sensor in the detection area.
It should be noted that, in the acquiring system 1500 of the region of interest, the content such as the information interaction and the execution process between the first node 1501 and the second node 1502 are based on the same concept, and specific content can be referred to the description of the foregoing method embodiments of the present application, which is not repeated herein.
Referring to fig. 16, fig. 16 is a schematic structural diagram of an apparatus for acquiring a region of interest according to an embodiment of the present application, the apparatus 1600 for acquiring a region of interest is applied to a first node in a system for acquiring a region of interest, the system includes a plurality of first nodes and a plurality of second nodes, a detection region includes a plurality of sub-detection regions, each sub-detection region corresponds to a first node, the sub-detection region is divided into a plurality of detection units, and the apparatus 1600 for acquiring a region of interest includes: a clustering module 1601, configured to cluster, based on data obtained from the sub-detection areas, a plurality of detection units included in the sub-detection areas to obtain a clustering result, where the clustering result indicates at least one first region of interest corresponding to the sub-detection areas, and the first region of interest includes a detection unit of a target class; the sending module 1602 is configured to send first indication information to the second node, where the first indication information includes a clustering result.
The first indication information is used for indicating the first node to execute clustering operation on at least one first region of interest according to a clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is a target category and is positioned on the boundary between different sub-detection regions in the detection region.
In one possible design, the acquisition device 1600 for a region of interest further includes: the receiving module is used for receiving second indication information sent by the second node, wherein the second indication information comprises a proximity relation among a plurality of different detection units in the detection area; the determining module is used for determining the target detection unit corresponding to the boundary of the sub-detection area according to the detection unit of the target category in the sub-detection area and the second indicating information, and the first indicating information is also used for indicating the target detection unit.
In one possible design, the second indication information is obtained based on a graph model corresponding to the detection region, the vertices of the graph model representing a plurality of detection units within the detection region, and the edges of the graph model indicating proximity relations between a plurality of different detection units within the detection region. Wherein each detection unit is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
In one possible design, the first node and the second node are each deployed with a stream processing engine, and the data obtained from the sub-detection area is real-time data.
It should be noted that, content such as information interaction and execution process between each module/unit in the method device 1600 for acquiring a region of interest, each method embodiment corresponding to fig. 2 to 13 in the present application is based on the same concept, and specific content may be referred to the description in the foregoing illustrated method embodiment of the present application, which is not repeated herein.
Referring to fig. 17, fig. 17 is a schematic structural diagram of an apparatus for acquiring a region of interest according to an embodiment of the present application, where the apparatus 1700 for acquiring a region of interest is applied to a first node in a system for acquiring a region of interest, the system includes a plurality of first nodes and second nodes, the apparatus is configured to determine a region of interest from a detection region, the detection region includes a plurality of sub-detection regions, each sub-detection region corresponds to one first node, the sub-detection region is divided into a plurality of detection units, and the apparatus 1700 for acquiring a region of interest includes: a receiving module 1701, configured to receive first indication information sent by each first node, where the first indication information includes a clustering result, and the clustering result is used to indicate identification information of a detection unit in each first interest area in a sub-detection area corresponding to the first node, and the first interest area includes a detection unit of a target class;
The clustering module 1702 is configured to perform a clustering operation on the first region of interest according to a clustering result and a target detection unit, and obtain at least one second region of interest corresponding to the detection region, where a category of the target detection unit is a target category and is located on a boundary between different sub-detection regions in the detection region.
In one possible design, the apparatus further comprises: the sending module is used for sending second indicating information to the first node, the second indicating information comprises a close relation among a plurality of different detection units in the detection area, the second indicating information is used for the first node to determine a target detection unit corresponding to the boundary of the sub-detection area, and the first indicating information is also used for indicating the target detection unit.
In one possible design, the second indication information is obtained based on a graph model corresponding to the detection area, the vertex of the graph model representing a plurality of detection units within the detection area, and the edge of the graph model indicating a proximity relationship between a plurality of different detection units within the detection area; wherein each detection unit is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
In one possible design, the first node and the second node are each deployed with a stream processing engine, and the data obtained from the sub-detection area is real-time data.
