CN113837034A - Aggregated population monitoring method, device and computer storage medium - Google Patents
Aggregated population monitoring method, device and computer storage medium Download PDFInfo
- Publication number
- CN113837034A CN113837034A CN202111052188.0A CN202111052188A CN113837034A CN 113837034 A CN113837034 A CN 113837034A CN 202111052188 A CN202111052188 A CN 202111052188A CN 113837034 A CN113837034 A CN 113837034A
- Authority
- CN
- China
- Prior art keywords
- target
- monitoring
- preset
- coincidence
- crowd
- 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
Landscapes
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The application provides a crowd accumulation monitoring method, equipment and a computer storage medium, which mainly comprise the steps of obtaining target monitoring crowds meeting a preset crowd accumulation threshold value from each monitoring image according to the preset crowd accumulation threshold value, obtaining target coincidence values corresponding to the target objects according to the target objects identified from the target monitoring crowds, and determining the target objects of which the target coincidence values exceed the preset coincidence threshold value according to the preset coincidence threshold value. Therefore, the clustering analysis method and the clustering analysis device can perform clustering analysis on the gathered crowd.
Description
Technical Field
The embodiment of the application relates to the technical field of image recognition, in particular to a method and a device for monitoring crowds and a computer storage medium.
Background
The existing identification of the crowd gathering is mainly realized by human judgment, so that a large amount of manpower is consumed, and the condition of misjudgment and missed judgment is easy to occur.
In view of the above, a technical solution capable of performing automatic identification for various crowds in a public place is needed.
Disclosure of Invention
In view of the foregoing, the present application provides a method, an apparatus, and a computer storage medium for monitoring an aggregated population, which can perform cluster analysis on the aggregated population to identify the aggregated population.
The application provides a crowd monitoring method in a first aspect, which includes: acquiring target monitoring people meeting a preset aggregation people number threshold from each monitoring image according to the preset aggregation people number threshold; acquiring each target coincidence value corresponding to each target object according to each target object identified from each target monitoring crowd; and acquiring each target object of which the target coincidence value exceeds a preset coincidence threshold value according to the preset coincidence threshold value.
A second aspect of the present application provides a computer storage medium, wherein instructions for executing steps of the aggregated population monitoring method according to the first aspect are stored in the computer storage medium
A third aspect of the present application provides an aggregated population monitoring device, comprising: the acquisition module is used for acquiring target monitoring crowds meeting a preset aggregation population threshold value from each monitoring image according to the preset aggregation population threshold value; and the analysis module is used for acquiring each target coincidence value corresponding to each target object according to each target object identified from each target monitoring crowd, and determining each target object of which the target coincidence value exceeds the preset coincidence threshold value according to a preset coincidence threshold value.
In summary, the method, the device and the computer storage medium for monitoring the crowd gathering in the embodiment of the present application can automatically identify the crowd gathering according to the preset crowd gathering threshold and the preset coincidence threshold.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart illustrating an aggregated population monitoring method according to a first embodiment of the present application.
Fig. 2 is a flowchart illustrating an aggregated population monitoring method according to a second embodiment of the present application.
Fig. 3 is a flowchart illustrating an aggregated population monitoring method according to a third embodiment of the present application.
Fig. 4 is a schematic diagram of an architecture of an aggregated crowd monitoring apparatus according to a fifth embodiment of the present application.
Element number
400: an aggregated population monitoring device; 402: an acquisition module; 404: and an analysis module.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application shall fall within the scope of the protection of the embodiments in the present application.
The following further describes specific implementations of embodiments of the present application with reference to the drawings of the embodiments of the present application.
First embodiment
Fig. 1 shows a flow chart of an aggregated population monitoring method according to a first embodiment of the present application. As shown in the figure, the present embodiment mainly includes the following steps:
and S102, acquiring target monitoring crowds meeting the preset aggregation people number threshold from each monitoring image according to the preset aggregation people number threshold.
Alternatively, each monitoring image may be acquired with each monitoring apparatus (e.g., a monitoring camera) provided in a public place.
Optionally, the acquired monitoring image may include a panoramic image.
Optionally, the number of the crowd in the monitored image can be detected, the number of the crowd in the monitored image is identified, and when the number of the crowd in the monitored image exceeds a preset threshold value of the number of the crowd in the monitored image, the crowd in the monitored image is determined as the target monitored crowd.
For example, assuming that the preset aggregated population threshold is set to 5 people, when it is detected that the number of aggregated population in the monitored image is not less than 5 people, the aggregated population in the monitored image is determined as the target monitored population.
And step S104, acquiring each target coincidence value corresponding to each target object according to each target object identified from each target monitoring crowd.
In this embodiment, each target monitoring crowd may be identified, each target object in each target monitoring crowd may be obtained, and the number of occurrences of each target object in each target monitoring crowd may be counted to obtain each target coincidence value corresponding to each target object.
For example, when a certain target object (a monarch) is detected to appear in the target monitoring crowd a and the target monitoring crowd B successively, the target coincidence value of the monarch is 2.
Optionally, each target monitoring crowd may be identified by using a head-shoulder recognition technology and/or a face recognition technology to obtain each target object in each target monitoring crowd.
And step S106, acquiring each target object with the target coincidence value exceeding the preset coincidence threshold according to the preset coincidence threshold.
Specifically, one target object may be used as the current target object, an analysis result that the target coincidence value of the current target object exceeds or does not exceed the preset coincidence threshold value is obtained according to the preset coincidence threshold value and the target coincidence value of the current target object, and if the target coincidence value of the current target object exceeds the preset coincidence threshold value, the current target object (for example, the identity information of the current target object) is output.
Preferably, a corresponding prompt message (e.g., an alert message) may be further output for each target object whose target coincidence value exceeds the preset coincidence threshold.
In summary, the method for monitoring the crowds in the embodiment of the application can perform cluster analysis on various crowds in a public place according to the preset threshold of the number of the crowds and the preset coincidence threshold, and therefore the method is particularly suitable for automatically screening the behaviors of the crowds.
Second embodiment
Fig. 2 shows an aggregated population monitoring method according to a second embodiment of the present application, which can be used as a preprocessing step of the step S102, as shown in the figure, the method of this embodiment mainly includes the following steps:
step S202, obtaining each monitoring image of each monitoring device and each monitoring area corresponding to each monitoring image.
Alternatively, the monitoring device may include various types of cameras disposed in respective designated areas of a public place.
And step S204, acquiring each monitoring image of which the monitoring area meets the preset target area according to the preset target area.
Optionally, an area (e.g., a patrol blind area) in a public place that needs to be focused on may be set to generate a preset target area, and each monitored image that meets the preset target area is screened from each monitored image for performing subsequent analysis processing, so as to improve the monitoring processing efficiency.
Optionally, a corresponding preset target time period may be set according to a high-speed time period of the behavior of the crowd gathering, the shooting time corresponding to each monitoring image is obtained to serve as each monitoring time corresponding to each monitoring image, and each monitoring image of which the monitoring time meets the preset target time period is obtained according to the preset target time period to perform subsequent analysis processing, so as to improve the monitoring processing efficiency.
Therefore, the method and the device for monitoring the image quality can screen each acquired monitoring image by setting the preset target area and the preset target time period, so that the processing efficiency of monitoring analysis is effectively improved, and the system operation load can be reduced.
Third embodiment
Fig. 3 is a flowchart illustrating an aggregated population monitoring method according to a third embodiment of the present application. As shown in the figure, the present embodiment mainly includes the following steps:
continuing to the step S102, continuing to execute the step S302, and obtaining the number of times of the same frame of the target group consisting of at least two target objects in each target monitoring group according to each target object identified from each target monitoring group.
For example, the number of times of the same frame between the target objects may be counted according to the target objects identified from the target monitoring groups, for example, three target objects of a monarch, B monarch and C may be determined as one target group, and the number of times of the same frame of the target group in the target monitoring groups may be counted.
And step S304, acquiring a target group with the same frame times exceeding a preset same frame threshold according to the preset same frame threshold.
Specifically, assuming that the preset same-frame threshold is set to 3 times, when the number of times of the same frame of the target group consisting of the group a, the group B, and the group C in each target monitoring group reaches 3 times or more, the relevant prompt information (for example, the warning information) is output for the target group consisting of the group a, the group B, and the group C.
To sum up, the embodiment of the application can achieve the technical effect of effectively monitoring the behaviors of the crowd gathering by automatically identifying the number of times of the same frame among all target objects in the crowd monitoring the target.
Fourth embodiment
A fourth embodiment of the present application provides a computer storage medium, in which instructions for executing the steps of the aggregated population monitoring method according to the above embodiments are stored.
Fifth embodiment
Fig. 4 shows an architecture diagram of an aggregated population monitoring device 400 according to a fifth embodiment of the present application. As shown, the aggregated population monitoring device 400 of the present embodiment mainly includes an acquisition module 402 and an analysis module 404.
The obtaining module 402 is configured to obtain, from each monitored image, each target monitored crowd meeting a preset aggregation people number threshold according to the preset aggregation people number threshold.
Optionally, the obtaining module 402 is further configured to obtain each monitoring image of each monitoring device and each monitoring area corresponding to each monitoring image; and acquiring each monitoring image of which the monitoring area meets the preset target area according to the preset target area.
Optionally, the obtaining module 402 is further configured to obtain each monitoring time corresponding to each monitoring image; and acquiring each monitoring image of which the monitoring time meets the preset target time period according to the preset target time period.
Optionally, the monitoring image comprises a panoramic image.
The analysis module 404 is configured to obtain, according to each target object identified from each target monitoring crowd, each target coincidence value corresponding to each target object, and determine, according to a preset coincidence threshold, each target object whose target coincidence value exceeds the preset coincidence threshold.
Optionally, the analysis module 404 is further configured to identify each target monitoring population, and obtain each target object in each target monitoring population; and counting the occurrence times of each target object in each target monitoring crowd, and acquiring each target coincidence value corresponding to each target object.
Optionally, the analysis module 404 is further configured to identify each target monitoring crowd by using a head-shoulder recognition technology and/or a face recognition technology, and obtain each target object in each target monitoring crowd.
Optionally, the analysis module 404 is further configured to, for each of the target objects, perform the following steps: according to the preset coincidence threshold value and the target coincidence value of the target object, obtaining an analysis result that the target coincidence value of the target object exceeds or does not exceed the preset coincidence threshold value; and responding to the analysis result that the target coincidence value of the target object exceeds the preset coincidence threshold value, and outputting prompt information of the target object.
Optionally, the analysis module 404 is further configured to obtain, according to each target object identified from each target monitoring population, the number of times of the same frame of a target population in each target monitoring population, where the target population is composed of at least two target objects; and acquiring the target group with the same frame times exceeding the preset same frame threshold according to the preset same frame threshold.
In addition, the aggregated group monitoring apparatus 400 according to the embodiment of the present invention may also be used to implement other steps in the foregoing aggregated group monitoring method embodiments, and has the beneficial effects of the corresponding method step embodiments, which are not described herein again.
In summary, the aggregated population monitoring method, the device and the computer storage medium according to the embodiments of the present application may identify the occurrence number of each target object in the aggregated population and the number of times of the same frame between each target object, so as to analyze the aggregated population.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the embodiments of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A method of aggregate population monitoring, comprising:
acquiring target monitoring people meeting a preset aggregation people number threshold from each monitoring image according to the preset aggregation people number threshold;
acquiring each target coincidence value corresponding to each target object according to each target object identified from each target monitoring crowd; and
and acquiring each target object of which the target coincidence value exceeds a preset coincidence threshold value according to the preset coincidence threshold value.
2. The method for monitoring people gathering according to claim 1, further comprising:
acquiring each monitoring image of each monitoring device and each monitoring area corresponding to each monitoring image;
and acquiring each monitoring image of which the monitoring area meets the preset target area according to the preset target area.
3. The method for crowd monitoring as recited in claim 2, further comprising:
acquiring each monitoring time corresponding to each monitoring image;
and acquiring each monitoring image of which the monitoring time meets the preset target time period according to the preset target time period.
4. The aggregated population monitoring method of claim 1, wherein the monitored images comprise panoramic images.
5. The method for monitoring the crowd according to claim 1, wherein the obtaining, according to the target objects identified from the target monitored crowd, target coincidence values corresponding to the target objects comprises:
identifying each target monitoring crowd and acquiring each target object in each target monitoring crowd;
and counting the occurrence times of each target object in each target monitoring crowd, and acquiring each target coincidence value corresponding to each target object.
6. The crowd monitoring method of claim 5, wherein the identifying each of the target monitored populations and obtaining each of the target objects in each of the target monitored populations comprises:
and identifying each target monitoring crowd by using a head-shoulder identification technology and/or a face identification technology, and acquiring each target object in each target monitoring crowd.
7. The method for monitoring the aggregated population according to claim 1, wherein the determining, according to a preset coincidence threshold, each of the target objects whose target coincidence value exceeds the preset coincidence threshold comprises:
for each of the target objects, performing the steps of:
according to the preset coincidence threshold value and the target coincidence value of the target object, obtaining an analysis result that the target coincidence value of the target object exceeds or does not exceed the preset coincidence threshold value;
and responding to the analysis result that the target coincidence value of the target object exceeds the preset coincidence threshold value, and outputting prompt information of the target object.
8. The method for monitoring people gathering according to claim 1, further comprising:
according to each target object identified from each target monitoring crowd, acquiring the number of times of the same frame of a target crowd consisting of at least two target objects in each target monitoring crowd; and
and acquiring the target group with the same frame times exceeding the preset same frame threshold according to the preset same frame threshold.
9. A computer storage medium having stored therein instructions for performing the steps of the aggregated population monitoring method of any one of claims 1 to 8.
10. An aggregated population monitoring device, comprising:
the acquisition module is used for acquiring target monitoring crowds meeting a preset aggregation population threshold value from each monitoring image according to the preset aggregation population threshold value;
and the analysis module is used for acquiring each target coincidence value corresponding to each target object according to each target object identified from each target monitoring crowd, and determining each target object of which the target coincidence value exceeds the preset coincidence threshold value according to a preset coincidence threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111052188.0A CN113837034A (en) | 2021-09-08 | 2021-09-08 | Aggregated population monitoring method, device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111052188.0A CN113837034A (en) | 2021-09-08 | 2021-09-08 | Aggregated population monitoring method, device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837034A true CN113837034A (en) | 2021-12-24 |
Family
ID=78958633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111052188.0A Pending CN113837034A (en) | 2021-09-08 | 2021-09-08 | Aggregated population monitoring method, device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837034A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018228174A1 (en) * | 2017-06-16 | 2018-12-20 | 腾讯科技（深圳）有限公司 | Method, apparatus and device for obtaining object density, and storage medium |
| CN109446989A (en) * | 2018-10-29 | 2019-03-08 | 上海七牛信息技术有限公司 | Crowd massing detection method, device and storage medium |
| CN111027518A (en) * | 2019-12-26 | 2020-04-17 | 广州市炬盾科技发展有限公司 | Suspicious crowd intelligent alarm method and device, computer equipment and storage medium |
| CN111325048A (en) * | 2018-12-13 | 2020-06-23 | 杭州海康威视数字技术股份有限公司 | A kind of people gathering detection method and device |
| CN111405239A (en) * | 2020-02-17 | 2020-07-10 | 浙江大华技术股份有限公司 | Monitoring method, server, monitoring system, and computer-readable storage medium |
-
2021
- 2021-09-08 CN CN202111052188.0A patent/CN113837034A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018228174A1 (en) * | 2017-06-16 | 2018-12-20 | 腾讯科技（深圳）有限公司 | Method, apparatus and device for obtaining object density, and storage medium |
| CN109446989A (en) * | 2018-10-29 | 2019-03-08 | 上海七牛信息技术有限公司 | Crowd massing detection method, device and storage medium |
| CN111325048A (en) * | 2018-12-13 | 2020-06-23 | 杭州海康威视数字技术股份有限公司 | A kind of people gathering detection method and device |
| CN111027518A (en) * | 2019-12-26 | 2020-04-17 | 广州市炬盾科技发展有限公司 | Suspicious crowd intelligent alarm method and device, computer equipment and storage medium |
| CN111405239A (en) * | 2020-02-17 | 2020-07-10 | 浙江大华技术股份有限公司 | Monitoring method, server, monitoring system, and computer-readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 编辑部: "海康威视400万职能人员检测筒机型网络摄像机", pages 1 - 4, Retrieved from the Internet <URL:https://www.asmag.com.cn/test/202012/70855.html> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112291520B (en) | Abnormal event identification method and device, storage medium and electronic device | |
| CN111898581A (en) | Animal detection method, device, electronic equipment and readable storage medium | |
| CN109711318B (en) | Multi-face detection and tracking method based on video stream | |
| CN103514694A (en) | Intrusion detection monitoring system | |
| CN110781853A (en) | Crowd abnormality detection method and related device | |
| CN110705472A (en) | Off-duty method and system based on video image recognition | |
| CN107330414A (en) | Act of violence monitoring method | |
| CN110781735A (en) | Alarm method and system for identifying on-duty state of personnel | |
| CN108174198B (en) | Video image quality diagnosis analysis detection device and application system | |
| CN110619308A (en) | Aisle sundry detection method, device, system and equipment | |
| CN114049732A (en) | Transformer substation video monitoring method and system and storage medium | |
| CN117978969A (en) | AI video management platform applied to aquaculture | |
| CN111818286A (en) | Video monitoring equipment fault detection system | |
| CN115346150B (en) | A violent behavior detection method and system based on edge computing | |
| CN112929604A (en) | Office image acquisition management system | |
| CN114139016A (en) | Data processing method and system for intelligent cell | |
| CN115861929A (en) | Monitoring system, method, equipment and storage medium for service specification of electric power business hall | |
| CN119832673B (en) | A campus security system based on the Internet of Things and its service terminal | |
| CN113837034A (en) | Aggregated population monitoring method, device and computer storage medium | |
| CN120125850A (en) | Image data processing method and system | |
| CN109120896B (en) | Security video monitoring guard system | |
| CN113902993A (en) | Environmental state analysis method and system based on environmental monitoring | |
| CN115511142B (en) | Logistics transfer field early warning management method, device, computer equipment and storage medium | |
| CN113592014B (en) | Identification method and device of safety helmet, computer equipment and storage medium | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211224 |