CN113992894A - Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection - Google Patents
Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection Download PDFInfo
- Publication number
- CN113992894A CN113992894A CN202111252809.XA CN202111252809A CN113992894A CN 113992894 A CN113992894 A CN 113992894A CN 202111252809 A CN202111252809 A CN 202111252809A CN 113992894 A CN113992894 A CN 113992894A
- Authority
- CN
- China
- Prior art keywords
- unit
- abnormal
- event identification
- module
- time sequence
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 17
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000003287 optical effect Effects 0.000 claims abstract description 8
- 239000012634 fragment Substances 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims 6
- 230000002123 temporal effect Effects 0.000 claims 6
- 230000000694 effects Effects 0.000 abstract description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005067 remediation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection, which comprises a visual coding module, a BSN module and an abnormal event identification module, wherein the visual coding module is used for carrying out fragment branching on images and videos, the BSN module is used for extracting branch fragment characteristics and listing the characteristics into a candidate evaluation unit, the abnormal event identification module is used for identifying abnormal events, and when the visual coding module receives input videos, image branching and optical flow branching are respectively carried out on single-frame images and multi-frame optical flows to obtain video fragment branches; the camera can be pulled in and tracked when the behavior is abnormal, the face and the situation of the shot abnormal behavior are clearer, the convenience and the accuracy of later tracking and judgment are improved, the use effect is better, the abnormal behavior data can be loaded with warning information and sent to a security layer or a management layer, the timeliness of security work is improved, and the practicability is higher.
Description
Technical Field
The invention relates to the field of video monitoring, in particular to an abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection.
Background
An abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection is a system for identifying abnormal events of monitoring videos, is mainly used for security video monitoring, and belongs to a back-defense system of security video monitoring.
The existing abnormal event recognition system based on monitoring video time sequence action positioning and abnormal detection has certain defects to be improved when in use, firstly, the existing abnormal event recognition system based on monitoring video time sequence action positioning and abnormal detection cannot record people or things of abnormal behaviors in detail when the abnormal behaviors occur, the phenomenon of fuzzy shooting can occur, and people or things of the abnormal behaviors are difficult to judge and track in the later period; secondly, when an abnormal behavior occurs, the conventional abnormal event identification system based on monitoring video time sequence action positioning and abnormality detection cannot timely notify a security layer or a management layer, so that the security layer or the management layer cannot receive the abnormal behavior information at the first time, the optimal remediation time is easily missed, and the practicability is poor.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the existing abnormal event recognition system based on monitoring video time sequence action positioning and abnormal detection cannot record people or things of abnormal behaviors in detail when the abnormal behaviors occur, so that the phenomenon of fuzzy shooting can occur, and the people or things of the abnormal behaviors are difficult to judge and track in the later period; secondly, when an abnormal behavior occurs, the conventional abnormal event identification system based on monitoring video time sequence action positioning and abnormality detection cannot timely notify a security layer or a management layer, so that the security layer or the management layer cannot receive the abnormal behavior information at the first time, the optimal remediation time is easily missed, and the practicability is poor.
The invention solves the technical problems through the following technical scheme, and the abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection comprises a visual coding module, a BSN module and an abnormal event identification module;
the visual coding module is used for carrying out fragment branching on the images and videos;
the BSN module is used for extracting branch segment characteristics and listing the characteristics into a candidate evaluation unit;
the abnormal event identification module is used for identifying an abnormal event.
Preferably, when the video coding module receives an input video, the video coding module performs image branching and optical flow branching on a single-frame image and a multi-frame optical flow respectively to obtain video segment branches.
Preferably, the BSN module specifically comprises the following processing steps:
step 1: when a video clip branch is received, extracting a characteristic sequence;
step 2: then, a time sequence evaluation unit carries out time sequence evaluation on the characteristic sequence, wherein the probability sequence comprises an action, an action start and an action end;
and step 3: the candidate generating unit generates candidate time sequence intervals at the beginning and the end of the action, and constructs BSP characteristics in the candidate time sequence intervals;
and 4, step 4: the BSP characteristics of the component enter a candidate evaluation unit to be evaluated.
Preferably, the specific processing steps of the abnormal event identification module are as follows:
the method comprises the following steps: the receiving unit receives the BSP characteristics to be evaluated and transmits the BSP characteristics to the evaluating unit;
step two: the calculation unit calculates the BSP characteristics in the evaluation unit by a permutation entropy algorithm;
step three: the calculation result is output by the output unit, and the recording module records the result.
Preferably, the permutation entropy algorithm comprises the following steps:
step (1): setting a one-dimensional time sequence: x ═ X (1), X (2), ·, X (n);
step (2): performing phase space reconstruction on any element X (i) in X by adopting a phase space reconstruction delay coordinate method,taking m continuous sampling points of each sampling point to obtain a reconstructed vector of an m-dimensional space of points x (i): xi＝{x(i),x(i+1),···,x(i+(m-1)*ι}；
And (3): the phase space matrix for sequence X is:
wherein m and l are the reconstruction dimension and the delay time, respectively;
and (4): and (3) carrying out ascending arrangement on the elements of the reconstructed vector Xi of x (i) to obtain: x'i＝{x(i+(j1-1)*ι)≤x(i+(j2-1)*ι)≤...≤x(i+(jm-1)' iota }, the arrangement obtained being:
and (5): it is a full array m! Counting the occurrence times of various arrangement conditions of the X sequence, and calculating the relative frequency of the occurrence of various arrangement conditions as the probability p1, p2, … pk, k<M! Calculating the permutation entropy after the sequence normalization:
preferably, the recording module in step three includes a determining unit, a wifi unit, an executing unit, a transmitting unit, and a storing unit:
s1: the judgment unit judges the output result, and when the judgment unit judges that abnormal literary texts exist, the wifi unit sends an execution command to the execution unit;
s2: the execution unit executes intelligent monitoring pull-in and tracking shooting work so as to record faces or events of abnormal behaviors;
s3: the recorded data is transmitted to the storage unit through the transmission unit to be stored.
Preferably, the recording module further comprises a communication unit, an editing unit, a warning unit, a sending unit and a repository, wherein the repository stores terminal numbers of a security layer and a management layer, after the storage unit receives the stored data, the editing unit edits the data, the sending unit sends the edited data to the terminal numbers stored in the repository, and meanwhile, the warning unit loads warning information.
Compared with the prior art, the invention has the following advantages:
the method can detect various video abnormal phenomena, such as the phenomenon that a camera is shifted or shielded, a video signal is interfered, a video signal is poor or no video signal exists, and the like, effectively solves the problem that the video of the front-end equipment is abnormal and cannot be found in time, and can greatly reduce the daily equipment maintenance workload of guard personnel;
the recording module can pull in and track the camera when the behavior is abnormal, so that the shot abnormal behavior face and state are clearer, the convenience and accuracy of later tracking and judgment are improved, and the using effect is better;
can carry warning information with unusual behavior data and send to security protection layer or management layer, improve the promptness of security protection work, the practicality is higher.
Drawings
FIG. 1 is a system block diagram of the present invention;
fig. 2 is a system diagram of a recording module of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
As shown in fig. 1-2, the present embodiment provides the following technical solutions: the abnormal event identification system based on the monitoring video time sequence action positioning and the abnormal detection comprises a visual coding module, a BSN module and an abnormal event identification module;
the visual coding module is used for carrying out fragment branching on the images and the videos;
the BSN module is used for extracting branch segment characteristics and listing the characteristics into a candidate evaluation unit;
the abnormal event identification module is used for identifying an abnormal event.
When the visual coding module receives an input video, image branching and optical flow branching are respectively carried out on a single-frame image and a multi-frame optical flow to obtain video segment branches.
The specific processing steps of the BSN module are as follows:
step 1: when a video clip branch is received, extracting a characteristic sequence;
step 2: then, a time sequence evaluation unit carries out time sequence evaluation on the characteristic sequence, wherein the probability sequence comprises an action, an action start and an action end;
and step 3: the candidate generating unit generates candidate time sequence intervals at the beginning and the end of the action, and constructs BSP characteristics in the candidate time sequence intervals;
and 4, step 4: the BSP characteristics of the component enter a candidate evaluation unit to be evaluated.
The abnormal event identification module specifically comprises the following processing steps:
the method comprises the following steps: the receiving unit receives the BSP characteristics to be evaluated and transmits the BSP characteristics to the evaluating unit;
step two: the calculation unit calculates the BSP characteristics in the evaluation unit by a permutation entropy algorithm;
step three: the calculation result is output by the output unit, and the recording module records the result.
The permutation entropy algorithm comprises the following calculation steps:
step (1): setting a one-dimensional time sequence: x ═ X (1), X (2), ·, X (n);
step (2): performing phase space reconstruction on any element X (i) in the X by adopting a phase space reconstruction delay coordinate method, and taking continuous m sample points of each sampling point to obtain a reconstruction vector of an m-dimensional space of the point X (i): xi＝{x(i),x(i+1),···,x(i+(m-1)*ι}；
And (3): the phase space matrix for sequence X is:
wherein m and l are the reconstruction dimension and the delay time, respectively;
and (4): and (3) carrying out ascending arrangement on the elements of the reconstructed vector Xi of x (i) to obtain: x'i＝{x(i+(j1-1)*ι)≤x(i+(j2-1)*ι)≤...≤x(i+(jm-1)' iota }, the arrangement obtained being:
and (5): it is a full array m! Counting the occurrence times of various arrangement conditions of the X sequence, and calculating the relative frequency of the occurrence of various arrangement conditions as the probability p1, p2, … pk, k<M! Calculating the permutation entropy after the sequence normalization:
the recording module in the third step comprises a judging unit, a wifi unit, an executing unit, a transmission unit and a storage unit:
s1: the judgment unit judges the output result, and when the judgment unit judges that abnormal literary texts exist, the wifi unit sends an execution command to the execution unit;
s2: the execution unit executes intelligent monitoring pull-in and tracking shooting work so as to record faces or events of abnormal behaviors;
s3: the recorded data is transmitted to the storage unit through the transmission unit to be stored.
The recording module further comprises a communication unit, an editing unit, a warning unit, a sending unit and a repository, wherein a security layer terminal number and a management layer terminal number are stored in the repository, after the storage unit receives the stored data, the editing unit edits the data, the sending unit sends the edited data to the terminal number stored in the repository, and meanwhile the warning unit carries warning information.
In summary, when the invention is used, when a video clip branch is received, a feature sequence is extracted, then a time sequence evaluation unit carries out time sequence evaluation on the feature sequence, wherein a probability sequence comprises an action, an action start and an action end, the action start and the action end are generated by a candidate generation unit to form a candidate time sequence interval, BSP features are constructed in the candidate time sequence interval, the BSP features of the components enter a candidate evaluation unit to be evaluated, the receiving unit receives the BSP features to be evaluated and transmits the BSP features to the evaluation unit, a calculation unit calculates the BSP features in the evaluation unit by an entropy permutation algorithm, the calculation result is output by an output unit, a recording module records the result, a judgment unit in the recording module judges the output result, when an abnormal text is judged, a wifi unit sends an execution command to an execution unit, and the execution unit executes intelligent monitoring pull-in, The shooting work is tracked, so that the face or the state of an abnormal behavior is recorded, the recorded data are transmitted to the storage unit through the transmission unit to be stored, and meanwhile, warning information is pushed to the security layer and the management layer.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (7)
1. The abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection is characterized by comprising a visual coding module, a BSN module and an abnormal event identification module;
the visual coding module is used for carrying out fragment branching on the images and videos;
the BSN module is used for extracting branch segment characteristics and listing the characteristics into a candidate evaluation unit;
the abnormal event identification module is used for identifying an abnormal event.
2. The system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 1, wherein: and when the visual coding module receives the input video, respectively carrying out image branching and optical flow branching on the single-frame image and the multi-frame optical flow to obtain video segment branches.
3. The system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 1, wherein: the specific processing steps of the BSN module are as follows:
step 1: when a video clip branch is received, extracting a characteristic sequence;
step 2: then, a time sequence evaluation unit carries out time sequence evaluation on the characteristic sequence, wherein the probability sequence comprises an action, an action start and an action end;
and step 3: the candidate generating unit generates candidate time sequence intervals at the beginning and the end of the action, and constructs BSP characteristics in the candidate time sequence intervals;
and 4, step 4: the BSP characteristics of the component enter a candidate evaluation unit to be evaluated.
4. The system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 1, wherein: the abnormal event identification module specifically comprises the following processing steps:
the method comprises the following steps: the receiving unit receives the BSP characteristics to be evaluated and transmits the BSP characteristics to the evaluating unit;
step two: the calculation unit calculates the BSP characteristics in the evaluation unit by a permutation entropy algorithm;
step three: the calculation result is output by the output unit, and the recording module records the result.
5. The system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 4, wherein: the permutation entropy algorithm comprises the following calculation steps:
step (1): setting a one-dimensional time sequence: x ═ X (1), X (2), ·, X (n);
step (2): performing phase space reconstruction on any element X (i) in the X by adopting a phase space reconstruction delay coordinate method, and taking continuous m sample points of each sampling point to obtain a reconstruction vector of an m-dimensional space of the point X (i): xi＝{x(i),x(i+1),···,x(i+(m-1)*ι}；
And (3): the phase space matrix for sequence X is:
wherein m and l are the reconstruction dimension and the delay time, respectively;
and (4): and (3) carrying out ascending arrangement on the elements of the reconstructed vector Xi of x (i) to obtain: x'i＝{x(i+(j1-1)*ι)≤x(i+(j2-1)*ι)≤...≤x(i+(jm-1)' iota }, the arrangement obtained being:
and (5): it is a full array m! Counting the occurrence times of various arrangement conditions of the X sequence, and calculating the relative frequency of the occurrence of various arrangement conditions as the probability p1, p2, … pk, k<M! Calculating the permutation entropy after the sequence normalization:
6. the system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 4, wherein: the recording module in the third step comprises a judging unit, a wifi unit, an executing unit, a transmission unit and a storage unit:
s1: the judgment unit judges the output result, and when the judgment unit judges that abnormal literary texts exist, the wifi unit sends an execution command to the execution unit;
s2: the execution unit executes intelligent monitoring pull-in and tracking shooting work so as to record faces or events of abnormal behaviors;
s3: the recorded data is transmitted to the storage unit through the transmission unit to be stored.
7. The system for anomaly event identification based on surveillance video temporal action localization and anomaly detection according to claim 6, wherein: the recording module further comprises a communication unit, an editing unit, a warning unit, a sending unit and a repository, wherein a security layer terminal number and a management layer terminal number are stored in the repository, after the storage unit receives the stored data, the editing unit edits the data, the sending unit sends the edited data to the terminal number stored in the repository, and meanwhile the warning unit carries warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252809.XA CN113992894A (en) | 2021-10-27 | 2021-10-27 | Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252809.XA CN113992894A (en) | 2021-10-27 | 2021-10-27 | Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113992894A true CN113992894A (en) | 2022-01-28 |
Family
ID=79742203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111252809.XA Pending CN113992894A (en) | 2021-10-27 | 2021-10-27 | Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113992894A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102970517A (en) * | 2012-11-28 | 2013-03-13 | 四川长虹电器股份有限公司 | Holder lens autonomous control method based on abnormal condition identification |
| JP2014044510A (en) * | 2012-08-24 | 2014-03-13 | Hitachi-Ge Nuclear Energy Ltd | Abnormality diagnostic device |
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
| CN109165634A (en) * | 2018-09-21 | 2019-01-08 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method, apparatus and system |
| CN110087099A (en) * | 2019-03-11 | 2019-08-02 | 北京大学 | A kind of monitoring method and system for protecting privacy |
| CN110532951A (en) * | 2019-08-30 | 2019-12-03 | 江苏航天大为科技股份有限公司 | A kind of Metro Passenger abnormal behaviour analysis method based on section displacement |
| CN110602526A (en) * | 2019-09-11 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Video processing method, video processing device, computer equipment and storage medium |
| CN111291699A (en) * | 2020-02-19 | 2020-06-16 | 山东大学 | Substation personnel behavior identification method based on monitoring video time sequence action positioning and abnormity detection |
| CN112132094A (en) * | 2020-09-30 | 2020-12-25 | 中国科学技术大学 | Continuous sign language recognition system based on multi-language collaboration |
| CN112800975A (en) * | 2021-01-29 | 2021-05-14 | 中国船舶重工集团公司第七一三研究所 | Behavior identification method in security check channel based on image processing |
| CN113093578A (en) * | 2021-04-09 | 2021-07-09 | 上海商汤智能科技有限公司 | Control method and device, electronic equipment and storage medium |
-
2021
- 2021-10-27 CN CN202111252809.XA patent/CN113992894A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014044510A (en) * | 2012-08-24 | 2014-03-13 | Hitachi-Ge Nuclear Energy Ltd | Abnormality diagnostic device |
| CN102970517A (en) * | 2012-11-28 | 2013-03-13 | 四川长虹电器股份有限公司 | Holder lens autonomous control method based on abnormal condition identification |
| CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| CN109165634A (en) * | 2018-09-21 | 2019-01-08 | 深圳市九洲电器有限公司 | A kind of intelligent identification Method, apparatus and system |
| CN110087099A (en) * | 2019-03-11 | 2019-08-02 | 北京大学 | A kind of monitoring method and system for protecting privacy |
| CN110532951A (en) * | 2019-08-30 | 2019-12-03 | 江苏航天大为科技股份有限公司 | A kind of Metro Passenger abnormal behaviour analysis method based on section displacement |
| CN110602526A (en) * | 2019-09-11 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Video processing method, video processing device, computer equipment and storage medium |
| CN111291699A (en) * | 2020-02-19 | 2020-06-16 | 山东大学 | Substation personnel behavior identification method based on monitoring video time sequence action positioning and abnormity detection |
| CN112132094A (en) * | 2020-09-30 | 2020-12-25 | 中国科学技术大学 | Continuous sign language recognition system based on multi-language collaboration |
| CN112800975A (en) * | 2021-01-29 | 2021-05-14 | 中国船舶重工集团公司第七一三研究所 | Behavior identification method in security check channel based on image processing |
| CN113093578A (en) * | 2021-04-09 | 2021-07-09 | 上海商汤智能科技有限公司 | Control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102752574B (en) | Video monitoring system and method | |
| CN100566408C (en) | Image processing equipment, image processing system and filter setting method | |
| CN108230637B (en) | Fire-fighting fire alarm method and system | |
| CN101281593A (en) | Method and system for researching intelligent video monitoring case | |
| CN111259720B (en) | Unsupervised pedestrian re-identification method based on self-supervision agent feature learning | |
| US20190042088A1 (en) | A method of data analysis and extraction for embedded security devices | |
| CN113347502B (en) | Video review method, video review device, electronic equipment and medium | |
| CN101299269A (en) | Method and device for calibration of static scene | |
| CN104252539A (en) | Intelligent video analysis and management method and system based on search engine | |
| CN110942027A (en) | Method and device for determining occlusion strategy, storage medium and electronic device | |
| CN109033192A (en) | A kind of video monitoring intelligent data acquisition processing method | |
| CN204926080U (en) | System for video can be retrieveed with target to discernment people's face or video recording of license plate target | |
| CN101674466B (en) | Multi-information fusion intelligent video monitoring fore-end system | |
| CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
| CN105681653A (en) | Video file generation method and device | |
| CN111064928A (en) | Video monitoring system with face recognition function | |
| CN210666820U (en) | Pedestrian abnormal behavior detection system based on DSP edge calculation | |
| CN113992894A (en) | Abnormal event identification system based on monitoring video time sequence action positioning and abnormal detection | |
| CN112291538A (en) | Video monitoring data storage method and device | |
| CN102708210A (en) | Method and system for checking key events from video data | |
| JP5548202B2 (en) | Optimization method of scene retrieval based on stream of images archived in video database | |
| KR101459103B1 (en) | Method for video monitoring using video surveillance system | |
| CN114550291A (en) | Gait feature extraction method, device and equipment | |
| Singla et al. | Detecting Criminal Activities From CCTV by using Object Detection and machine Learning Algorithms | |
| CN111027466A (en) | Intelligent detection method and device for use specification of bank outlet super cabinet |
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 |