In one possible design, the clustering module 1702 is specifically configured to determine a first region of interest to be merged from a plurality of first regions of interest included in the detection region, and determine at least one second region of interest corresponding to the detection region according to the determined first region of interest to be merged, the first indication information, and the first indication information.
It should be noted that, content such as information interaction and execution process between each module/unit in the method apparatus 1700 for acquiring a region of interest, each method embodiment corresponding to fig. 2 to 13 in the present application is based on the same concept, and specific content may be referred to the description in the foregoing illustrated method embodiment of the present application, which is not repeated herein.
Referring to fig. 18, fig. 18 is a schematic structural diagram of a computing node according to an embodiment of the present application, and the computing node 1800 may be a first node or a second node. Specifically, the computing node 1800 includes: receiver 1801, transmitter 1802, processor 1803 and memory 1804 (where the number of processors 1803 in computing node 1800 may be one or more, as exemplified by one processor in fig. 18), where processor 1803 may include an application processor 18031 and a communication processor 18032. In some embodiments of the application, the receiver 1801, transmitter 1802, processor 1803 and memory 1804 may be connected by a bus or other means.
Memory 1804 may include read only memory and random access memory and provide instructions and data to processor 1803. A portion of the memory 1804 may also include non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 1804 stores a processor and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for performing various operations.
The processor 1803 controls the operation of the compute node. In particular applications, the various components of the compute node are coupled together by a bus system that may include, in addition to a data bus, a power bus, a control bus, a status signal bus, and the like. For clarity of illustration, however, the various buses are referred to in the figures as bus systems.
The methods disclosed in the embodiments of the present application described above may be applied to the processor 1803 or implemented by the processor 1803. The processor 1803 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 1803. The processor 1803 may be a general-purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor, or a microcontroller, and may further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The processor 1803 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 1804, and the processor 1803 reads information in the memory 1804 and, in combination with the hardware, performs the steps of the method described above.
The receiver 1801 may be used to receive input numeric or character information and to generate signal inputs related to the relevant settings of the computing nodes and the control of functions. The transmitter 1802 is operable to output numeric or character information via a first interface; the transmitter 1802 is further operable to send instructions to the disk stack via the first interface to modify data in the disk stack; the transmitter 1802 may also include a display device such as a display screen.
In an embodiment of the present application, in an instance, the processor 1803 is configured to execute a method for acquiring a region of interest performed by the first node in the corresponding embodiment of fig. 2 to 14. In another case, the processor 1803 is configured to perform the method for acquiring the region of interest performed by the second node in the corresponding embodiment of fig. 2 to 14.
It should be noted that, the specific manner in which the processor 1803 executes the above steps is based on the same concept as that of the method embodiments corresponding to fig. 2 to 14, which brings about the same technical effects as that of the method embodiments corresponding to fig. 2 to 14, and the specific details of the method embodiments shown in the foregoing description of the present application are omitted herein.
There is also provided in an embodiment of the present application a computer program product comprising a program which, when run on a computer, causes the computer to perform the steps performed by a first node in the method described in the embodiment shown in the previous figures 2 to 14 or causes the computer to perform the steps performed by a second node in the method described in the embodiment shown in the previous figures 2 to 14.
In an embodiment of the present application, there is also provided a computer-readable storage medium having stored therein a program for performing signal processing, which when run on a computer causes the computer to perform the steps performed by a first node in the method described in the embodiment shown in the foregoing fig. 2 to 14, or causes the computer to perform the steps performed by a second node in the method described in the embodiment shown in the foregoing fig. 2 to 14.
The device for acquiring the region of interest, the first node and the second node provided by the embodiment of the application may be specifically a chip, where the chip includes: a processing unit, which may be, for example, a processor, and a communication unit, which may be, for example, an input/output interface, pins or circuitry, etc. The processing unit may execute the computer-executable instructions stored in the storage unit to cause the chip to perform the method for acquiring the region of interest described in the embodiment shown in fig. 2 to 13, or to perform the method for acquiring the region of interest described in the embodiment shown in fig. 14.
Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit in the wireless access device side located outside the chip, such as a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM), etc.
The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the method of the first aspect.
It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device (which may be a personal computer, a second node, or a network device, etc.) to perform the method according to the embodiments of the present application.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, second node, or data center to another website, computer, second node, or data center by a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a second node, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
Claims (30)
1. A method for acquiring a region of interest, wherein the method is applied to a system for acquiring a region of interest, the system including a plurality of first nodes and second nodes, a detection region including a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection region including a plurality of detection units, the method comprising:
each first node clusters a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest comprises detection units of a target class;
each first node sends first indication information to the second node, wherein the first indication information comprises the clustering result;
and the second node performs clustering operation on the first region of interest according to the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is the target category and is positioned on the boundary between different sub-detection regions in the detection region.
2. The method according to claim 1, wherein the method further comprises:
the second node sends second indication information to each first node, wherein the second indication information comprises a proximity relation among a plurality of different detection units in the detection area;
and each first node determines the target detection unit corresponding to the boundary of the sub-detection area according to the detection unit of the target category in the sub-detection area and the second indication information, wherein the first indication information is also used for indicating the target detection unit.
3. The method according to claim 1 or 2, wherein the second indication information is obtained based on a graph model corresponding to the detection area, vertices of the graph model representing a plurality of detection units within the detection area, edges of the graph model indicating proximity relations between a plurality of different detection units within the detection area;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
4. The method according to claim 1 or 2, wherein the first node and the second node are each deployed with a stream processing engine, and the data obtained from the sub-detection area is real-time data.
5. The method according to claim 1 or 2, wherein the second node performs a clustering operation on the first region of interest according to the clustering result and the target detection unit, to obtain at least one second region of interest corresponding to the detection region, and the method comprises:
the second node determines a first region of interest to be combined from a plurality of first regions of interest included in the detection region according to the clustering result and the target detection unit;
and the second node determines at least one second region of interest corresponding to the detection region according to the first regions of interest to be combined.
6. The method of claim 1 or 2, wherein the data obtained from the sub-detection zone comprises any one of the following: data transmitted by the base stations in the sub-detection area, position information of communication equipment in the sub-detection area, or data acquired by the sensors in the detection area.
7. A method for acquiring a region of interest, wherein the method is applied to a system for acquiring a region of interest, the system including a plurality of first nodes and second nodes, a detection region including a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection region including a plurality of detection units, the method comprising:
each first node clusters a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest comprises detection units of a target class;
each first node sends first indication information to the second node, wherein the first indication information comprises the clustering result, the first indication information is used for indicating the first node to execute clustering operation on the first region of interest by using the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, and the category of the target detection unit is the target category and is located on the boundary between different sub-detection regions in the detection region.
8. The method of claim 7, wherein the method further comprises:
each first node receives second indication information sent by the second node, wherein the second indication information comprises a proximity relation among a plurality of different detection units in the detection area;
and each first node determines the target detection unit corresponding to the boundary of the sub-detection area according to the detection unit of the target category in the sub-detection area and the second indication information, wherein the first indication information is also used for indicating the target detection unit.
9. The method according to claim 7 or 8, wherein the second indication information is obtained based on a graph model corresponding to the detection area, vertices of the graph model representing a plurality of detection units within the detection area, edges of the graph model indicating proximity relations between a plurality of different detection units within the detection area;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
10. A method for acquiring a region of interest, wherein the method is applied to a system for acquiring a region of interest, the system including a plurality of first nodes and second nodes, a detection region including a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection region including a plurality of detection units, the method comprising:
the second node receives first indication information sent by each first node, wherein the first indication information comprises a clustering result, the clustering result indicates at least one first interested region in the sub-detection region corresponding to the first node, and the first interested region comprises a detection unit of a target class;
and the second node performs clustering operation on the first region of interest according to the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is the target category and is positioned on the boundary between different sub-detection regions in the detection region.
11. The method according to claim 10, wherein the method further comprises:
The second node sends second indication information to each first node, wherein the second indication information comprises a close relation among a plurality of different detection units in the detection area, the second indication information is used for the first node to determine the target detection unit according to the second indication information, and the first indication information is also used for indicating the target detection unit.
12. The method according to claim 10 or 11, wherein the second indication information is obtained based on a graph model corresponding to the detection area, vertices of the graph model representing a plurality of detection units within the detection area, edges of the graph model indicating proximity relations between a plurality of different detection units within the detection area;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
13. A method for acquiring a region of interest, the method being applied to a system for acquiring a region of interest, the system including a plurality of first nodes and second nodes, the first nodes and the second nodes each having a stream processing engine disposed thereon, the detection region including a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection regions including a plurality of detection units, the method comprising:
Each first node clusters a plurality of detection units included in the sub-detection area in a stream processing mode based on real-time data obtained from the sub-detection area to obtain a clustering result, wherein the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest comprises detection units of a target class;
each first node sends first indication information to the second node, wherein the first indication information comprises the clustering result;
and the second node executes clustering operation on the first region of interest according to the clustering result to obtain at least one second region of interest corresponding to the detection region.
14. The method of claim 13, wherein the second node performs a clustering operation on the first region of interest based on the clustering result, comprising:
and the second node executes clustering operation on the first region of interest according to the clustering result and a target detection unit, wherein the category of the target detection unit is the target category and is positioned on the boundary between different sub-detection areas in the detection area.
15. The acquisition system of the region of interest is characterized by comprising a plurality of first nodes and second nodes, wherein a detection area comprises a plurality of sub-detection areas, each sub-detection area corresponds to one first node, and the sub-detection areas comprise a plurality of detection units; wherein, the liquid crystal display device comprises a liquid crystal display device,
each first node is configured to cluster a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, where the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest includes detection units of a target class;
each first node is further configured to send first indication information to the second node, where the first indication information includes the clustering result;
and the second node is used for executing clustering operation on the first region of interest according to the clustering result and a target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is the target category and is positioned on the boundary between different sub-detection regions in the detection region.
16. The system of claim 15, wherein the system further comprises a controller configured to control the controller,
the second node is further configured to send second indication information to each of the first nodes, where the second indication information includes a proximity relationship between a plurality of different detection units in the detection area;
each first node is further configured to determine, according to the detection unit of the target class and the second indication information in the sub-detection area, the target detection unit corresponding to the boundary of the sub-detection area, where the first indication information is further used to indicate the target detection unit.
17. The system of claim 15 or 16, wherein the second indication information is derived based on a graph model corresponding to the detection region, vertices of the graph model representing a plurality of detection units within the detection region, edges of the graph model indicating proximity relationships between a plurality of different detection units within the detection region;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
18. The system of claim 15 or 16, wherein the first node and the second node each have a streaming engine deployed thereon, and the data obtained from the sub-detection area is real-time data.
19. The system according to claim 15 or 16, wherein the second node is specifically configured to:
determining a first region of interest to be combined from a plurality of first regions of interest included in the detection region according to the clustering result and the target detection unit;
and determining at least one second region of interest corresponding to the detection region according to the first regions of interest to be combined.
20. The system of claim 15 or 16, wherein the data obtained from the sub-detection zone comprises any one of: data transmitted by the base stations in the sub-detection area, position information of communication equipment in the sub-detection area, or data acquired by the sensors in the detection area.
21. An acquisition device of a region of interest, wherein the device is applied to a first node in an acquisition system of the region of interest, the system comprising a plurality of the first nodes and a second node, a detection region comprising a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection region comprising a plurality of detection units, the device comprising:
A clustering module, configured to cluster a plurality of detection units included in the sub-detection area based on data obtained from the sub-detection area to obtain a clustering result, where the clustering result indicates at least one first region of interest corresponding to the sub-detection area, and the first region of interest includes a detection unit of a target class;
the sending module is configured to send first indication information to the second node, where the first indication information includes the clustering result, where the first indication information is configured to instruct the first node to perform a clustering operation on the first region of interest by using the clustering result and a target detection unit, so as to obtain at least one second region of interest corresponding to the detection region, where a category of the target detection unit is the target category and is located on a boundary between different sub-detection regions in the detection region.
22. The apparatus of claim 21, wherein the apparatus further comprises:
the receiving module is used for receiving second indication information sent by the second node, and the second indication information comprises a close relation among a plurality of different detection units in the detection area;
The determining module is configured to determine, according to the detection unit of the target class and the second indication information in the sub-detection area, the target detection unit corresponding to a boundary of the sub-detection area, where the first indication information is further used to indicate the target detection unit.
23. The apparatus of claim 21 or 22, wherein the second indication information is derived based on a graph model corresponding to the detection region, vertices of the graph model representing a plurality of detection units within the detection region, edges of the graph model indicating proximity relationships between a plurality of different detection units within the detection region;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
24. An acquisition device of a region of interest, wherein the device is applied to a second node in an acquisition system of the region of interest, the system further comprising a plurality of first nodes, a detection region comprising a plurality of sub-detection regions, each of the sub-detection regions corresponding to one of the first nodes, the sub-detection region comprising a plurality of detection units, the device comprising:
The receiving module is used for receiving first indication information sent by each first node, wherein the first indication information comprises a clustering result, the clustering result indicates at least one first region of interest in the sub-detection region corresponding to the first node, and the first region of interest comprises a detection unit of a target class;
and the clustering module is used for executing clustering operation on the first region of interest according to the clustering result and the target detection unit to obtain at least one second region of interest corresponding to the detection region, wherein the category of the target detection unit is the target category and is positioned on the boundary between different sub-detection regions in the detection region.
25. The apparatus of claim 24, wherein the apparatus further comprises:
the second node sends second indication information to each first node, wherein the second indication information comprises a close relation among a plurality of different detection units in the detection area, the second indication information is used for the first node to determine the target detection unit according to the second indication information, and the first indication information is also used for indicating the target detection unit.
26. The apparatus of claim 24 or 25, wherein the second indication information is derived based on a graph model corresponding to the detection region, vertices of the graph model representing a plurality of detection units within the detection region, edges of the graph model indicating proximity relationships between a plurality of different detection units within the detection region;
wherein each of the detection units is embodied as any one of the following: a regular network, an irregular polygonal mesh, or a spatial region determined based on location information of the physical device within the detection region.
27. A computer program product, characterized in that the computer program product comprises a program which, when run on a computer, causes the computer to carry out the method according to any one of claims 1 to 6 or causes the computer to carry out the method according to any one of claims 7 to 9 or causes the computer to carry out the method according to any one of claims 10 to 12 or causes the computer to carry out the method according to claim 13 or 14.
28. A computer-readable storage medium, in which a program is stored which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 6, or causes the computer to perform the method of any one of claims 7 to 9, or causes the computer to perform the method of any one of claims 10 to 12, or causes the computer to perform the method of claim 13 or 14.
29. A first node comprising a processor and a memory, the processor being coupled to the memory,
the memory is used for storing programs;
the processor being configured to execute a program in the memory, to cause the first node to perform the steps performed by the first node in the method according to any one of claims 1 to 9, or to cause the first node to perform the steps performed by the first node in the method according to claim 13 or 14.
30. A second node comprising a processor and a memory, the processor being coupled to the memory,
the memory is used for storing programs;
the processor is configured to execute a program in the memory, to cause the first node to perform the steps performed by the second node in the method according to any one of claims 1 to 6, or to cause the first node to perform the steps performed by the second node in the method according to any one of claims 10 to 14.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210313658.2A CN116863127A (en) | 2022-03-28 | 2022-03-28 | Method for acquiring region of interest and related equipment |
| PCT/CN2023/082705 WO2023185545A1 (en) | 2022-03-28 | 2023-03-21 | Method for acquiring region of interest, and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210313658.2A CN116863127A (en) | 2022-03-28 | 2022-03-28 | Method for acquiring region of interest and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116863127A true CN116863127A (en) | 2023-10-10 |
Family
ID=88199211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210313658.2A Pending CN116863127A (en) | 2022-03-28 | 2022-03-28 | Method for acquiring region of interest and related equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116863127A (en) |
| WO (1) | WO2023185545A1 (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528597B (en) * | 2016-09-23 | 2019-07-05 | 百度在线网络技术（北京）有限公司 | The mask method and device of point of interest |
| CN110460584B (en) * | 2019-07-16 | 2022-02-01 | 北京奇艺世纪科技有限公司 | Access request processing method and device, electronic equipment and computer readable medium |
| CN110726418B (en) * | 2019-10-10 | 2021-08-03 | 北京百度网讯科技有限公司 | Method, device and equipment for determining interest point region and storage medium |
| CN111695488B (en) * | 2020-06-09 | 2023-09-08 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for identifying interest surface |
| CN111813905B (en) * | 2020-06-17 | 2024-05-10 | 平安科技（深圳）有限公司 | Corpus generation method, corpus generation device, computer equipment and storage medium |
| CN111753089A (en) * | 2020-06-28 | 2020-10-09 | 深圳壹账通智能科技有限公司 | Topic clustering method and device, electronic equipment and storage medium |
| CN112765381A (en) * | 2021-01-18 | 2021-05-07 | 深圳市华尊科技股份有限公司 | Image retrieval method, electronic equipment and related product |
-
2022
- 2022-03-28 CN CN202210313658.2A patent/CN116863127A/en active Pending
-
2023
- 2023-03-21 WO PCT/CN2023/082705 patent/WO2023185545A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023185545A1 (en) | 2023-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | A time efficient approach for detecting errors in big sensor data on cloud | |
| JP6842440B2 (en) | Performance analysis method and management computer | |
| Yu et al. | Trajectory similarity clustering based on multi-feature distance measurement | |
| WO2021253761A1 (en) | Blockchain consensus node state monitoring method and apparatus | |
| CN108038145A (en) | Distributed Services tracking, system, storage medium and electronic equipment | |
| CN102694868B (en) | A kind of group system realizes and task dynamic allocation method | |
| CN109831478A (en) | Rule-based and model distributed processing intelligent decision system and method in real time | |
| CN107528904B (en) | Method and apparatus for data distributed anomaly detection | |
| CN111078818B (en) | Address analysis method and device, electronic equipment and storage medium | |
| CN102664961A (en) | Method for anomaly detection in MapReduce environment | |
| WO2017114276A1 (en) | User analysis method and system based on image | |
| CN113515672A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN109190025A (en) | information monitoring method, device, system and computer readable storage medium | |
| CN110474799A (en) | Fault Locating Method and device | |
| CN107729138A (en) | A kind of analysis method and device of high-performance distributed Vector spatial data | |
| CN104391879A (en) | Method and device for hierarchical clustering | |
| CN110347888A (en) | Processing method, device and the storage medium of order data | |
| CN107944697B (en) | Supply and demand relationship-based heat map calculation method and system, server and medium | |
| Pevec et al. | Distributed data platform for automotive industry: A robust solution for tackling big challenges of big data in transportation science | |
| CN101515864B (en) | Alarm information allocation system and allocation method thereof | |
| CN116863127A (en) | Method for acquiring region of interest and related equipment | |
| CN110138720B (en) | Method and device for detecting abnormal classification of network traffic, storage medium and processor | |
| CN110059234A (en) | Water utilities anomalous event method for detecting and device, computer installation and storage medium | |
| CN102930046B (en) | Data processing method, computing node and system | |
| CN115269519A (en) | Log detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |