CN115914563A - Method for improving image monitoring accuracy - Google Patents
Method for improving image monitoring accuracy Download PDFInfo
- Publication number
- CN115914563A CN115914563A CN202211325138.XA CN202211325138A CN115914563A CN 115914563 A CN115914563 A CN 115914563A CN 202211325138 A CN202211325138 A CN 202211325138A CN 115914563 A CN115914563 A CN 115914563A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- subsystem
- node
- lowsubset
- subseta
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a method for improving image monitoring accuracy, which comprises the following steps: the monitoring management subsystem acquires an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at the time t; dividing the objects with the object characteristic values lower than a first threshold in Set _ k _ t into object subsets LowSubset _ k _ t; selecting an object with a time point t + Delta _ t and a radius L meters of a Node _ k from an object set A provided by an interview alternative subsystem, and defining the object as an object subset Subseta; selecting the object which is most matched with each object in LowSubset _ k _ t from SubsetA, and defining the object with the matching value being more than or equal to a second threshold as a subset B; and B is taken as an object for Node _ k to successfully detect the entering of the monitoring area of Node _ k at the moment t. The method realizes area fine monitoring management through video monitoring, and cooperatively verifies the effectiveness of the object area visit by introducing at least one extra dimension for the condition that the object identification is fuzzy in the video monitoring process.
Description
The invention relates to a method for improving image monitoring accuracy, which is a divisional application with a parent application number of 202011318828.3 and an application date of 2020.11.23.
Technical Field
The invention relates to the field of monitoring, in particular to a method for improving image monitoring accuracy.
Background
With the rapid advance of information communication technology and the rapid development of global professional division, the cooperative cooperation between business entities is tighter, the mutual visit and exchange are more frequent, the visiting amount of business activities is exponentially increased, and accordingly, due to the requirements of personal safety management, information safety management, target investigation, visiting validity management and the like, regional visiting monitoring needs to be performed on widely visited personnel so as to improve the validity of management.
Typical scenarios are: in the power industry, personnel visit relates to safety management of visiting personnel, and whether the visiting personnel step into a dangerous area or not needs to be identified so as to facilitate timely response and avoid personal safety problems; in the high and new technology industry, the problem of information confidentiality and safety when people visit relates to, whether the visiting people step into the key product area of an enterprise or not needs to be identified and timely responded, and the leakage of core technology is avoided; when people visit during tour, safety management problems after visitors enter scenic spots are involved, whether the visitors enter forbidden zones by mistake or not needs to be identified and timely processed, and personal safety problems of the visitors are avoided; in the aspect of business sales referral effectiveness management, whether a customer visits for the first time needs to be identified so as to confirm the market guide attribution of the customer, and whether personnel enter a target monitoring area needs to be accurately acquired in various scenes so as to take relevant measures such as countermeasures or factual judgment.
For the monitoring affairs of visiting areas, the method adopted by the prior art mainly comprises the following steps:
video monitoring: the method comprises the steps that a camera is installed in a target area, and after a video is collected by the camera, an image is extracted for object identification to realize area visiting identification (misjudgment or missing detection is easily caused by face angles, crowd shielding and face wearing decoration shielding in the scheme);
entering registration (the method is difficult to ensure that the visit is always registered, the missing detection is formed, and in addition, the method is difficult to realize the area visit fine management);
registration is carried out through WIFI access authentication (the fact that registration is necessary to visit is difficult to guarantee, missing detection is formed, and in addition, the method is difficult to achieve regional visit fine management).
As described above, because the monitoring method in the prior art is incomplete, and has the problem that the area visit fine management cannot be realized or the accuracy of the visit monitoring is low, the area visit management is invalid, so a method for improving the image monitoring accuracy is provided, which improves the level of fine management of the area visit and the accuracy of the monitoring, and is a problem to be solved in the industry.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the invention provides a method for improving image monitoring accuracy, which realizes area refined monitoring management through video monitoring, and cooperatively verifies the effectiveness of the visit of an object area by introducing at least one extra dimension for the condition that the identification of the object is fuzzy in the video monitoring process, thereby improving the coverage rate and the accuracy of monitoring, finally realizing a refined, high-coverage and high-accuracy area visit monitoring scheme, and improving the effectiveness of the visit management.
The technical scheme adopted by the invention for solving the problems in the prior art is as follows:
the invention provides a method for improving image monitoring accuracy, which comprises the following steps:
step 1: the monitoring management subsystem acquires an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at the time t;
and 2, step: dividing the objects with the object characteristic values lower than a first threshold in Set _ k _ t into object subsets LowSubset _ k _ t;
and 3, step 3: the monitoring management subsystem selects a time point t + Delta _ t from an object set A provided by the visiting alternative subsystem, an object positioned in a Node _ k range with radius of L meters and defined as an object subset Subsesta;
and 4, step 4: the monitoring management subsystem selects an object which is most matched with each object in LowSubset _ k _ t from SubsetA, and defines an object with a matching value larger than or equal to a second threshold as a subset B;
and 5: the monitoring management subsystem takes the B as an object of the Node _ k for successfully detecting the entering of the Node _ k monitoring area at the moment t;
each element of the Set _ k _ t in the object Set at least comprises three items of information, namely an object ID, object content and an object characteristic value, wherein the object characteristic value is a comprehensive detection value used for indicating the reliability of the existence of an object;
in the step 3, the visiting alternative subsystem positions the position distribution information of the personnel in each area through the wireless signal, and the object set information provided by the visiting alternative subsystem is an object set which is detected by the visiting alternative subsystem and takes the reference position as the center and is within the radius G range after the reference position information provided by the visiting alternative subsystem is based on the reference position information provided by the monitoring management subsystem to the visiting alternative subsystem, wherein the reference position information is the center position of the monitoring area of the monitoring management subsystem.
Preferably, in step 1, the monitoring management subsystem obtains an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at time t, and the obtaining method specifically includes:
the video monitoring Node _ k actively reports the detected object set after detecting the existence of the object;
or
The monitoring management subsystem configures a video analysis subsystem to periodically report a detected object set;
or alternatively
And after the monitoring management subsystem sends a query request to the video analysis subsystem, the video analysis subsystem reports the detected object set.
Preferably, in step 1, the object ID refers to a number in a database for uniquely identifying an object, and the ID may also identify a corresponding monitoring area; the object content refers to image initial information of the object.
Preferably, in step 5, the information of the written data at least includes Node _ k identifier, time information t, object ID, and object initial information.
Preferably, the wireless signal may include any one or a combination of mobile communication signal, bluetooth, WIFI, LORA and NBIOT.
Preferably, in step 4, the subset B is constructed as follows:
step 4.1, selecting any object LowSubset _ k _ t _ i which is not subjected to object matching from LowSubset _ k _ t;
step 4.2, selecting any object Subseta _ j which is not matched with LowSubset _ k _ t _ i from Subseta;
4.3, calculating the matching degree of LowSubset _ k _ t _ i and SubsetA _ j to obtain a matching value M _ k _ t _ ij;
step 4.4, judging whether all the objects in Subseta are matched with LowSubset _ k _ t _ i, if yes, skipping to step 4.5, and if not, skipping to step 4.2;
step 4.5, judging whether all the objects in LowSubset _ k _ t complete matching operation, if so, skipping to step 4.6, and if not, skipping to step 4.1;
4.6, sorting matching values of different j values in the same i in the M _ k _ t _ ij from high to low to obtain PM _ k _ t _ iy;
step 4.7, selecting a PM _ k _ t _ p0 with the highest matching value from different i in the PM _ k _ t _ i0, judging whether the matching value is larger than or equal to a second threshold, if not, jumping to step 4.9, if so, writing the object information of the subsetA corresponding to the PM _ k _ t _ p0 into the subset B, and deleting the information of the PM _ k _ t _ py;
step 4.8, judging whether an object in the SubsetA corresponding to the PM _ k _ t _ p0 appears in the PM _ k _ t _ i0, if so, deleting the object in the PM _ k _ t _ iy, wherein i is not equal to p;
and 4.9, finishing the construction of the subset B.
Compared with the prior art, the invention has the following beneficial effects:
by adopting the method, the area refined monitoring management is realized through video monitoring, and for the condition that the identification of the object is fuzzy in the video monitoring process, the effectiveness of the visit to the object area is cooperatively verified by introducing at least one extra dimension, so that the coverage rate and the accuracy of monitoring are improved, the area visit monitoring scheme with the fineness, the high coverage rate and the high accuracy is finally realized, and the effectiveness of the visit management is improved.
Drawings
FIG. 1 is a process flow schematic of the present invention;
FIG. 2 is a schematic diagram of the system components of the present invention.
Detailed Description
In order to make the technical solution and the advantages of the present invention clearer, the following explains embodiments of the present invention in further detail.
As shown in fig. 2, the present invention provides a multi-dimensional cooperative monitoring system, comprising: the system comprises a monitoring management subsystem, a visiting alternative subsystem and a video analysis subsystem, wherein the functions of the subsystems are as follows:
the video analysis subsystem: the subsystem is responsible for video monitoring, image extraction and object detection, and reports an object detection result to the monitoring management subsystem;
visiting alternative subsystems: according to the coordinate position submitted by the monitoring management subsystem, acquiring an object with the coordinate as the center and within the radius G and sending information to the monitoring management subsystem;
the monitoring management subsystem: and based on the information provided by the video analysis subsystem and the visiting alternative subsystem, performing object detection based on a multi-dimensional cooperative monitoring method, and writing a detection result into a database in the monitoring management subsystem.
The invention also provides a multidimensional collaborative monitoring method, as shown in fig. 1, which specifically comprises the following steps:
step 1: the method comprises the steps that a monitoring management subsystem obtains an object Set _ k _ t reported by a certain video monitoring Node _ k in a video analysis subsystem at the time of t, wherein each element in the object Set at least comprises three items of information of an object ID, object content and an object characteristic value;
step 2: the monitoring management subsystem divides the objects with the object characteristic values lower than the threshold 1 in the Set _ k _ t into object subsets LowSubset _ k _ t and divides the objects with the object characteristic values higher than or equal to the threshold 1 into object subsets highSubset _ k _ t;
and step 3: the monitoring management subsystem selects a time point t + Delta _ t from an object set A provided by the visiting alternative subsystem, an object positioned in a Node _ k range with radius of L meters and defined as an object subset Subsesta;
and 4, step 4: the monitoring management subsystem selects an object which is most matched with each object in LowSubset _ k _ t from SubsetA, and defines an object with a matching value larger than or equal to a threshold 2 as a subset B;
and 5: the monitoring management subsystem takes HighSubset _ k _ t and B as objects of Node _ k which successfully detect entering a Node _ k monitoring area at the time of t, and writes the objects into a database.
The method for improving the image monitoring accuracy related to the steps 1, 2, 3, 4 and 5 comprises a monitoring management subsystem, a visiting alternative subsystem and a video analysis subsystem;
in the step 1, the monitoring management subsystem obtains an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at a time t, and the obtaining method specifically includes:
the video monitoring Node _ k actively reports the detected object set after detecting the existence of the object;
or alternatively
The monitoring management subsystem configures a video analysis subsystem to periodically report a detected object set;
or alternatively
After the monitoring management subsystem sends a query request to the video analysis subsystem, the video analysis subsystem reports the detected object set;
in step 1, the object ID index indicates a number used for uniquely identifying an object in a database, and preferably, the ID may also identify a corresponding monitoring area; the object content refers to image initial information of the object; the object characteristic value refers to a comprehensive detection value used for indicating the reliability of the existence or nonexistence of an object, and a typical comprehensive detection value is a three-family five-eye comprehensive detection value, which is not particularly limited;
in the step 3, the visiting alternative subsystem positions the position distribution information of the personnel in each area through wireless signals, wherein the wireless signals may include mobile communication signals, bluetooth, WIFI, LORA, NBIOT and the like, and are not limited specifically;
in step 3, the object set information provided by the visiting alternative subsystem is an object set which is detected by the visiting alternative subsystem and is centered at the reference position and within the radius G based on the reference position information provided by the visiting alternative subsystem from the monitoring management subsystem, and the reference position information is the central position of the monitoring area of the monitoring management subsystem;
in step 4, the subset B is constructed as follows:
step 4.1, selecting any object LowSubset _ k _ t _ i which is not subjected to object matching from LowSubset _ k _ t;
step 4.2, selecting any object subsetA _ j which is not matched with LowSubset _ k _ t _ i from the subsetA;
step 4.3, calculating the matching degree of LowSubset _ k _ t _ i and SubsetA _ j to obtain a matching value M _ k _ t _ ij;
step 4.4, judging whether all the objects in the subsetA are matched with LowSubset _ k _ t _ i, if so, jumping to step 4.5, and if not, jumping to step 4.2;
step 4.5, judging whether all the objects in LowSubset _ k _ t complete matching operation, if so, skipping to step 4.6, and if not, skipping to step 4.1;
4.6, sorting matching values of different j values in the same i in the M _ k _ t _ ij from high to low to obtain PM _ k _ t _ iy;
step 4.7, selecting a PM _ k _ t _ p0 with the highest matching value from different i in the PM _ k _ t _ i0, judging whether the matching value is larger than or equal to a threshold 2, if not, jumping to step 4.9, if so, writing the object information of the subsetA corresponding to the PM _ k _ t _ p0 into the subset B, and deleting the information of the PM _ k _ t _ py;
step 4.8, judging whether the object in the SubsetA corresponding to the PM _ k _ t _ p0 appears in the PM _ k _ t _ i0 (i is not equal to p), and if so, deleting the object in the PM _ k _ t _ iy;
step 4.9, finishing the construction of the subset B;
in step 5, the information written in the data at least includes Node _ k identifier, time information t, object ID, and object initial information.
A specific embodiment of a method for improving image monitoring accuracy is described below with specific embodiments:
example (b): as shown in fig. 2, the system of this embodiment is composed of a monitoring management subsystem, an access candidate subsystem, and a video analysis subsystem, where a threshold 1 is 0.8, a radius L is 60 meters, a Delta _ t is 30 seconds, a radius G is 300 meters, and a threshold 2 is 0.7, at which time a Node _ k Node in the video analysis subsystem reports an object detection result as shown in table 1 to the monitoring management subsystem, and it can be seen from table 1 that only an object with an object ID of 2 is greater than the threshold 1, that is, at which time t is determined, the object enters a Node _ k monitoring area, so that an object with an object ID of 2 in table 1 is divided into highsub _ k _ t (corresponding to highsub _ k _ t _ 0); however, since the two objects with object IDs 0 and 1 are less than the threshold 1, i.e. there is ambiguity, it is temporarily impossible to confirm whether they enter the Node _ k monitoring area, so that the two objects with object IDs 0 and 1 in table 1 are divided into lowset _ k _ t (corresponding to lowset _ k _ t _0 and lowset _ k _ t _1, respectively). Because the detection is fuzzy and the result can not be confirmed temporarily, the method of the invention introduces an extra dimension for collaborative determination, so that the monitoring management subsystem sends the reference position information RP governed by the monitoring management subsystem to the visiting alternative subsystem, the visiting alternative subsystem carries out positioning based on mobile communication signals, reports the alternative object set A positioned in the range of the radius G (namely 300 meters) of the reference position RP to the monitoring management subsystem, the information of the alternative object set A is detailed in a table 2, then the monitoring management subsystem screens out a time point t + Delta _ t and objects positioned in the range of L meters of the radius of Node _ k to obtain Subsetas (detailed in a table 2, including Subsetas _0, subsetas _1, subsetas _2, subsetas _3 and Subsetas _ 4), the monitoring management subsystem sequentially calculates the matching degree of LowSubset _ k _ t _0 and Subset A _ f (wherein f takes values of 0, 1, and 4), then calculates the matching degree of LowSubset _ k _ t _1 and Subset A _ f (wherein f takes values of 0, 1, and 4), and obtains M _ k _ t _ ij (wherein i takes values of 0 and 1, and j takes values of 0, 1, 2, 3, and 4), then sorts the matching degrees corresponding to different j values under the same i value of M _ k _ t _ ij from high to low to obtain the matching degree sorting result shown in Table 3, then finds out the maximum value from PM _ k _ t _00 and PM _ k _ t _10, namely PM _ k _ t _00, and then judges that the value is greater than 2 (corresponding to value 0.7), thus writes the sub-set of the corresponding objects in the LowSubset _ j, namely, the sub _ k _ t _0, and deletes the PM _ k _ y data, meanwhile, whether the column of PM _ k _ t _10 includes SubsetA _0 or not is judged, and since the real-time example includes the following steps, the 0 th element needs to be deleted from the PM _ k _ t _1y to obtain the result of the table 4, then the PM _ k _ t _10 is selected from the table 4, then the judgment is larger than the threshold 2 (corresponding to the value of 0.7), so that the object corresponding to the SubsetA _ j, namely the SubsetA _1, is written into the subset B, finally, the monitoring management subsystem takes the highset _ k _ t and the B as the objects of Node _ k which successfully detect the entry into the monitoring area of the Node _ k at the time t and writes the objects into the database, and the database is updated and detailed in the table 5.
Table 1 detected object information reported by video analysis subsystem
Table 2M _k _t _ijcalculation results
TABLE 3PM_k _t _iycalculation results
Element composition after deleting first multi-dimensional cooperative matching related elements in Table 4PM _k _t _iy
TABLE 5 database information
Node _ k identification | Time letterInformation processing device | Object ID | Object initial information |
k | t | 0 | Picture 0 |
k | t | 1 | Picture 1 |
k | t | 2 | Picture 2 |
By adopting the method, the area refined monitoring management is realized through video monitoring, and for the condition that the identification of the object is fuzzy in the video monitoring process, the effectiveness of the visit to the object area is cooperatively verified by introducing at least one extra dimension, so that the coverage rate and the accuracy of monitoring are improved, the area visit monitoring scheme with the fineness, the high coverage rate and the high accuracy is finally realized, and the effectiveness of the visit management is improved.
In summary, the present invention is only a preferred embodiment, and is not intended to limit the scope of the present invention, and various changes and modifications can be made by workers in the light of the above description without departing from the technical spirit of the present invention. The technical scope of the present invention is not limited to the content of the specification, and all equivalent changes and modifications in the shape, structure, characteristics and spirit described in the scope of the claims of the present invention are included in the scope of the claims of the present invention.
Claims (6)
1. A method for improving image monitoring accuracy is characterized by comprising the following steps:
step 1: the monitoring management subsystem acquires an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at the time t;
and 2, step: dividing the objects with the object characteristic values lower than a first threshold in Set _ k _ t into object subsets LowSubset _ k _ t;
and 3, step 3: the monitoring management subsystem selects a time point t + Delta _ t from an object set A provided by the visiting alternative subsystem, an object positioned in a Node _ k range with a radius of L meters and defined as an object subset SubstA;
and 4, step 4: the monitoring management subsystem selects an object which is most matched with each object in LowSubset _ k _ t from SubsetA, and defines an object with a matching value larger than or equal to a second threshold as a subset B;
and 5: the monitoring management subsystem takes the B as an object of Node _ k successfully detecting the entering of a Node _ k monitoring area at the time t;
each element of the Set _ k _ t in the object Set at least comprises three items of information, namely an object ID, object content and an object characteristic value, wherein the object characteristic value is a comprehensive detection value used for indicating the reliability of the existence of an object;
in the step 3, the visiting alternative subsystem positions the position distribution information of the personnel in each area through the wireless signal, and the object set information provided by the visiting alternative subsystem is an object set which is detected by the visiting alternative subsystem and takes the reference position as the center and is within the radius G range after the reference position information provided by the visiting alternative subsystem is based on the reference position information provided by the monitoring management subsystem to the visiting alternative subsystem, wherein the reference position information is the center position of the monitoring area of the monitoring management subsystem.
2. The method for improving the accuracy of image monitoring according to claim 1, wherein:
in the step 1, the monitoring management subsystem obtains an object Set _ k _ t reported by a certain video monitoring Node _ k in the video analysis subsystem at a time t, and the obtaining method specifically includes:
the video monitoring Node _ k actively reports the detected object set after detecting the existence of the object;
or
The monitoring management subsystem configures a video analysis subsystem to periodically report a detected object set;
or
And after the monitoring management subsystem sends a query request to the video analysis subsystem, the video analysis subsystem reports the detected object set.
3. The method for improving the accuracy of image monitoring according to claim 1, wherein:
in step 1, the object ID index is a number used for uniquely identifying an object in a database, and the ID may also identify a corresponding monitoring area; the object content refers to image initial information of the object.
4. The method for improving the accuracy of image monitoring according to claim 1, wherein:
in step 5, the information written in the data at least includes Node _ k identifier, time information t, object ID, and object initial information.
5. The method for improving the accuracy of image monitoring according to claim 1, wherein:
the wireless signal can comprise any one or a combination of several of mobile communication signals, bluetooth, WIFI, LORA and NBIOT.
6. The method for improving image monitoring accuracy according to any one of claims 1-4, wherein:
in step 4, the subset B is constructed as follows:
step 4.1, selecting any object LowSubset _ k _ t _ i which is not subjected to object matching from LowSubset _ k _ t;
step 4.2, selecting any object subsetA _ j which is not matched with LowSubset _ k _ t _ i from the subsetA;
step 4.3, calculating the matching degree of LowSubset _ k _ t _ i and SubsetA _ j to obtain a matching value M _ k _ t _ ij;
step 4.4, judging whether all the objects in Subseta are matched with LowSubset _ k _ t _ i, if yes, skipping to step 4.5, and if not, skipping to step 4.2;
step 4.5, judging whether all the objects in LowSubset _ k _ t complete matching operation, if so, skipping to step 4.6, and if not, skipping to step 4.1;
4.6, sorting matching values of different j values in the same i in the M _ k _ t _ ij from high to low to obtain PM _ k _ t _ iy;
step 4.7, selecting a PM _ k _ t _ p0 with the highest matching value from different i in the PM _ k _ t _ i0, judging whether the matching value is larger than or equal to a second threshold, if not, jumping to step 4.9, if so, writing the object information of the subsetA corresponding to the PM _ k _ t _ p0 into the subset B, and deleting the information of the PM _ k _ t _ py;
step 4.8, judging whether an object in the SubsetA corresponding to the PM _ k _ t _ p0 appears in the PM _ k _ t _ i0, if so, deleting the object in the PM _ k _ t _ iy, wherein i is not equal to p;
and 4.9, finishing the construction of the subset B.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211325138.XA CN115914563A (en) | 2020-11-23 | 2020-11-23 | Method for improving image monitoring accuracy |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011318828.3A CN112532934B (en) | 2020-11-23 | 2020-11-23 | Multi-dimensional cooperative monitoring system |
CN202211325138.XA CN115914563A (en) | 2020-11-23 | 2020-11-23 | Method for improving image monitoring accuracy |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011318828.3A Division CN112532934B (en) | 2020-11-23 | 2020-11-23 | Multi-dimensional cooperative monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115914563A true CN115914563A (en) | 2023-04-04 |
Family
ID=74992530
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211325138.XA Pending CN115914563A (en) | 2020-11-23 | 2020-11-23 | Method for improving image monitoring accuracy |
CN202011318828.3A Active CN112532934B (en) | 2020-11-23 | 2020-11-23 | Multi-dimensional cooperative monitoring system |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011318828.3A Active CN112532934B (en) | 2020-11-23 | 2020-11-23 | Multi-dimensional cooperative monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN115914563A (en) |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006118559A1 (en) * | 2005-04-29 | 2006-11-09 | Chubb International Holdings Limited | Automatic video quality monitoring for surveillance cameras |
CN101882248A (en) * | 2009-05-08 | 2010-11-10 | 北京正辰科技发展有限责任公司 | Multi-level digital city supervision system based on 3S (GIS, Geographic Information System/GPS, Global Position System/RS, Radio Station) |
CN102201061B (en) * | 2011-06-24 | 2012-10-31 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
CN102622798B (en) * | 2012-03-28 | 2014-04-16 | 东南大学 | Passenger flow statistical analysis system |
KR101425505B1 (en) * | 2013-10-25 | 2014-08-13 | 홍승권 | The monitering method of Intelligent surveilance system by using object recognition technology |
CN104780361B (en) * | 2015-03-27 | 2016-10-05 | 南京邮电大学 | A kind of quality evaluating method of city video monitoring system |
US10757377B2 (en) * | 2016-06-01 | 2020-08-25 | Pixart Imaging Inc. | Surveillance system and operation method thereof |
CN106408940B (en) * | 2016-11-02 | 2023-04-14 | 南京慧尔视智能科技有限公司 | Traffic detection method and device based on microwave and video data fusion |
CN108881809A (en) * | 2017-05-09 | 2018-11-23 | 杭州海康威视数字技术股份有限公司 | Video monitoring method, apparatus and system |
CN107590456B (en) * | 2017-09-06 | 2020-09-18 | 张栖瀚 | Method for detecting small and micro targets in high-altitude video monitoring |
CN109583278B (en) * | 2017-09-29 | 2021-08-24 | 杭州海康威视数字技术股份有限公司 | Face recognition alarm method, device and system and computer equipment |
CN107801203B (en) * | 2017-11-13 | 2020-11-17 | 深圳市戴升智能科技有限公司 | Population density and mobility estimation method and system based on multi-data fusion |
CN107909025B (en) * | 2017-11-13 | 2021-12-24 | 深圳市戴升智能科技有限公司 | Person identification and tracking method and system based on video and wireless monitoring |
CN109963113B (en) * | 2017-12-14 | 2021-06-22 | 浙江宇视科技有限公司 | Method and device for monitoring interested target |
CN110111515A (en) * | 2018-02-01 | 2019-08-09 | 广州弘度信息科技有限公司 | A kind of border intrusion detection method, apparatus, server and system |
CN108802758B (en) * | 2018-05-30 | 2021-02-12 | 北京应互科技有限公司 | Intelligent security monitoring device, method and system based on laser radar |
CN111161206A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera and monitoring system |
CN109766779B (en) * | 2018-12-20 | 2021-07-20 | 深圳云天励飞技术有限公司 | Loitering person identification method and related product |
CN109657624A (en) * | 2018-12-21 | 2019-04-19 | 秒针信息技术有限公司 | Monitoring method, the device and system of target object |
CN110458489A (en) * | 2019-07-05 | 2019-11-15 | 宁波海上鲜信息技术有限公司 | Chief storekeeper's method, system, storage medium and its intelligent terminal |
CN111144366A (en) * | 2019-12-31 | 2020-05-12 | 中国电子科技集团公司信息科学研究院 | Strange face clustering method based on joint face quality assessment |
CN111626108B (en) * | 2020-04-17 | 2023-04-21 | 浙江大华技术股份有限公司 | Target identification method and system |
-
2020
- 2020-11-23 CN CN202211325138.XA patent/CN115914563A/en active Pending
- 2020-11-23 CN CN202011318828.3A patent/CN112532934B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112532934B (en) | 2022-11-15 |
CN112532934A (en) | 2021-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110505583B (en) | Trajectory matching method based on bayonet data and signaling data | |
KR20180013998A (en) | Account theft risk identification method, identification device, prevention and control system | |
US11762396B2 (en) | Positioning system and positioning method based on WI-FI fingerprints | |
Kalogianni et al. | Passive WiFi monitoring of the rhythm of the campus | |
Yin et al. | A deep learning approach for rooftop geocoding | |
Saldivar-Carranza et al. | Identifying Vehicle Turning Movements at Intersections from Trajectory Data | |
CN110162975A (en) | A kind of multistep abnormal point detecting method based on neighbour's propagation clustering algorithm | |
Caceres et al. | Supervised land use inference from mobility patterns | |
CN106600287A (en) | Intelligent anti-counterfeiting early warning method and device | |
Swangmuang et al. | On clustering RSS fingerprints for improving scalability of performance prediction of indoor positioning systems | |
CN112532934B (en) | Multi-dimensional cooperative monitoring system | |
CN115409472B (en) | Intelligent case handling process management method and system and electronic equipment | |
Petraco et al. | Statistical discrimination of footwear: a method for the comparison of accidentals on shoe outsoles inspired by facial recognition techniques | |
CN114882974B (en) | Psychological diagnosis database access artificial intelligence verification system and method | |
US20230073876A1 (en) | Systems And Methods For High Volume Processing Support Of Electronic Signature Tracking | |
CN111444892B (en) | Track tracking system based on line, query method and device | |
US20200272647A1 (en) | Contextual Grouping | |
Pierdicca et al. | Identifying the use of a park based on clusters of visitors' movements from mobile phone data | |
Lan et al. | Detecting Anomalous Trajectories of Workers using Density Method | |
CN112040411A (en) | Data analysis method and device | |
Jeong et al. | Anomaly detection in taxi flow by a projection method | |
JP2016029548A (en) | Portable storage device, action history management system, and program | |
de Castro Silva et al. | Impersonation fraud detection on building access control systems: An approach based on anomalous social and spatio-temporal behaviors | |
CN116469254B (en) | Information processing method and device | |
CN113409018B (en) | People stream density determining method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |