CN117726883B - Regional population analysis method, device, equipment and storage medium - Google Patents
Regional population analysis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117726883B CN117726883B CN202410172388.7A CN202410172388A CN117726883B CN 117726883 B CN117726883 B CN 117726883B CN 202410172388 A CN202410172388 A CN 202410172388A CN 117726883 B CN117726883 B CN 117726883B
- Authority
- CN
- China
- Prior art keywords
- track
- mode
- target
- determining
- target object
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 100
- 238000010586 diagram Methods 0.000 claims abstract description 90
- 230000000694 effects Effects 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 77
- 239000011159 matrix material Substances 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000003062 neural network model Methods 0.000 description 12
- 238000012549 training Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 230000001815 facial effect Effects 0.000 description 6
- 230000003993 interaction Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 239000013604 expression vector Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000007667 floating Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a regional population analysis method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring at least two single-mode track diagrams of the activity of a target object in a target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map; fusing at least two single-mode track graphs to obtain a target track graph corresponding to a target object; based on the track activity region in the target track map, an object type of the target object relative to the target region is determined, wherein the object type is associated with an activity time of the target object in the target region. The technical scheme of the embodiment of the invention solves the problem that the prior regional population technology cannot ensure higher analysis accuracy in a complex scene of regional population analysis, can fully utilize multi-mode track data to carry out comprehensive analysis, and then determines the regional population analysis result according to the analysis result, thereby improving the regional population analysis accuracy and efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of regional population analysis, in particular to a regional population analysis method, a regional population analysis device, regional population analysis equipment and a regional population analysis storage medium.
Background
With the rapid promotion of the urban process, the data of regional floating population is continuously increased, and great challenges are brought to the aspects of urban infrastructure, safety prevention and control, social management and the like. How to accurately and efficiently analyze the behavior characteristics of regional floating population becomes a focus problem to be solved at present.
Existing regional population analysis techniques fall into two main categories. (1) Time-based regional population analysis (2) cluster-based regional population analysis. The main limitations of these methods are as follows: (1) Based on regional population analysis of time series, human experience is often relied on in actual application time, and complex scenes cannot be dealt with. (2) The regional population analysis based on clustering is sensitive to initial and noise points, so that an analysis result is inaccurate easily, and when the regional population analysis is put into practical use, a large amount of time and labor cost are required to be put into debugging, so that the floor application is difficult.
Disclosure of Invention
The embodiment of the invention provides a regional population analysis method, a device, equipment and a storage medium, which can fully utilize multi-mode track data to carry out comprehensive analysis, and then determine regional population analysis results according to the analysis results, thereby improving the accuracy and efficiency of regional population analysis.
In a first aspect, an embodiment of the present invention provides a regional population analysis method, including:
acquiring at least two single-mode track diagrams of the activity of a target object in a target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object;
An object type of the target object relative to the target area is determined based on a track activity area in the target track graph, wherein the object type is associated with an activity time of the target object in the target area.
In a second aspect, an embodiment of the present invention provides an area population analysis apparatus, the apparatus comprising:
the single-mode track diagram determining module is used for acquiring at least two single-mode track diagrams of the target object moving in the target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
the target track diagram determining module is used for fusing at least two single-mode track diagrams to obtain a target track diagram corresponding to the target object;
and the object type determining module is used for determining the object type of the target object relative to the target area based on the track activity area in the target track graph, wherein the object type is associated with the activity time of the target object in the target area.
In a third aspect, an embodiment of the present invention provides a computer apparatus, including:
One or more processors;
a memory for storing one or more programs;
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the regional population analysis method of any of the embodiments.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the regional population analysis method of any of the embodiments.
According to the technical scheme provided by the embodiment of the invention, at least two single-mode track diagrams of the target object moving in the target area are obtained; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map; fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object; an object type of the target object relative to the target area is determined based on a track activity area in the target track graph, wherein the object type is associated with an activity time of the target object in the target area. The technical scheme of the embodiment of the invention solves the problem that the prior regional population technology cannot ensure higher analysis accuracy in a complex scene of regional population analysis, can fully utilize multi-mode track data to carry out comprehensive analysis, and then determines the regional population analysis result according to the analysis result, thereby improving the regional population analysis accuracy and efficiency.
Drawings
FIG. 1 is a flow chart of a regional population analysis method provided by an embodiment of the present invention;
FIG. 2 is a flow chart of yet another regional population analysis method provided by an embodiment of the present invention;
FIG. 3 is a workflow diagram for regional population analysis provided by an embodiment of the present invention;
FIG. 4 is a workflow diagram of data acquisition and preprocessing provided by an embodiment of the present invention;
FIG. 5 is a workflow diagram of a single-mode trajectory and graph construction provided by an embodiment of the present invention;
FIG. 6 is a workflow diagram of multi-modal trajectory generation and trajectory graph construction provided by embodiments of the present invention;
fig. 7 is a schematic structural diagram of a regional population analysis apparatus according to an embodiment of the present invention;
Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of a regional population analysis method provided by an embodiment of the present invention, where the embodiment of the present invention is applicable to a scenario in which an activity track of a target object is analyzed to determine whether the target object is a resident population of a target region, the method may be performed by a regional population analysis device, and the device may be implemented by software and/or hardware.
As shown in fig. 1, the regional population analysis method includes the steps of:
S110, acquiring at least two single-mode track diagrams of the target object moving in the target area.
The target area may be an area where area population analysis is required. For example, the target area may be specified by a human. The manner in which the target region is specifically determined is not identified here. The target object may be an active object within the target area that needs to be analyzed. Specifically, the target object may be specified by a person, or objects that are active in the target area may be all target objects.
The single-mode trajectory graph may be a space-time graph corresponding to a single-mode angle determination of an activity trajectory of the target object within the target region. Specifically, the single mode of the embodiment of the invention comprises the following steps: face, identification code, and vehicle. Correspondingly, the single-mode trajectory graph comprises: a face track map, an identification code track map, and a vehicle track map.
Specifically, a corresponding mode acquisition device can be installed in the target area, when the single mode acquisition data of the mode acquisition device are acquired, when identification information of a target object appears in the single mode acquisition data, single mode track points are determined according to the device positions of the mode acquisition device corresponding to the acquisition data, then the single mode track points of the same type are sequentially connected according to the activity time of the target object at each single mode track point, further the activity track of the target object is determined, and finally a time-space diagram corresponding to the activity track is determined, so that a single mode track diagram is obtained.
And S120, fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object.
The target track graph can be a multi-mode track graph obtained by fusing the single-mode track graph. Specifically, after the single-mode track diagrams to be fused are determined, the track nodes can be rearranged and connected according to the time information corresponding to the track nodes in each single-mode track diagram, so that the target track diagram is determined. The target track map is obtained by fusing a plurality of single-mode track maps, so that the single-mode data such as the face, the identity recognition code and the vehicle can be fused, the track of the target object can be conveniently analyzed from the multi-mode angle, and the accuracy of regional population analysis is improved.
S130, determining the object type of the target object relative to the target area based on the track activity area in the target track graph.
The track active area may be an active area of a target object corresponding to the target track map. Specifically, the target track map may be analyzed, and the track activity area may be determined according to the track corresponding area of the target object in the target track map. Further, the object type may be a type indicating the time at which the target object is active within the target area. The object type is associated with an activity time of the target object in the target area. Exemplary object types include resident objects and non-resident objects. Specifically, the object type of the target object can be determined according to the overlapping portion of the track active region and the target region. For example, a coincidence region of the trajectory active region and the target region may be determined, and then the object type may be determined based on the size of the coincidence region. For example, in the case where the overlapping area is greater than the preset overlapping area threshold, it may be determined that the target object is a resident object; and under the condition that the coincidence region is smaller than a preset coincidence region threshold value, determining that the target object is a resident object.
According to the technical scheme provided by the embodiment of the invention, at least two single-mode track diagrams of the target object moving in the target area are obtained; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map; fusing at least two single-mode track graphs to obtain a target track graph corresponding to a target object; based on the track activity region in the target track map, an object type of the target object relative to the target region is determined, wherein the object type is associated with an activity time of the target object in the target region. The technical scheme of the embodiment of the invention solves the problem that the prior regional population technology cannot ensure higher analysis accuracy in a complex scene of regional population analysis, can fully utilize multi-mode track data to carry out comprehensive analysis, and then determines the regional population analysis result according to the analysis result, thereby improving the regional population analysis accuracy and efficiency.
FIG. 2 is a flowchart of another regional population analysis method provided by the embodiment of the present invention, where the embodiment of the present invention is applicable to analyzing an activity track of a target object to determine whether the target object is a resident population of a target region, and on the basis of the above embodiment, the embodiment further illustrates how to obtain at least two single-mode track diagrams of the target object activity in the target region; how to fuse at least two single-mode track graphs to obtain a target track graph corresponding to a target object; and how to determine the object type of the target object relative to the target area based on the track activity area in the target track map, the apparatus may be implemented in software and/or hardware, and integrated in a computer device having application development functions.
As shown in fig. 2, the regional population analysis method includes the steps of:
S210, acquiring equipment acquisition data of a modal acquisition equipment in a target area, and determining a single-mode track point related to a target object according to the equipment acquisition data and the equipment position information of the modal acquisition equipment.
The target area may be an area where area population analysis is required. For example, the target area may be specified by a human. The manner in which the target region is specifically determined is not identified here. The modality acquisition device may be a device that acquires information about a moving object within a target area. Specifically, the modality acquisition device includes: at least one of a face collection device, an identification code collection device, and a vehicle collection device. The face acquisition device can acquire face images of the moving objects in the target area. The identification code acquisition device can acquire the identification code of the movable object in the target area. Alternatively, IMSI (International Mobile Subscriber Identity, international mobile object identity) may be used as the identity of the active object in the target area. The vehicle acquisition device may acquire a vehicle image of a moving object within the target area. By acquiring the device acquisition data of the modal acquisition device, the activity frequency and the activity time of the active object in the target area can be analyzed based on the device acquisition data, so that whether the active object is a resident object in the target area or not can be conveniently determined later. The duration corresponding to the device acquisition data can be specified by human, namely, an operator can acquire the modal acquisition data in a specified time period.
Further, the device location information may be geographic location information of the modality acquisition device. The target object may be an active object within the target area that needs to be analyzed. The single-mode trajectory point may be an active trajectory point of the target object determined from one mode angle. Specifically, a location point where the modal collection device is located may be taken as a track point, and when the modal collection device collects activity information about the target object, the track point corresponding to the modal collection device may be taken as a single-mode track point.
S220, determining a single-mode track according to the single-mode track points, and determining the single-mode track map according to the single-mode track.
Wherein the single-mode trajectory may be an activity trajectory determined from a single-mode angle with respect to the target object within the target region. Specifically, since the single mode of the embodiment of the present invention includes: face, identification code, and vehicle. Accordingly, the single-mode trajectory may include: a face trajectory determined from a face perspective, an identification code trajectory determined from an identification code perspective, and a vehicle trajectory determined from a vehicle perspective. Specifically, after the single-mode track points are determined, each single-mode track point can be sequentially connected according to the appearance time of the target object corresponding to the single-mode track point, so that a single-mode track is obtained.
Further, the single-mode trajectory graph may be a space-time graph corresponding to the single-mode trajectory. Wherein the single-mode trajectory graph comprises: at least one of a face track map, an identification code track map, and a vehicle track map. Specifically, in the process of determining the single-mode track map, an edge set and an adjacent matrix related to time can be determined according to the single-mode track, and then the single-mode track map can be determined according to the edge set and the adjacent matrix. By converting the single-mode track into a single-mode track map, the track information of the target object can be conveniently analyzed based on time information.
Optionally, determining the single-mode trajectory graph according to the single-mode trajectory includes: determining at least one single-mode track node based on device position information of a mode acquisition device in the single-mode track; determining a single-mode edge set array according to the space distance and the time interval between single-mode track nodes in the single-mode track; determining a single-mode adjacency matrix according to the time sequence of the single-mode track node on the preset analysis duration; and determining a single-mode track graph according to the single-mode track nodes, the single-mode edge set arrays and the single-mode adjacency matrix.
Wherein the single-mode trajectory node may be a trajectory node that appears in a single-mode trajectory graph. Specifically, the single-mode track node, that is, the single-mode track point, has the same meaning. The spatial distance may be a corresponding actual position distance between the single-mode trajectory nodes. For example, the spatial distance may be determined from actual geographic location coordinates corresponding to the unimodal trajectory node. Further, the time interval may be a time interval in which the target object appears at a different single-mode trajectory node. Illustratively, the time that the target object appears at the single-mode trajectory node A is a1, the time that the target object appears at the single-mode trajectory node B is B1, and then the time interval between the single-mode trajectory node A and the single-mode trajectory node B is the difference of a 1-B1. Further, the unimodal edge set array may be an edge set array corresponding to a unimodal trajectory graph. Specifically, the single-mode edge set array can be determined according to the determined spatial distance and the determined time interval between the single-mode track nodes.
The unimodal adjacency matrix may be an adjacency matrix corresponding to the unimodal trajectory graph. Specifically, the single-mode adjacency matrix can be determined according to the time sequence of the single-mode track node on the preset analysis duration. The preset analysis duration may be a preset duration for performing data analysis. Specifically, the preset analysis duration may be equal to the duration of the data acquisition by the acquiring device.
S230, inputting each single-mode track diagram into a pre-trained single-mode track diagram representation model respectively to obtain a single-mode representation vector corresponding to the single-mode track diagram.
Wherein the single-mode trajectory graph representation model can analyze trajectory characteristics of the single-mode trajectory graph. The unimodal representation vector may be vector data characterizing the correlation of the trajectory features in the unimodal trajectory graph. Specifically, each single-mode track diagram can be input into a pre-trained single-mode track diagram representation model to obtain a single-mode representation vector corresponding to the single-mode track diagram. By determining the unimodal representation vectors, the trajectory features of the unimodal trajectory graphs may be quantified, facilitating subsequent determination of similarities between the unimodal trajectory graphs based on the unimodal representation vectors.
S240, respectively determining the vector similarity between every two single-mode representation vectors, and determining at least two single-mode track diagrams to be fused based on the vector similarity.
Wherein the vector similarity may be a single-modality representation of the degree of similarity between vectors. Specifically, the vector similarity may be determined by calculating the euclidean distance between the unimodal representation vectors, or the like. Further, the vector similarity and a preset similarity threshold value can be compared, and at least two single-mode track diagrams to be fused are determined according to the comparison result. Alternatively, respective similarity thresholds may be set between different unimodal representation vectors. For example, a first similarity threshold is set between the face representation vector and the recognition code representation vector; a second similarity threshold is set between the identification code representing vector and the vehicle representing vector, and a third similarity threshold is set between the face representing vector and the vehicle representing vector.
Further, the vector similarity between the two monomodal expression vectors and the corresponding similarity threshold value can be compared, and the monomodal trajectory graph corresponding to the vector similarity can be used as the monomodal trajectory graph to be fused under the condition that the vector similarity is greater than the similarity threshold value. Furthermore, similarity determination can be performed between every two single-mode expression vectors in the three single-mode expression vectors, so as to determine at least two single-mode graphs to be fused.
S250, fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object.
The target track graph can be a multi-mode track graph obtained by fusing the single-mode track graph. Specifically, after the single-mode track diagrams to be fused are determined, the track nodes can be rearranged and connected according to the time information corresponding to the track nodes in each single-mode track diagram, so that the target track diagram is determined.
Optionally, fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object, including: determining at least one target object track from each single-mode track map to be fused; and respectively determining object track points in each target object track, connecting each object track point based on a time point corresponding to each object track point to obtain a target object track corresponding to the target object, and determining a target track graph according to the target object track.
Wherein the target object trajectory may be a single-mode activity trajectory with respect to the target object. Specifically, the track in each single-mode track map can be split, so as to determine at least one target track. Specifically, the manner in which the single-mode trajectory graph is split is not limited herein. For example, the rail joints may be split in a single-mode trajectory graph from a temporal or spatial perspective.
Further, the object trajectory point may be an active trajectory node of the target object determined from a multi-modal perspective. Specifically, a single-mode track node in the target object track can be determined, and each single-mode track node is used as an object track point. The target object trajectory may be an activity trajectory with respect to the target object determined from a multi-modal perspective. Specifically, after the object track points are determined, according to the time corresponding to the object track points, connecting each object track point in sequence from the morning to the evening, so as to obtain a target object track, and finally determining a target track diagram according to the target object track.
Optionally, determining the target track map according to the target object track includes: determining at least one multi-mode track node based on device position information of a mode acquisition device in a target object track; determining a multi-mode edge set array according to the space distance and the time interval between multi-mode track nodes in the target object track; determining a multi-mode adjacency matrix according to the time sequence of the multi-mode track nodes on the preset analysis duration; and determining a target track graph according to the multi-mode track nodes, the multi-mode edge set array and the multi-mode adjacency matrix.
Wherein the multi-modal trajectory node may be a trajectory node that appears in a multi-modal trajectory graph. Specifically, the multi-mode track node, namely the object track point, has the same meaning. The spatial distance may be a corresponding actual position distance between the multi-modal trajectory nodes. For example, the spatial distance may be determined from actual geographic location coordinates corresponding to the multi-modal trajectory node. Further, the time interval may be a time interval in which the target object appears at different multi-modal trajectory nodes. Illustratively, the target object appears at the multi-modal trace node A for a time a1 and at the multi-modal trace node B for a time B1, then the time interval between the multi-modal trace node A and the multi-modal trace node B is the difference of a 1-B1. Further, the multi-mode edge set array may be an edge set array corresponding to the multi-mode trajectory graph. Specifically, the multi-mode edge set array may be determined according to the above-determined spatial distance and time interval between the multi-mode track nodes.
The multi-modal adjacency matrix may be an adjacency matrix corresponding to the multi-modal trajectory graph. Specifically, the multi-mode adjacency matrix can be determined according to the time sequence of the multi-mode track node on the preset analysis duration. The preset analysis duration may be a preset duration for performing data analysis. Specifically, the preset analysis duration may be equal to the duration of the data acquisition by the acquiring device.
S260, inputting the target track graph into a multi-modal track graph representation model trained in advance to obtain multi-modal representation vectors.
The multi-mode track graph representation model can analyze track characteristics of the multi-mode track graph. The multimodal representation vector may be vector data characterizing the correlation of the trace features in the multimodal trace map. Specifically, each multi-modal track map may be input into a pre-trained multi-modal track map representation model, so as to obtain multi-modal representation vectors corresponding to the multi-modal track map. By determining the multi-modal representation vector, track characteristics of the multi-modal track map can be quantified, so that the subsequent determination of the activity degree of the target object compared with the target area based on the multi-modal representation vector is facilitated.
S270, determining the target object type of the target object relative to the target area according to the multi-modal representation vector and a preset track vector threshold.
The preset trajectory vector threshold may be a preset threshold for determining the multimodal expression vector. Specifically, the multi-modal representation vector may be compared with a preset trajectory vector threshold, and a target object type of the target object relative to the target region may be determined according to the comparison result. The target object type may be a type representing the time that the target object is active within the target area. Specifically, the target object types include resident objects and non-resident objects. Specifically, it may be determined that the target object is a resident object when the multi-modal representation vector is greater than the preset trajectory vector threshold; in the case that the multimodal representation vector is less than the preset trajectory vector threshold, the target object may be determined to be a very resident object.
Illustratively, FIG. 3 is a workflow diagram for regional population analysis provided by an embodiment of the present invention. As shown in fig. 3, the field device captures facial images, IMSIs and license plate signals in real time, the signals are preprocessed and stored in a database to form corresponding track data, then each mode respectively constructs own track graph, inputs the characteristics of each mode track graph into a graph space-time neural network model based on similarity, inquires the characteristic similarity among the modes, combines tracks of the same object under different modes to form an object space-time track, and inputs the object characteristics obtained from the graph space-time neural network model based on interaction to perform regional population analysis.
The workflow may be divided into the following steps: step 1: data acquisition and preprocessing; step 2: constructing a single-mode track and a graph; step 3: training a graph neural network model based on similarity; step 4: object multi-mode track generation and track map construction; step 5: training a graph neural network model based on interaction; step 6: regional population analysis. Next, six steps of the embodiment of the present invention will be described in detail.
FIG. 4 is a flowchart of a data acquisition and preprocessing process according to an embodiment of the present invention. The purpose of this step is to receive data for the overall system and filter the abnormal data to provide a stable and clean data source for the overall system. As shown in fig. 4, the data acquisition and preprocessing includes the steps of:
step 1.1: and debugging the face camera to acquire stable face image data.
Step 1.2: filtering abnormal facial image data, and deleting data with abnormal longitude and latitude, non-facial image, no equipment place or acquisition time and other keywords missing.
Step 1.3: and debugging the detecting device to obtain stable IMSI data.
Step 1.4: the IMSI abnormal data is filtered, and the IMSI data with the missing important fields such as distance, direction and the like and the abnormal longitude and latitude are deleted.
Step 1.5: and debugging the license plate camera to obtain stable license plate image data.
Step 1.6: and filtering license plate abnormal data, and deleting license plate data with inconsistent license plate length, abnormal longitude and latitude, acquisition time or missing key fields of equipment and the like.
Step 1.7: the face, IMSI and license plate data are stored, and indexes are built for the time, longitude and latitude and ID of the data, so that the follow-up inquiry and data calling are facilitated.
FIG. 5 is a workflow diagram of a single-mode trajectory and graph construction provided by an embodiment of the present invention. The aim of this step is to form a space-time trajectory from the single-mode trajectory points and construct a single-mode trajectory graph based on the trajectory data. As shown in fig. 5, the single-mode trajectory and map construction includes the steps of:
step 2.1: and generating a face track. And extracting the characteristics of the facial images, and constructing a first file of people for clustering the facial images to form a facial track.
Step 2.2: and generating an IMSI track. And fusing the same IMSI track point data together to form IMSI track data.
Step 2.3: and generating a vehicle track. And fusing the track point data with the same license plate number to form the track data of the vehicle.
Step 2.4: for single-mode tracks, respectively constructing a space-time diagram based on similarityWhere V is the node set (longitude and latitude of the face camera, the detection device, the vehicle camera, respectively), et and At represent the edge set and the adjacency matrix of t, respectively. The edge set represents the spatial distance and time interval between nodes. The adjacency matrix based on the time-series pearson correlation coefficient is defined as: /(I)
Wherein,Time series of nodes i and j over time period t,/>, respectively，/>The time series averages of nodes i and j over time period t, respectively.
Further, step 3 is a graph neural network model training based on similarity. The method aims at training a model by using data, so that the model automatically mines rules from mass data and learns the representation of objects in different modal tracks.
The method aims at training a model by using data, so that the model automatically mines rules from mass data and learns the representation of objects in different modal tracks. Step 3 comprises the following steps:
step 3.1: and (5) inputting the space-time track diagram of each mode established in the step 2.4.
Step 3.2: and establishing a graph neural network model based on the similarity.
Step 3.3: and training a graph neural network model according to the labeling data.
Step 3.4: deploying a trained similarity-based graph neural network model.
FIG. 6 is a workflow diagram of multi-modal trajectory generation and trajectory graph construction provided by an embodiment of the present invention. The aim of the step is to fuse the track of the object between different modes and construct an object multi-mode track diagram so as to fully utilize the information between the modes. As shown in fig. 6, the multi-modal trajectory generation and trajectory graph construction includes the steps of:
Step 4.1: single-mode trajectory reasoning. And (3) reasoning the single-mode track by using the model in the step 3.4, and generating a track map representation vector.
Step 4.2: track similarity query. The trace diagrams among different modes represent vectors for similarity query.
Step 4.3: an object multi-modal trajectory is generated. And setting a track similarity threshold according to an actual result, and fusing tracks among different modes to obtain the multi-mode track of the object.
Step 4.4: and constructing an object multi-modal trajectory graph. Constructing an interaction-based space-time diagramWhere V is the node set (longitude and latitude of the face camera, the detection device, the vehicle camera, respectively), et and At represent the edge set and the adjacency matrix of t, respectively. The edge set represents the spatial distance and time interval between nodes. The adjacency matrix based on the time-series pearson correlation coefficient is defined as: /(I). Wherein/>Time series of nodes i and j over time period t,/>, respectively，/>The time series averages of nodes i and j over time period t, respectively.
Step 5 is interaction-based graph neural network model training. The purpose of this step is to train the model with data, letting the model learn from the massive data the representation of the object trajectory in different modes. Step 5 comprises the following steps:
Step 5.1: inputting the object multi-modal track map established in the step 4.4.
Step 5.2: and establishing an interaction-based graph neural network model.
Step 5.3: and training a graph neural network model according to the labeling data.
Step 5.4: deploying a trained interaction-based graph neural network model.
Step 6 is regional population analysis. The purpose of the steps is to perform a region analysis on the object to determine if the object is a resident object with respect to the target region. Step 6 comprises the following steps:
Step 6.1: object multimodal trajectory reasoning. And (3) reasoning the single-mode track by using the model in the step 3.4, and generating a track map representation vector.
Step 6.2: regional population analysis. Queries are conducted against actual demands, such as resident population and floating population are often concerned in regional population analysis, and corresponding thresholds can be set according to experiments and tests to conduct object classification and attribution.
According to the technical scheme provided by the embodiment of the invention, the face, the IMSI, the license plate equipment characteristics and the track characteristics are considered to construct the space-time track diagram, the multi-mode space-time track diagram of the object is formed, the data limit among different modes is broken, and the multi-mode track data is fully utilized to carry out efficient and accurate regional population analysis. The technical scheme provided by the embodiment of the invention can cope with noise points, reduces the interference of sparse data and noise data on a model, and has good adaptability to track sparsity.
According to the technical scheme provided by the embodiment of the invention, the single-mode track point related to the target object is determined by acquiring the equipment acquisition data of the modal acquisition equipment in the target area and according to the equipment acquisition data and the equipment position information of the modal acquisition equipment; determining a single-mode track according to the single-mode track points, and determining a single-mode track diagram according to the single-mode track; inputting each single-mode track diagram into a pre-trained single-mode track diagram representation model respectively to obtain a single-mode representation vector corresponding to the single-mode track diagram; respectively determining the vector similarity between every two single-mode representation vectors, and determining at least two single-mode track diagrams to be fused based on the vector similarity; fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to a target object; inputting the target track graph into a multi-modal track graph representation model trained in advance to obtain multi-modal representation vectors; and determining the type of the target object relative to the target area according to the multi-modal representation vector and the preset track vector threshold. The technical scheme of the embodiment of the invention solves the problem that the prior regional population technology cannot ensure higher analysis accuracy in a complex scene of regional population analysis, can fully utilize multi-mode track data to carry out comprehensive analysis, and then determines the regional population analysis result according to the analysis result, thereby improving the regional population analysis accuracy and efficiency.
Fig. 7 is a schematic structural diagram of an area population analysis device provided by the embodiment of the present invention, where the embodiment of the present invention is applicable to a scenario in which an activity track of a target object is analyzed to determine whether the target object is a resident population of a target area, and the device may be implemented by software and/or hardware, and integrated into a computer device with an application development function.
As shown in fig. 7, the regional population analysis apparatus includes: a unimodal trajectory graph determination module 310, a target trajectory graph determination module 320, and an object type determination module 330.
The single-mode track diagram determining module 310 is configured to obtain at least two single-mode track diagrams of the target object moving in the target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map; the target track diagram determining module 320 is configured to fuse at least two single-mode track diagrams to obtain a target track diagram corresponding to the target object; an object type determining module 330 is configured to determine an object type of the target object relative to the target area based on a track activity area in the target track map, where the object type is associated with an activity time of the target object in the target area.
According to the technical scheme provided by the embodiment of the invention, at least two single-mode track diagrams of the target object moving in the target area are obtained; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map; fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object; an object type of the target object relative to the target area is determined based on a track activity area in the target track graph, wherein the object type is associated with an activity time of the target object in the target area. The technical scheme of the embodiment of the invention solves the problem that the prior regional population technology cannot ensure higher analysis accuracy in a complex scene of regional population analysis, can fully utilize multi-mode track data to carry out comprehensive analysis, and then determines the regional population analysis result according to the analysis result, thereby improving the regional population analysis accuracy and efficiency.
In an alternative embodiment, the single-mode trajectory graph determining module 310 is specifically configured to: acquiring equipment acquisition data of modal acquisition equipment in the target area; wherein the modality acquisition device comprises: at least one of a face acquisition device, an identification code acquisition device, and a vehicle acquisition device; according to the device acquisition data and the device position information of the modal acquisition device, determining a single-mode track point related to a target object; and determining a single-mode track according to the single-mode track points, and determining the single-mode track graph according to the single-mode track.
In an alternative embodiment, the single-mode trajectory graph determining module 310 includes: a single-mode trajectory diagram determining unit configured to: determining at least one single-mode track node based on device position information of a mode acquisition device in the single-mode track; determining a single-mode edge set array according to the space distance and the time interval between single-mode track nodes in the single-mode track; determining a single-mode adjacency matrix according to the time sequence of the single-mode track node on the preset analysis duration; and determining the single-mode track graph according to the single-mode track nodes, the single-mode edge set array and the single-mode adjacency matrix.
In an alternative embodiment, the target trajectory graph determining module 320 is specifically configured to: inputting each single-mode track diagram into a pre-trained single-mode track diagram representation model respectively to obtain a single-mode representation vector corresponding to the single-mode track diagram; wherein the single-mode representation vector is vector data related to a trajectory feature; respectively determining the vector similarity between every two single-mode representation vectors, and determining at least two single-mode track diagrams to be fused based on the vector similarity; and fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object.
In an alternative embodiment, the target trajectory graph determining module 320 includes: a single-mode track diagram fusion unit, which is used for: determining at least one target object track from each single-mode track map to be fused; and respectively determining object track points in each target object track, connecting each object track point based on a time point corresponding to each object track point to obtain a target object track corresponding to the target object, and determining the target track map according to the target object track.
In an alternative embodiment, the single-mode trajectory graph fusion unit includes: a target trajectory graph determination subunit configured to: determining at least one multi-mode track node based on device position information of a mode acquisition device in the target object track; determining a multi-mode edge set array according to the space distance and the time interval between multi-mode track nodes in the target object track; determining a multi-mode adjacency matrix according to the time sequence of the multi-mode track node on the preset analysis duration; and determining the target track graph according to the multi-mode track nodes, the multi-mode edge set array and the multi-mode adjacency matrix.
In an alternative embodiment, the object type determining module 330 is specifically configured to: inputting the target track graph into a multi-modal track graph representation model trained in advance to obtain a multi-modal representation vector; wherein the multi-modal representation vector is vector data related to a trace map feature; and determining the target object type of the target object relative to the target area according to the multi-modal representation vector and a preset track vector threshold.
The regional population analysis device provided by the embodiment of the invention can execute the regional population analysis method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention. FIG. 8 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention. The computer device 12 may be any terminal device with computing power that may be configured in a regional population analysis device.
As shown in FIG. 8, the computer device 12 is in the form of a general purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 may be one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, commonly referred to as a "hard disk drive"). Although not shown in fig. 8, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable objects to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through network adapter 20. As shown in fig. 8, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in fig. 8, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the regional population analysis method provided by the present embodiment, the method includes:
acquiring at least two single-mode track diagrams of the activity of a target object in a target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object;
An object type of the target object relative to the target area is determined based on a track activity area in the target track graph, wherein the object type is associated with an activity time of the target object in the target area.
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a regional population analysis method as provided by any embodiment of the present invention, comprising:
acquiring at least two single-mode track diagrams of the activity of a target object in a target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object;
An object type of the target object relative to the target area is determined based on a track activity area in the target track graph, wherein the object type is associated with an activity time of the target object in the target area.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the subject computer, partly on the subject computer, as a stand-alone software package, partly on the subject computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the object computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the internet using an internet service provider).
Claims (5)
1. A method of regional population analysis, comprising:
acquiring at least two single-mode track diagrams of the activity of a target object in a target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object;
Determining an object type of the target object relative to the target area based on a track activity area in the target track graph, wherein the object type is associated with the activity time of the target object in the target area;
acquiring at least two single-mode track diagrams about a target object in a target area, wherein the single-mode track diagrams comprise:
Acquiring equipment acquisition data of modal acquisition equipment in the target area; wherein the modality acquisition device comprises: at least one of a face acquisition device, an identification code acquisition device, and a vehicle acquisition device;
According to the device acquisition data and the device position information of the modal acquisition device, determining a single-mode track point related to a target object;
determining a single-mode track according to the single-mode track points, and determining the single-mode track map according to the single-mode track;
The determining the single-mode track map according to the single-mode track comprises the following steps:
determining at least one single-mode track node based on device position information of a mode acquisition device in the single-mode track;
Determining a single-mode edge set array according to the space distance and the time interval between single-mode track nodes in the single-mode track;
Determining a single-mode adjacency matrix according to the time sequence of the single-mode track node on the preset analysis duration;
determining the single-mode track graph according to the single-mode track nodes, the single-mode edge set array and the single-mode adjacency matrix;
wherein the single-mode edge set array is an edge set array corresponding to the single-mode track graph; the single-mode adjacency matrix is an adjacency matrix corresponding to the single-mode track graph;
The fusing at least two single-mode track graphs to obtain a target track graph corresponding to the target object includes:
Inputting each single-mode track diagram into a pre-trained single-mode track diagram representation model respectively to obtain a single-mode representation vector corresponding to the single-mode track diagram; wherein the single-mode representation vector is vector data related to a trajectory feature;
respectively determining the vector similarity between every two single-mode representation vectors, and determining at least two single-mode track diagrams to be fused based on the vector similarity;
Fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object;
the fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object comprises the following steps:
Determining at least one target object track from each single-mode track map to be fused;
respectively determining object track points in each target object track, connecting each object track point based on a time point corresponding to each object track point to obtain a target object track corresponding to the target object, and determining the target track map according to the target object track;
wherein the determining the target track map according to the target object track includes:
Determining at least one multi-mode track node based on device position information of a mode acquisition device in the target object track;
determining a multi-mode edge set array according to the space distance and the time interval between multi-mode track nodes in the multi-mode track;
Determining a multi-mode adjacency matrix according to the time sequence of the multi-mode track node on the preset analysis duration;
and determining the target track graph according to the multi-mode track nodes, the multi-mode edge set array and the multi-mode adjacency matrix.
2. The method of claim 1, wherein the determining the object type of the target object relative to the target region based on the trajectory activity region in the target trajectory graph comprises:
Inputting the target track graph into a multi-modal track graph representation model trained in advance to obtain a multi-modal representation vector; wherein the multi-modal representation vector is vector data related to a trace map feature;
And determining the target object type of the target object relative to the target area according to the multi-modal representation vector and a preset track vector threshold.
3. A regional population analysis apparatus, the apparatus comprising:
the single-mode track diagram determining module is used for acquiring at least two single-mode track diagrams of the target object moving in the target area; the single-mode track map comprises at least one of a face track map, an identification code track map and a vehicle track map;
the target track diagram determining module is used for fusing at least two single-mode track diagrams to obtain a target track diagram corresponding to the target object;
an object type determining module, configured to determine an object type of the target object relative to the target area based on a track activity area in the target track map, where the object type is associated with an activity time of the target object in the target area;
wherein, the single-mode track diagram determining module is used for: acquiring equipment acquisition data of modal acquisition equipment in the target area; wherein the modality acquisition device comprises: at least one of a face acquisition device, an identification code acquisition device, and a vehicle acquisition device;
According to the device acquisition data and the device position information of the modal acquisition device, determining a single-mode track point related to a target object;
determining a single-mode track according to the single-mode track points, and determining the single-mode track map according to the single-mode track;
The single-mode track diagram determining module comprises: a single-mode trajectory diagram determining unit configured to: determining at least one single-mode track node based on device position information of a mode acquisition device in the single-mode track;
Determining a single-mode edge set array according to the space distance and the time interval between single-mode track nodes in the single-mode track;
Determining a single-mode adjacency matrix according to the time sequence of the single-mode track node on the preset analysis duration;
Determining the single-mode track graph according to the single-mode track nodes, the single-mode edge set array and the single-mode adjacency matrix; wherein the single-mode edge set array is an edge set array corresponding to the single-mode track graph; the single-mode adjacency matrix is an adjacency matrix corresponding to the single-mode track graph;
Wherein, the single-mode track diagram determining module comprises: a single-mode trajectory diagram determining unit configured to: determining at least one single-mode track node based on device position information of a mode acquisition device in the single-mode track; determining a single-mode edge set array according to the space distance and the time interval between single-mode track nodes in the single-mode track; determining a single-mode adjacency matrix according to the time sequence of the single-mode track node on the preset analysis duration; determining the single-mode track graph according to the single-mode track nodes, the single-mode edge set array and the single-mode adjacency matrix;
The target track diagram determining module is used for: inputting each single-mode track diagram into a pre-trained single-mode track diagram representation model respectively to obtain a single-mode representation vector corresponding to the single-mode track diagram; wherein the single-mode representation vector is vector data related to a trajectory feature; respectively determining the vector similarity between every two single-mode representation vectors, and determining at least two single-mode track diagrams to be fused based on the vector similarity; fusing at least two single-mode track graphs to be fused to obtain a target track graph corresponding to the target object;
Wherein, the target track diagram determining module comprises: a single-mode track diagram fusion unit, which is used for: determining at least one target object track from each single-mode track map to be fused; respectively determining object track points in each target object track, connecting each object track point based on a time point corresponding to each object track point to obtain a target object track corresponding to the target object, and determining the target track map according to the target object track;
The single-mode track map fusion unit comprises: a target trajectory graph determination subunit configured to: determining at least one multi-mode track node based on device position information of a mode acquisition device in the target object track; determining a multi-mode edge set array according to the space distance and the time interval between multi-mode track nodes in the multi-mode track; determining a multi-mode adjacency matrix according to the time sequence of the multi-mode track node on the preset analysis duration; and determining the target track graph according to the multi-mode track nodes, the multi-mode edge set array and the multi-mode adjacency matrix.
4. A computer device, the computer device comprising:
One or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the regional population analysis method of any one of claims 1-2.
5. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the regional population analysis method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410172388.7A CN117726883B (en) | 2024-02-07 | 2024-02-07 | Regional population analysis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410172388.7A CN117726883B (en) | 2024-02-07 | 2024-02-07 | Regional population analysis method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117726883A CN117726883A (en) | 2024-03-19 |
| CN117726883B true CN117726883B (en) | 2024-05-24 |
Family
ID=90207279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410172388.7A Active CN117726883B (en) | 2024-02-07 | 2024-02-07 | Regional population analysis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117726883B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325056A (en) * | 2018-12-14 | 2020-06-23 | 成都云天励飞技术有限公司 | Floating population analysis method and related product |
| CN111695511A (en) * | 2020-06-12 | 2020-09-22 | 中国人民公安大学 | Object management method, device, machine readable medium and equipment based on urban community |
| CN112348265A (en) * | 2020-11-10 | 2021-02-09 | 交控科技股份有限公司 | Feasible path mining method and device under monitoring scene |
| EP3989031A1 (en) * | 2020-10-26 | 2022-04-27 | Volvo Car Corporation | Systems and methods for fusing road friction data to enhance vehicle maneuvering |
| CN115345390A (en) * | 2022-10-19 | 2022-11-15 | 武汉大数据产业发展有限公司 | Behavior trajectory prediction method and device, electronic equipment and storage medium |
| CN116842432A (en) * | 2023-04-04 | 2023-10-03 | 成都合络创新科技有限公司 | Car code association and face code association method in electric image calculation |
| CN117076788A (en) * | 2023-05-10 | 2023-11-17 | 武汉众智数字技术有限公司 | Personnel foothold point location analysis method and system based on multidimensional sensing data |
-
2024
- 2024-02-07 CN CN202410172388.7A patent/CN117726883B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325056A (en) * | 2018-12-14 | 2020-06-23 | 成都云天励飞技术有限公司 | Floating population analysis method and related product |
| CN111695511A (en) * | 2020-06-12 | 2020-09-22 | 中国人民公安大学 | Object management method, device, machine readable medium and equipment based on urban community |
| EP3989031A1 (en) * | 2020-10-26 | 2022-04-27 | Volvo Car Corporation | Systems and methods for fusing road friction data to enhance vehicle maneuvering |
| CN112348265A (en) * | 2020-11-10 | 2021-02-09 | 交控科技股份有限公司 | Feasible path mining method and device under monitoring scene |
| CN115345390A (en) * | 2022-10-19 | 2022-11-15 | 武汉大数据产业发展有限公司 | Behavior trajectory prediction method and device, electronic equipment and storage medium |
| CN116842432A (en) * | 2023-04-04 | 2023-10-03 | 成都合络创新科技有限公司 | Car code association and face code association method in electric image calculation |
| CN117076788A (en) * | 2023-05-10 | 2023-11-17 | 武汉众智数字技术有限公司 | Personnel foothold point location analysis method and system based on multidimensional sensing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117726883A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110175527B (en) | Pedestrian re-identification method and device, computer equipment and readable medium | |
| CN110472531B (en) | Video processing method, device, electronic equipment and storage medium | |
| CN112380981B (en) | Face key point detection method and device, storage medium and electronic equipment | |
| CN112770265B (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
| CN116778292B (en) | Method, device, equipment and storage medium for fusing space-time trajectories of multi-mode vehicles | |
| CN112560829B (en) | Crowd quantity determination method, device, equipment and storage medium | |
| CN109902681B (en) | User group relation determining method, device, equipment and storage medium | |
| CN110851488A (en) | Multi-source-based multi-modal data fusion analysis processing method and platform | |
| CN114637884B (en) | Method, device and equipment for matching cable-stayed cable-computed space-time trajectory with road network | |
| CN112309126A (en) | License plate detection method and device, electronic equipment and computer readable storage medium | |
| CN115690153A (en) | Intelligent agent track prediction method and system | |
| CN110363193B (en) | Vehicle weight recognition method, device, equipment and computer storage medium | |
| CN117011581A (en) | Image recognition method, medium, device and computing equipment | |
| CN111126422B (en) | Method, device, equipment and medium for establishing industry model and determining industry | |
| CN117240632B (en) | Attack detection method and system based on knowledge graph | |
| CN114422848A (en) | Video segmentation method and device, electronic equipment and storage medium | |
| CN113869364A (en) | Image processing method, image processing apparatus, electronic device, and medium | |
| CN117726883B (en) | Regional population analysis method, device, equipment and storage medium | |
| CN112580616A (en) | Crowd quantity determination method, device, equipment and storage medium | |
| CN115169588A (en) | Electrographic computation space-time trajectory vehicle code correlation method, device, equipment and storage medium | |
| CN115576990A (en) | Method, device, equipment and medium for evaluating visual truth value data and perception data | |
| CN114842261A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN113642443A (en) | Model testing method and device, electronic equipment and storage medium | |
| CN112925948A (en) | Video processing method and device, medium, chip and electronic equipment thereof | |
| CN112989083B (en) | Personnel identity analysis 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |