CN118072375A - Face image acquisition system - Google Patents
Face image acquisition system Download PDFInfo
- Publication number
- CN118072375A CN118072375A CN202410460168.4A CN202410460168A CN118072375A CN 118072375 A CN118072375 A CN 118072375A CN 202410460168 A CN202410460168 A CN 202410460168A CN 118072375 A CN118072375 A CN 118072375A
- Authority
- CN
- China
- Prior art keywords
- unit
- video
- image acquisition
- abnormal
- video data
- 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.)
- Granted
Links
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000013500 data storage Methods 0.000 claims abstract description 17
- 238000009434 installation Methods 0.000 claims abstract description 10
- 230000002159 abnormal effect Effects 0.000 claims description 36
- 238000012544 monitoring process Methods 0.000 claims description 31
- 230000033001 locomotion Effects 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 5
- 239000003990 capacitor Substances 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 208000006011 Stroke Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a face image acquisition system, which relates to the technical field of face image acquisition and comprises the following components: a face image acquisition system comprises a camera installation and debugging unit, a field image acquisition unit, a video data processing unit, a calculation and analysis module, a warning unit, a video data storage planning module and a comprehensive power supply module; the comprehensive power supply module is used for supplying electric energy to the camera installation and debugging unit and the video data storage planning module. The invention is applied to banks, can rapidly study and analyze video of time slots based on face recognition, can automatically screen and judge personnel appearing in sites and time slots and suspected abnormal behavior personnel and abnormal behavior degree of abnormal behavior personnel, and can rapidly screen and identify biological evidence by matching with face recognition.
Description
Technical Field
The invention relates to the technical field of face image acquisition, in particular to a face image acquisition system.
Background
The face image acquisition system is a system based on data acquisition and monitoring of people, and in the traditional monitoring mode system at present, video evidence needs to be rapidly analyzed and identified through an identification department to biological evidence and forensic data in the video so as to improve the effect of investigation and judgment.
However, in the existing video evidence, most of the video evidence is a direct monitoring record of a long-period on-site time period, and forensic authentication and judicial authentication personnel may be required to observe and judge illegal personnel for a long time, so that the time and efficiency of authentication and research and judgment are reduced.
Disclosure of Invention
The invention aims to provide a face image acquisition system which solves the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the utility model provides a face image acquisition system which characterized in that: comprising the following steps: the system comprises a camera mounting and debugging unit, a field image acquisition unit, a video data processing unit, a calculation and analysis module, a warning unit, a video data storage planning module and a comprehensive power supply module;
The comprehensive power supply module is used for supplying electric energy to the camera installation and debugging unit and the video data storage planning module, shooting the conditions in the periphery of the bank under the cooperation of the camera installation and debugging unit and the on-site image acquisition unit, uploading the data to the video data processing unit for calculation and analysis, and automatically uploading the data to the video data storage planning module for storage;
The video data in the video data processing unit is subjected to overall planning of information through the calculation and analysis module to calculate abnormal states of personnel on the bank site, and the corresponding alarm and warning are carried out through the warning unit;
the calculation and analysis module comprises: the device comprises a frame difference algorithm unit, an abnormal behavior identification judgment algorithm unit and an abnormal behavior degree judgment algorithm unit.
Optionally, the calculation and analysis module comprises a frame difference algorithm unit, an abnormal behavior identification judgment algorithm unit and an abnormal behavior degree judgment algorithm unit;
The frame rate difference algorithm unit is as follows:
the frame difference algorithm unit is expressed as: the ZT classifies the conditions near the bank according to the difference among a plurality of frames in the video to obtain someone and no person, and the specific algorithm formula is as follows:
Splitting the processed video into a framing sequence: (Z1, Z2 … … Zn);
For each group of adjacent frames Zt and Z (t+1), calculating adjacent frame difference values ;
Detecting the motion of the frame difference value Y to determine the number of people in the motion area of the adjacent framesWherein (x, y) represents a pixel point in a moving image;
for each frame, carrying out de-duplication processing on the detected number of people to ensure that each person is only counted once, and obtaining the number of the face after de-duplication 。
Optionally, the abnormal behavior recognition and judgment algorithm unit is as follows:
Residence time of the same person in different time periods in frame rate difference algorithm unit ；
Wherein; (n) refers to the number of times a person appears in a video;
(ti+1) and (ti) are the time points of the i-th and i+1th occurrences, respectively;
Speed of movement of person ；
Wherein: (b 1, c 1) and (b 2, c 2) respectively represent the positions of persons between two frames;
U shows the time interval between two frames;
The motion amplitude e is calculated by the area of a boundary box on the assumption that the motion trail of the person in a certain period of time is represented by the boundary box;
Where h is the area of the bounding box;
abnormal behavior judgment: inputting a moving speed v, an activity amplitude e and a stay time T;
setting a threshold value: a movement speed threshold va-vb, an activity amplitude ea-eb and a dwell time Ta-Tb;
if v, e and T are within the threshold values of va-vb, ea-eb and Ta-Tb, then the person is evidenced to have abnormal behavior.
Optionally, the abnormal behavior degree judgment algorithm unit is as follows:
；
T is the residence time T, (n) is the number of times (n) that the person appears in the video, and X is the sum of the accumulated numbers of people;
Setting a threshold value: qa (0% -25%) is low risk, qa (25% -74%) is medium risk and Qa (74% -100%) is high risk, abnormal people near a bank and the abnormal degree of the abnormal people are obtained through the formula, an abnormal video picture of a target abnormal person is called out through a frame difference algorithm unit, and information of suspicious people is rapidly judged by matching with the comparison of a face recognition algorithm module and a database.
Optionally, the camera installation and debugging unit adopts: the device comprises a high-definition camera, a network camera and a cloud camera, wherein the high-definition camera is used for capturing real-time images of a monitoring area;
the network camera is used for remotely monitoring the bank;
and the cloud camera uploads the video monitoring data to the cloud for remote access by other devices.
Optionally, the on-site image acquisition unit includes: the device comprises a video monitoring unit, a video recording unit and a motion detection unit;
the video monitoring unit is used for monitoring the internal and external areas of the bank;
The video recording unit is used for recording and monitoring video and storing the video; the motion detection unit can identify and monitor abnormal behaviors of people appearing in the bank.
Optionally, the integrated power module includes: the system comprises an external power transmission unit and an emergency standby power supply, wherein the external power transmission unit is an external power transmission cable and is used for directly supplying power to electric equipment in the system through the external power transmission cable and is controlled by a control center.
Optionally, the urgent standby power supply is super large electric capacity, in case when the emergent power failure outage appears, super large electric capacity is switched by control center and is regulated and control to carry out urgent power supply to the inside electrical apparatus of this system, the warning unit includes: the system comprises a display alarm assembly and a prompt alarm assembly, wherein the display alarm assembly is used for sending an abnormal signal to an administrator computer, and the prompt alarm assembly is used for sending an audible and visual alarm signal inside a bank.
Optionally, the video data storage planning module includes: the video data processing unit can call the video data in the video data storage module, delete and tear useless fragments in the video data through the calculation analysis module, and conduct video export through the calculation analysis module. The device comprises a frame difference algorithm unit, an abnormal behavior identification judgment algorithm unit and an abnormal behavior degree judgment algorithm unit.
Compared with the prior art, the invention has the following beneficial effects:
According to the invention, a plurality of videos are subjected to time period separation for one time, then the separated video segments are subjected to frame difference algorithm unit calculation, personnel existing in the on-site time period are firstly judged, then the abnormal behavior recognition judgment algorithm unit is combined with the number of the face after the duplication removal obtained in the frame difference algorithm unit, the time of stay of a personal bank area is obtained, the time required by the person for bank processing business is combined for carrying out research judgment, the occurrence frequency is required to be combined with whether the person is currently processing business or not for comparison and analysis, otherwise, the abnormal behavior degree judgment algorithm unit integrates the data of the frame difference algorithm unit and the abnormal behavior recognition judgment algorithm unit (the abnormal people existing in different time points from the frame difference algorithm unit to the abnormal behavior recognition judgment algorithm unit are combined to obtain abnormal high and low of the same person), the situation of the acquired data of the graph is classified, the abnormal degree is obtained and classified into high risk, medium risk and low risk, the abnormal degree list of the abnormal personnel in the video segments is rapidly determined, and the practical evidence of the abnormal degree in important biological identification applied to intelligent sites such as banks is improved.
Drawings
FIG. 1 is a flow chart of a method of the face image acquisition system;
fig. 2 is a schematic diagram of the overall structure of the face image acquisition system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
It should be noted that, the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals related to the present disclosure are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of relevant data is required to comply with relevant laws and regulations and standards of relevant countries and regions.
Referring to fig. 1 to 2, the present embodiment provides a face image acquisition system, including: a face image acquisition system comprising: the system comprises a camera mounting and debugging unit, a field image acquisition unit, a video data processing unit, a calculation and analysis module, a warning unit, a video data storage planning module and a comprehensive power supply module;
The comprehensive power supply module is used for supplying electric energy to the camera installation and debugging unit and the video data storage planning module, shooting the situation inside the periphery of the bank through the cooperation of the camera installation and debugging unit and the on-site image acquisition unit, uploading data into the video data processing unit for calculation and analysis, and automatically uploading the data into the video data storage planning module for storage;
The video data in the video data processing unit is subjected to overall planning of information through the calculation and analysis module to calculate the abnormal state of personnel appearing on the bank site, and the corresponding alarm and warning are carried out through the warning unit;
The video data processing unit can retrieve the video data in the video data storage module, prune and split useless fragments in the video data through the calculation and analysis module, and conduct video export through the calculation and analysis module;
The video data storage planning module comprises: the video storage server is used for storing video monitoring data, and the cloud storage is used for improving remote backup.
In this embodiment, when an illegal person appears in the bank and the operation is illegal, the video data monitored in the time is retrieved based on the facial image acquisition system, and is identified and analyzed so as to analyze and collect biological and forensic medical data, the intelligent forensic identification time value adopts the means of artificial intelligence and modern informatization of big data, and biological evidence and the like are rapidly and accurately analyzed and identified by combining with forensic medical theoretical knowledge, so that the efficiency and quality of investigation and judgment are improved, and when the bank is subjected to the artificial illegal operation, people which are abnormal can be timely analyzed and judged by means of the system, so that the identification and detection efficiency and speed of the intelligent forensic are convenient.
Referring to fig. 1 to 2, the camera mounting and debugging unit includes:
The high-definition camera is used for capturing real-time images of the monitoring area; the network camera can perform remote monitoring of the bank; and uploading the video monitoring data to the cloud by the cloud camera for remote access by other equipment.
In this embodiment, the appearance that appears the control dead angle can be reduced under the cooperation of adoption multiunit camera and multiple camera to carry out convenient processing to biological evidence and forensic evidence in the video monitoring for the follow-up forensic, can realize that the control of bank scene, shooting and data upload and storage under the cooperation of multiple camera simultaneously.
Referring to fig. 1 to 2, the live image acquisition unit includes:
the device comprises a video monitoring unit, a video recording unit and a motion detection unit; the video monitoring unit is used for monitoring the internal and external areas of the bank; the video recording unit is used for recording and monitoring video and storing the video; the motion detection unit can identify and monitor abnormal behaviors of people appearing in the bank.
In this embodiment, the use of the on-site image acquisition unit can monitor, record and store the internal condition of the bank in real time, so that the suspicious person can be compared with the forensic face of the bank in the follow-up process, and the motion detection unit can automatically detect the motion in the video, so that the recognition capability of abnormal behaviors is improved, and the monitoring effect is improved.
Referring to fig. 1 to 2, the integrated power module includes:
The emergency power supply is an oversized capacitor, and the oversized capacitor is switched and regulated by the control center once emergency power failure occurs, so that emergency power supply is performed to electric appliances in the system.
In this embodiment, when external power supply abnormality makes external power supply interrupt, in order to guarantee the inside real-time monitoring demand of bank, emergent power supply is carried out through super-large electric capacity to avoid appearing because of the condition that the monitoring was missed appears in the external outage, avoid the unsafe condition that the human factor appears.
Referring to fig. 1 to 2, the warning unit includes:
the system comprises a display alarm assembly and a prompt alarm assembly, wherein the display alarm assembly is used for sending an abnormal signal to an administrator computer, and the prompt alarm assembly is used for sending an audible and visual alarm signal inside a bank.
In this embodiment, the warning unit can report to the police and warn the unusual artificial condition that appears in the scene of bank for the observer can be immediate observe unusual information.
Working principle: when the face image acquisition system is used, after illegal actions occur in a bank, the monitoring video in the time is called out and processed by the calculation and analysis module,
S1: firstly, dividing data shot by a plurality of cameras (S1, S2 … Sn) according to time periods (t 1, t2 … tn) (S1 t1, S1t2, S1tn … S2t1 … Sntn), and then calculating the data through a frame rate difference algorithm unit;
the frame difference algorithm unit is expressed as: the ZT algorithm can classify the conditions near the bank according to the difference among a plurality of frames in the video to obtain someone and no person, and the specific algorithm formula is as follows:
1. Splitting the processed video into a framing sequence: (Z1, Z2 … … Zn);
2. For each group of adjacent frames Zt and Z (t+1), calculating adjacent frame difference values ；
3. Motion detection is performed on the frame difference value Y to determine the motion area of the adjacent frameWherein (x, y) represents a pixel point in the moving image to determine a person appearing in the video;
4. for the detected motion area, the number of people is determined according to the characteristics of the size, the density and the like of the pixel points. For example, assume that each movement area corresponds to one person, or the number of persons is estimated based on the size of the area and the average size of the person;
5. For each frame, carrying out de-duplication processing on the detected number of people to ensure that each person is only counted once, and obtaining the number of the face after de-duplication ；
S2: after judging whether people appear in each piece of video data and the total number of people appearing, cutting the unmanned video data fragments in the part of data, and calculating and classifying the video fragments with people through an abnormal behavior recognition judgment algorithm unit to obtain abnormal or abnormal behaviors of the people in the video;
abnormal behavior recognition and judgment algorithm unit: the algorithm can carry out input judgment based on the behavior characteristics (moving speed, activity amplitude, time of stay and occurrence frequency of a person bank area in a frame difference algorithm unit) of the person in the video, and a specific algorithm formula is as follows:
1. Residence time of the same person in different time periods in frame rate difference algorithm unit ；
Wherein: (n) refers to the number of times a person appears in a video;
(ti+1) and (ti) are the time points of the i-th and i+1th occurrences, respectively;
2. Speed of movement of person ;
Wherein: (b 1, c 1) and (b 2, c 2) respectively represent the positions of persons between two frames;
U shows the time interval between two frames;
3. The activity amplitude e, which can be calculated by the area of a boundary box, is assumed that the motion trail of the person in a certain period of time can be represented by the boundary box;
Where h is the area of the bounding box;
4. Abnormal behavior judgment
Input: a moving speed v; a motion amplitude e; residence time T;
Setting a threshold value: a movement speed threshold va-vb, an activity amplitude ea-eb; residence time Ta-Tb;
If v, e and T are within the threshold values of va-vb, ea-eb and Ta-Tb, the abnormal behavior of the person is proved;
the method comprises the steps that according to the time of stay of a person in a bank area in a frame rate difference algorithm unit, the person needs to be combined with the time required by the person to process business at the bank, and the occurrence frequency needs to be combined with whether the person is currently processing business or not for comparison and analysis;
S3: splitting and storing information without abnormal data, calculating the information with abnormal data through an abnormal behavior degree judging algorithm unit, integrating the data of the frame difference algorithm unit and the data of the behavior abnormal behavior recognition judging algorithm unit by the abnormal behavior degree judging algorithm unit (comparing abnormal people existing from the frame difference algorithm unit to different time points of the behavior abnormal behavior recognition judging algorithm unit to obtain abnormal high and abnormal low of the same person), and classifying the situation of the acquired data of the graph to obtain abnormal degree and classifying the abnormal degree into high, medium and low, wherein the algorithm is expressed as Q, and a specific algorithm formula of the abnormal behavior degree judging algorithm unit is as follows:
Input: residence time T,
Number of occurrences of people in video、
；
Setting a threshold value: qa (0% -25%) is low risk; qa (25% -74%) is risk of stroke; qa (74% -100%) is high risk, so that abnormal people nearby a bank and the abnormal degree of the abnormal people can be obtained through the formula, abnormal video pictures of target abnormal people can be automatically called out through a frame rate difference algorithm unit, and information of suspicious people can be rapidly judged by matching with the comparison of a face recognition algorithm module and a database for observation.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The utility model provides a face image acquisition system which characterized in that: comprising the following steps: the system comprises a camera mounting and debugging unit, a field image acquisition unit, a video data processing unit, a calculation and analysis module, a warning unit, a video data storage planning module and a comprehensive power supply module;
The comprehensive power supply module is used for supplying electric energy to the camera installation and debugging unit and the video data storage planning module, shooting the conditions in the periphery of the bank under the cooperation of the camera installation and debugging unit and the on-site image acquisition unit, uploading the data to the video data processing unit for calculation and analysis, and automatically uploading the data to the video data storage planning module for storage;
The video data in the video data processing unit is subjected to overall planning of information through the calculation and analysis module to calculate abnormal states of personnel on the bank site, and the corresponding alarm and warning are carried out through the warning unit;
the calculation and analysis module comprises: the device comprises a frame difference algorithm unit, an abnormal behavior identification judgment algorithm unit and an abnormal behavior degree judgment algorithm unit.
2. The face image acquisition system of claim 1, wherein: the calculation and analysis module comprises a frame difference algorithm unit, an abnormal behavior identification judgment algorithm unit and an abnormal behavior degree judgment algorithm unit;
The frame rate difference algorithm unit is as follows:
The frame difference algorithm unit is expressed as ZT, classifies the conditions near the bank according to the difference among a plurality of frames in the video, and obtains the existence and the no-existence, wherein the specific algorithm formula is as follows:
Splitting the processed video into a framing sequence: (Z1, Z2 … … Zn);
For each group of adjacent frames Zt and Z (t+1), calculating adjacent frame difference values ；
Detecting the motion of the frame difference value Y to determine the number of people in the motion area of the adjacent frames；
Wherein (x, y) represents a pixel point in a moving image;
for each frame, carrying out de-duplication processing on the detected number of people to ensure that each person is only counted once, and obtaining the number of the face after de-duplication 。
3. The face image acquisition system of claim 2, wherein: the abnormal behavior recognition and judgment algorithm unit is as follows:
Residence time of the same person in different time periods in frame rate difference algorithm unit ；
Wherein (n) refers to the number of times a person appears in the video;
(ti+1) and (ti) are the time points of the i-th and i+1th occurrences, respectively;
Speed of movement of person ;
Wherein (b 1, c 1) and (b 2, c 2) represent the positions of the persons between the two frames, respectively;
U is the time interval between two frames;
Assuming that the motion trail of the person in a certain period of time is represented by a boundary box, the motion amplitude is calculated by the area of the boundary box;
Amplitude of movement Where h is the area of the bounding box;
abnormal behavior judgment: inputting a moving speed v, an activity amplitude e and a stay time T;
setting a threshold value: a movement speed threshold va-vb, an activity amplitude ea-eb and a dwell time Ta-Tb;
if v, e and T are within the threshold values of va-vb, ea-eb and Ta-Tb, then the person is evidenced to have abnormal behavior.
4. A face image acquisition system according to claim 3, wherein: the abnormal behavior degree judging algorithm unit is as follows:
；
t is the residence time T, and (n) is the number of times (n) that the person appears in the video;
Setting a threshold value: qa (0% -25%) is low risk, qa (25% -74%) is medium risk and Qa (74% -100%) is high risk, abnormal people near a bank and the abnormal degree of the abnormal people are obtained through the formula, an abnormal video picture of a target abnormal person is called out through a frame difference algorithm unit, and information of suspicious people is rapidly judged by matching with the comparison of a face recognition algorithm module and a database.
5. The face image acquisition system of claim 1, wherein: the camera installation and debugging unit adopts a high-definition camera, a network camera and a cloud camera, and the high-definition camera is used for capturing real-time images of a monitoring area;
the network camera is used for remotely monitoring the bank;
and the cloud camera uploads the video monitoring data to the cloud for remote access by other devices.
6. The face image acquisition system of claim 1, wherein: the on-site image acquisition unit includes: the device comprises a video monitoring unit, a video recording unit and a motion detection unit;
the video monitoring unit is used for monitoring the internal and external areas of the bank;
The video recording unit is used for recording and monitoring video and storing the video; the motion detection unit can identify and monitor abnormal behaviors of people appearing in the bank.
7. The face image acquisition system of claim 1, wherein: the comprehensive power supply module comprises an external power transmission unit and an emergency standby power supply, wherein the external power transmission unit is an external power transmission cable and is used for directly supplying power to electric equipment in the system through the external power transmission cable and is controlled by the control center.
8. The facial image acquisition system as recited in claim 4, wherein: the emergency standby power supply is an oversized capacitor, and when emergency power failure and outage occur, the oversized capacitor is switched and regulated by the control center to carry out emergency power supply on internal electric appliances of the system, the warning unit comprises a display warning component and a prompt warning component, the display warning component is used for sending abnormal signals to an administrator computer, and the prompt warning component is used for sending audible and visual warning signals inside a bank.
9. The face image acquisition system of claim 1, wherein: the video data storage planning module comprises a video storage server and a cloud storage, wherein the video storage server is used for storing video monitoring data, the cloud storage is used for improving remote backup, and the video data processing unit can retrieve video data in the video data storage module, delete and tear useless fragments in the video data through the calculation analysis module and conduct video export through the calculation analysis module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410460168.4A CN118072375B (en) | 2024-04-17 | Face image acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410460168.4A CN118072375B (en) | 2024-04-17 | Face image acquisition system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118072375A true CN118072375A (en) | 2024-05-24 |
| CN118072375B CN118072375B (en) | 2024-06-21 |
Family
ID=
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184409A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Machine-vision-based passenger flow statistics method and system |
| JP2012123676A (en) * | 2010-12-09 | 2012-06-28 | Canon Inc | Personal authentication device |
| KR20130068334A (en) * | 2011-12-15 | 2013-06-26 | 주식회사 버들소프트 | Automatic recognition and response system of the armed robbers and the methods of the same |
| CN106780009A (en) * | 2016-12-07 | 2017-05-31 | 云赛智联股份有限公司 | A kind of self-help bank's crime prevention system |
| CN111461041A (en) * | 2020-04-07 | 2020-07-28 | 西安交通大学 | Multi-factor joint abnormal pedestrian distinguishing method based on generation of countermeasure network |
| CN115131845A (en) * | 2021-03-26 | 2022-09-30 | 三六零视觉(北京)科技有限公司 | Portrait identification method and device, storage medium and electronic equipment |
| CN116129490A (en) * | 2022-12-13 | 2023-05-16 | 上海船舶工艺研究所(中国船舶集团有限公司第十一研究所) | Monitoring device and monitoring method for complex environment behavior recognition |
| CN116245865A (en) * | 2023-03-20 | 2023-06-09 | 鸿湖万联(江苏)科技发展有限公司 | Image quality detection method and device, electronic equipment and storage medium |
| CN116862740A (en) * | 2023-07-13 | 2023-10-10 | 辽宁警察学院 | Intelligent prison management and control system based on Internet |
| CN117409454A (en) * | 2023-08-25 | 2024-01-16 | 中国人民解放军空军军医大学 | Facial muscle movement monitoring-based emotion dynamic recognition method and device |
| CN117612107A (en) * | 2023-12-07 | 2024-02-27 | 上海亿虎网络科技有限公司 | Method for detecting abnormal personnel in place |
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012123676A (en) * | 2010-12-09 | 2012-06-28 | Canon Inc | Personal authentication device |
| CN102184409A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Machine-vision-based passenger flow statistics method and system |
| KR20130068334A (en) * | 2011-12-15 | 2013-06-26 | 주식회사 버들소프트 | Automatic recognition and response system of the armed robbers and the methods of the same |
| CN106780009A (en) * | 2016-12-07 | 2017-05-31 | 云赛智联股份有限公司 | A kind of self-help bank's crime prevention system |
| CN111461041A (en) * | 2020-04-07 | 2020-07-28 | 西安交通大学 | Multi-factor joint abnormal pedestrian distinguishing method based on generation of countermeasure network |
| CN115131845A (en) * | 2021-03-26 | 2022-09-30 | 三六零视觉(北京)科技有限公司 | Portrait identification method and device, storage medium and electronic equipment |
| CN116129490A (en) * | 2022-12-13 | 2023-05-16 | 上海船舶工艺研究所(中国船舶集团有限公司第十一研究所) | Monitoring device and monitoring method for complex environment behavior recognition |
| CN116245865A (en) * | 2023-03-20 | 2023-06-09 | 鸿湖万联(江苏)科技发展有限公司 | Image quality detection method and device, electronic equipment and storage medium |
| CN116862740A (en) * | 2023-07-13 | 2023-10-10 | 辽宁警察学院 | Intelligent prison management and control system based on Internet |
| CN117409454A (en) * | 2023-08-25 | 2024-01-16 | 中国人民解放军空军军医大学 | Facial muscle movement monitoring-based emotion dynamic recognition method and device |
| CN117612107A (en) * | 2023-12-07 | 2024-02-27 | 上海亿虎网络科技有限公司 | Method for detecting abnormal personnel in place |
Non-Patent Citations (1)
| Title |
|---|
| 方骞: "室内场景中人员的异常行为检测算法研究", CNKI优秀硕士学位论文全文库, 15 July 2023 (2023-07-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428522B (en) | Intelligent security system of wisdom new town | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| CN109711318B (en) | Multi-face detection and tracking method based on video stream | |
| CN110062208A (en) | A kind of security protection intelligence real-time analyzer and method | |
| CN110351536A (en) | A kind of substation abnormality detection system, method and device | |
| CN111540152A (en) | Intelligent security early warning system | |
| CN205354056U (en) | Law enforcement record appearance with face identification | |
| CN103049460A (en) | Video surveillance scene information classifying and storing method and search method | |
| CN109377697A (en) | Rapid Alarm method of disposal under a kind of intensive camera head environment | |
| US10657783B2 (en) | Video surveillance method based on object detection and system thereof | |
| CN110602453B (en) | Internet of things big data intelligent video security monitoring system | |
| CN112102574B (en) | Intelligent alarm system for security room | |
| CN111064928A (en) | Video monitoring system with face recognition function | |
| CN118072375B (en) | Face image acquisition system | |
| CN111462442A (en) | Intelligent visual detection system and method for cable tunnel | |
| CN107124577A (en) | A kind of real-time alarm system for guarding against theft based on moving object detection | |
| CN118072375A (en) | Face image acquisition system | |
| CN115641608A (en) | Intelligent identification equipment for personal protection articles for distribution network operation based on edge intelligence | |
| CN101853552A (en) | Omnibearing non-blind area moving object detection method | |
| Tung et al. | Camera tamper detection using codebook model for video surveillance | |
| CN114511987A (en) | Intelligent industrial information monitoring system based on cloud computing | |
| CN112804492A (en) | Communication prompting method and device for electronic cat eye | |
| CN111586355A (en) | Algorithm system for capturing portrait and analyzing behavior characteristics of portrait by high-definition camera | |
| KR20150031059A (en) | The Development Of CCTV For Security By Pattern Recognition Technology | |
| CN208386794U (en) | A kind of network video monitor and control system based on intellectual analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |