CN112287815A - Intelligent security personnel deployment and control system and method for complex scene - Google Patents
Intelligent security personnel deployment and control system and method for complex scene Download PDFInfo
- Publication number
- CN112287815A CN112287815A CN202011170373.5A CN202011170373A CN112287815A CN 112287815 A CN112287815 A CN 112287815A CN 202011170373 A CN202011170373 A CN 202011170373A CN 112287815 A CN112287815 A CN 112287815A
- Authority
- CN
- China
- Prior art keywords
- feature
- person
- pedestrian
- similarity
- gait
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000005021 gait Effects 0.000 claims abstract description 45
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 15
- 238000011835 investigation Methods 0.000 abstract 2
- 238000012544 monitoring process Methods 0.000 description 11
- 230000009471 action Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 210000001930 leg bone Anatomy 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a complex scene-oriented intelligent security personnel arrangement and control method, which comprises the steps of conducting investigation on suspicious personnel in two modes, firstly conducting investigation on all field personnel using three technologies of face recognition, pedestrian re-recognition and gait recognition by setting a first threshold, conducting marking and tracking on personnel with any recognition result higher than the first threshold, combining the three recognition technologies through an analytic hierarchy process by adopting a weighting method, comparing the weighting similarity with a second threshold, and conducting marking and tracking on personnel higher than the second threshold.
Description
Technical Field
The application relates to the technical field of intelligent security and protection, in particular to a complex-scene-oriented intelligent security and protection personnel control system and method.
Background
The existing intelligent security scheme is mostly based on a video monitoring technology. Video monitoring technology has a long history and is an important technical means for assisting public security departments in fighting crimes and maintaining social stability. The traditional video monitoring system collects video images of a monitored area through a camera, mainly plays a role in recording, cannot find suspicious people in real time and forecast emergency without human intervention, and cannot play a role in early warning; therefore, the traditional video monitoring system needs to consume more manpower and material resources when being used, is very easily influenced by the external environment, and once extreme weather conditions or artificial damage occurs, the monitoring efficiency and quality of the traditional video monitoring system are greatly reduced.
Compared with the traditional video monitoring system, the intelligent video monitoring system uses the technologies of image processing, pattern recognition, computer vision and the like. By applying the technologies, real-time early warning of emergency can be realized, so that video monitoring is not limited by manpower and material resources. The existing intelligent security system mostly uses a face recognition technology to perform personnel control, human face features of personnel in a monitoring picture are extracted and compared with target object face features in a database, and after a target object in the picture is recognized, an alarm module is triggered and tracked.
The existing scheme has the defect that the target face image is difficult to acquire in a complex scene such as a station with large pedestrian flow, an airport and other public places. On one hand, due to the fact that the flow of people is large, the face information of pedestrians can be shielded and cannot be collected; on the other hand, the person actively shelters from the face information of the person, so that the face information of the person cannot be collected, and the difficulty and the accuracy of the person identity information confirmation in the monitoring area are improved.
Disclosure of Invention
The application aims to provide a complex-scene-oriented intelligent security personnel deployment and control method, and aims to at least solve one of the problems in the prior art. The application also provides a complex-scene-oriented intelligent security personnel deployment and control system, equipment and a computer-readable storage medium.
In order to achieve the above purpose, the present application provides the following technical solutions:
a smart security personnel deployment and control method for complex scenes comprises the following steps:
acquiring video stream data;
performing feature extraction according to the video stream data, wherein the features extracted by the feature extraction specifically comprise face features, pedestrian re-identification features and gait features of all people in the video stream data;
acquiring the face feature, the pedestrian re-identification feature and the gait feature of a target object;
respectively calculating to obtain the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data;
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, and if so, marking and tracking the first person;
if not, determining relevant weights of the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity of each person through an analytic hierarchy process and carrying out weighted calculation to obtain weighted similarity;
and judging whether a second person with the weighted similarity larger than a second threshold exists, and if so, carrying out mark tracking on the second person.
Further, the feature extraction according to the video stream data is completed by processing through a trained feature extractor.
Further, the above-mentioned obtaining of the face feature, the pedestrian re-recognition feature and the gait feature of the target object is to pre-store the target object in the feature information base by means of pre-building a feature information base for waiting information extraction.
Further, the above-mentioned analytic hierarchy process specifically includes the following,
establishing a hierarchical structure model; constructing a correlation matrix for judging the pair comparison; checking the hierarchical single ordering and the consistency thereof; and (5) checking the total sorting of the layers and the consistency thereof.
Further, the first threshold is specifically 0.7.
Further, the second threshold is specifically 0.6.
The invention also provides a complex-scene-oriented intelligent security personnel deployment and control system, which comprises:
the video acquisition module is arranged at a place to be monitored and used for acquiring video stream data;
the characteristic extraction module comprises a characteristic extraction module and a characteristic extraction module,
a face feature extraction module for extracting the face features of all the persons in the video stream data,
a pedestrian re-identification feature extraction module for extracting pedestrian re-identification features of all people in the video stream data,
the gait feature extraction module is used for extracting gait features of all people in the video stream data;
a characteristic comparison module for obtaining the face characteristic, the pedestrian re-identification characteristic and the gait characteristic of the target object,
respectively calculating the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data,
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, if so, marking and tracking the first person,
if not, determining the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity of each person by an analytic hierarchy process to obtain a relevant weight and performing weighted calculation to obtain a weighted similarity,
judging whether a second person with the weighted similarity larger than a second threshold exists or not, and if so, carrying out mark tracking on the second person;
and the characteristic information base is used for storing the face characteristic, the pedestrian re-identification characteristic and the gait characteristic of the target object.
Further, the system also comprises a control unit,
a suspicious personnel tracking library for storing and recording the first personnel and the second personnel,
a tracking module associated with the suspect tracking library for tracking the first person and the second person;
and the automatic alarm module is associated with the tracking module and is used for carrying out automatic alarm according to the tracking information of the tracking module.
The invention also provides a complex-scene-oriented intelligent security personnel deployment and control device, which comprises:
a memory for storing a computer program;
a processor for implementing the steps of the method for deploying and controlling smart security personnel facing complex scenes according to any one of claims 1 to 6 when the computer program is executed.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the steps of a method for intelligent security personnel deployment and control oriented to complex scenarios as claimed in any one of claims 1 to 6.
Has the advantages that:
according to the intelligent security personnel arrangement and control method for the complex scene, suspicious personnel are investigated in two modes, firstly, all field personnel using three technologies of face recognition, pedestrian re-recognition and gait recognition are investigated by setting a first threshold, personnel with any recognition result higher than the first threshold are marked and tracked, the three recognition technologies are combined through an analytic hierarchy process by adopting a weighting method, the weighting similarity is compared with a second threshold, and personnel higher than the second threshold are marked and tracked.
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 introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a complex-scene-oriented intelligent security personnel deployment and control method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a complex-scene-oriented intelligent security personnel deployment and control system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a complex-scene-oriented intelligent security personnel deployment and control device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described 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, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a complex-scene-oriented intelligent security personnel deployment and control method according to an embodiment of the present application.
The intelligent security personnel deployment and control method for the complex scene comprises the following steps:
acquiring video stream data;
performing feature extraction according to the video stream data, wherein the features extracted by the feature extraction specifically comprise face features, pedestrian re-identification features and gait features of all people in the video stream data;
acquiring the face feature, the pedestrian re-identification feature and the gait feature of a target object;
respectively calculating to obtain the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data;
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, and if so, marking and tracking the first person;
if not, determining relevant weights of the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity of each person through an analytic hierarchy process and carrying out weighted calculation to obtain weighted similarity;
judging whether a second person with the weighted similarity larger than a second threshold exists, and if so, performing mark tracking on the second person.
In the embodiment 1, suspicious people are checked in two ways, firstly, all field personnel using three technologies of face recognition, pedestrian re-recognition and gait recognition are checked by setting a first threshold, any person with a recognition result higher than the first threshold is marked and tracked, the three recognition technologies are combined by an analytic hierarchy process by adopting a weighting method, the weighted similarity is compared with a second threshold, and the person higher than the second threshold is marked and tracked.
Face recognition relies mainly on extracting static features of the face. The pedestrian re-identification is based on the overall posture of the pedestrian for retrieval, mainly extracts static external features such as wearing, backpack, hairstyle, umbrella and the like, and identifies the pedestrian by analyzing the wearing and posture of the pedestrian. The gait recognition and extraction feature points comprise two aspects, on one hand, static internal features such as height, head shape, leg bones, joints, muscles and other physiological structures are extracted; in the second aspect, dynamic characteristics of the human body, such as walking posture, arm swing, head and shoulder shaking, motor nerve sensitivity and the like, are extracted. In ensemble learning, a plurality of basis learners are generally combined, and if the differences between the basis learners are large and have diversity, the combination of the basis learners can reduce the variance of the final prediction result.
In a preferred embodiment of the present invention, the feature extraction from the video stream data is performed by a trained feature extractor.
In a preferred embodiment of the present invention, the above-mentioned obtaining of the face feature, the pedestrian re-recognition feature and the gait feature of the target object is implemented by constructing a feature information base in advance, and storing the target object in the feature information base in advance to wait for information extraction.
As a preferred embodiment of the present invention, the above-mentioned analytic hierarchy process specifically includes the following,
analytic hierarchy process, AHP for short, refers to a decision-making method that decomposes elements always related to decision-making into levels such as targets, criteria, schemes, etc., and performs qualitative and quantitative analysis on the basis. The method is a hierarchical weight decision analysis method which is provided by the university of Pittsburgh, a university of American operational research, in the early 70 th century of the 20 th century and by applying a network system theory and a multi-target comprehensive evaluation method when researching the subject of 'power distribution according to the contribution of each industrial department to national welfare' for the United states department of defense. The analytic hierarchy process decomposes the problem into different composition factors according to the nature of the problem and the total target to be achieved, and combines the factors according to the mutual correlation influence and membership relation among the factors in different levels to form a multi-level analytic structure model, thereby finally leading the problem to be summarized into the determination of the relative important weight of the lowest level (scheme, measure and the like for decision making) relative to the highest level (total target) or the scheduling of the relative order of superiority and inferiority. The weight calculation steps of the analytic hierarchy process are as follows: 1. establishing a hierarchical structure model; 2. constructing a judgment (pair comparison) matrix; 3. checking the hierarchical single ordering and the consistency thereof; 4. and (5) checking the total sorting of the layers and the consistency thereof. Considering that most pedestrian re-identification features are external features (such as wearing, backpack, hairstyle, umbrella and the like) which are easy to change, the pedestrian re-identification features in the analytic hierarchy process are set to be relatively unimportant, and the weighted feature similarity is calculated according to the features.
In a preferred embodiment of the present invention, the first threshold is specifically 0.7. A threshold needs to be preset before similarity calculation, and the threshold affects the false recognition rate and the passing rate, wherein the false recognition rate refers to the probability of false recognition and is also called the false recognition rate; the pass rate refers to the probability of passing through for correct recognition. The higher the threshold value is, the lower the passing rate and the false recognition rate are, the lower the threshold value is, and the higher the passing rate and the false recognition rate are. In the application scenario of this patent, in order to identify the suspicious person as much as possible, a threshold value relatively lower than the general identification threshold value needs to be set. After practice demonstration analysis, the scheme sets the threshold value, namely the first threshold value, to be 0.7
In a preferred embodiment of the present invention, the second threshold is specifically 0.6. Similar to the setting of the first threshold, the single feature similarity of a certain person on site in the first stage exceeds the threshold of 0.7, which indicates that the person has a high possibility of being a target object; if the similarity of three characteristics of a certain field person is slightly lower than 0.7, the field person is not judged as a suspicious person in the first stage, in order to be identified by the persons, the threshold value in the second stage is set to be slightly lower than that in the first stage and is 0.6, after the three similarities are synthesized, if the weighted similarity exceeds 0.6, the field person is proved to be a target object in the characteristic information base, and the target object is added to the suspicious person tracking base.
Referring to fig. 2, in embodiment 2, the present invention further provides a complex-scene-oriented intelligent security personnel deployment and control system, including:
the video acquisition module 110 is arranged at a place to be monitored and used for acquiring video stream data;
the characteristic extraction module comprises a characteristic extraction module and a characteristic extraction module,
a face feature extraction module 121, configured to extract face features of all people in the video stream data,
a pedestrian re-identification feature extraction module 122, configured to extract pedestrian re-identification features of all people in the video stream data,
a gait feature extraction module 123, configured to extract gait features of all people in the video stream data;
a feature comparison module 130 for obtaining the face feature, the pedestrian re-identification feature and the gait feature of the target object,
respectively calculating the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data,
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, if so, marking and tracking the first person,
if not, determining the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity of each person by an analytic hierarchy process to obtain a relevant weight and performing weighted calculation to obtain a weighted similarity,
judging whether a second person with the weighted similarity larger than a second threshold exists or not, and if so, carrying out mark tracking on the second person;
the feature information base 140 is used for storing the face features, the pedestrian re-recognition features and the gait features of the target object.
In this embodiment 2, the suspicious persons are checked in two ways, that is, all the field persons using the three technologies of face recognition, pedestrian re-recognition and gait recognition are checked by setting a first threshold, any person with a recognition result higher than the first threshold is labeled and tracked, the three recognition technologies are combined by an analytic hierarchy process by adopting a weighting method, the weighted similarity is compared with a second threshold, and the person higher than the second threshold is labeled and tracked.
As a preferred embodiment of the present invention, the system further comprises,
a suspicious person tracking repository 150 for storing records of the first person and the second person,
a tracking module 160 associated with the suspect tracking library for tracking the first person and the second person;
and an automatic alarm module 170, associated with the tracking module, for automatically alarming according to the tracking information of the tracking module 160.
Through increasing above module, can make things convenient for this scheme to carry out can personnel's mark and track to can play a warning to the relevant staff and supervise the effect of handling.
Referring to fig. 3, in embodiment 3, the present invention further provides a complex-scene-oriented intelligent security personnel deployment and control device, including:
a memory 201 for storing a computer program;
a processor 202, configured to implement the steps of the method for deploying and controlling smart security personnel facing complex scenes according to any one of claims 1 to 6 when executing the computer program.
In this embodiment 3, by applying the above method, suspicious people can be checked in two ways, first, all field people who use three technologies of face recognition, pedestrian re-recognition and gait recognition are checked by setting a first threshold, people with any recognition result higher than the first threshold are marked and tracked, the three recognition technologies are combined by an analytic hierarchy process by using a weighting method, and the weighted similarity is compared with a second threshold, and people higher than the second threshold are marked and tracked.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the steps of a method for intelligent security personnel deployment and control oriented to complex scenarios as claimed in any one of claims 1 to 6.
The computer-readable storage media to which this application relates include Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage media known in the art.
For a description of a relevant part of the complex-scene-oriented intelligent security personnel deployment and control system, the complex-scene-oriented intelligent security personnel deployment and control equipment, and the computer-readable storage medium, please refer to a detailed description of a corresponding part of the complex-scene-oriented intelligent security personnel deployment and control method provided in the embodiments of the present application, and are not repeated herein. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A complex-scene-oriented intelligent security personnel deployment and control method is characterized by comprising the following steps:
acquiring video stream data;
performing feature extraction according to the video stream data, wherein the features extracted by the feature extraction specifically comprise face features, pedestrian re-identification features and gait features of all people in the video stream data;
acquiring the face feature, the pedestrian re-identification feature and the gait feature of a target object;
respectively calculating to obtain the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data;
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, and if so, marking and tracking the first person;
if not, determining relevant weights of the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity of each person through an analytic hierarchy process and carrying out weighted calculation to obtain weighted similarity;
and judging whether a second person with the weighted similarity larger than a second threshold exists, and if so, carrying out mark tracking on the second person.
2. The method as claimed in claim 1, wherein the feature extraction based on the video stream data is performed by a trained feature extractor.
3. The method as claimed in claim 1, wherein the face feature, the pedestrian re-identification feature and the gait feature of the target object are obtained by pre-building a feature information base, and the target object is pre-stored in the feature information base for waiting information extraction.
4. The method as claimed in claim 1, wherein the analytic hierarchy process comprises the following steps,
establishing a hierarchical structure model; constructing a correlation matrix for judging the pair comparison; checking the hierarchical single ordering and the consistency thereof; and (5) checking the total sorting of the layers and the consistency thereof.
5. The method as claimed in claim 1, wherein the first threshold is 0.7.
6. The method as claimed in claim 1, wherein the second threshold is 0.6.
7. The utility model provides a towards intelligent security personnel cloth accuse system of complicated scene which characterized in that includes:
the video acquisition module is arranged at a place to be monitored and used for acquiring video stream data;
the characteristic extraction module comprises a characteristic extraction module and a characteristic extraction module,
a face feature extraction module for extracting the face features of all the persons in the video stream data,
a pedestrian re-identification feature extraction module for extracting pedestrian re-identification features of all people in the video stream data,
the gait feature extraction module is used for extracting gait features of all people in the video stream data;
a characteristic comparison module for obtaining the face characteristic, the pedestrian re-identification characteristic and the gait characteristic of the target object,
respectively calculating the face feature similarity, the pedestrian re-recognition feature similarity and the gait feature similarity between each person and the target object in the video stream data,
judging whether a first person with any one of the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity larger than a first threshold exists, if so, marking and tracking the first person,
if not, determining the face feature similarity, the pedestrian re-identification feature similarity and the gait feature similarity of each person by an analytic hierarchy process to obtain a relevant weight and performing weighted calculation to obtain a weighted similarity,
judging whether a second person with the weighted similarity larger than a second threshold exists or not, and if so, carrying out mark tracking on the second person;
and the characteristic information base is used for storing the face characteristic, the pedestrian re-identification characteristic and the gait characteristic of the target object.
8. The intelligent security personnel deployment and control system for complex scenes of claim 7, further comprising,
a suspicious personnel tracking library for storing and recording the first personnel and the second personnel,
a tracking module associated with the suspect tracking library for tracking the first person and the second person;
and the automatic alarm module is associated with the tracking module and is used for carrying out automatic alarm according to the tracking information of the tracking module.
9. The utility model provides a towards intelligent security personnel cloth accuse equipment in complicated scene which characterized in that includes:
a memory for storing a computer program;
a processor for implementing the steps of the method for deploying and controlling smart security personnel facing complex scenes according to any one of claims 1 to 6 when the computer program is executed.
10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when being executed by a processor, the computer program implements the steps of the method for deploying and controlling smart security personnel facing to complex scenarios according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011170373.5A CN112287815A (en) | 2020-10-28 | 2020-10-28 | Intelligent security personnel deployment and control system and method for complex scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011170373.5A CN112287815A (en) | 2020-10-28 | 2020-10-28 | Intelligent security personnel deployment and control system and method for complex scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287815A true CN112287815A (en) | 2021-01-29 |
Family
ID=74372627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011170373.5A Pending CN112287815A (en) | 2020-10-28 | 2020-10-28 | Intelligent security personnel deployment and control system and method for complex scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287815A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269091A (en) * | 2021-05-26 | 2021-08-17 | 广州瀚信通信科技股份有限公司 | Personnel trajectory analysis method, equipment and medium for intelligent park |
| CN118135462A (en) * | 2024-03-29 | 2024-06-04 | 北京积加科技有限公司 | Stranger intrusion detection method and device based on face and gait recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150042674A (en) * | 2013-10-10 | 2015-04-21 | 재단법인대구경북과학기술원 | Multimodal user recognition robust to environment variation |
| CN109583278A (en) * | 2017-09-29 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | Method, apparatus, system and the computer equipment of recognition of face alarm |
| CN110188691A (en) * | 2019-05-30 | 2019-08-30 | 银河水滴科技（北京）有限公司 | A kind of motion track determines method and device |
| CN110287890A (en) * | 2019-06-26 | 2019-09-27 | 银河水滴科技（北京）有限公司 | A kind of recognition methods and device based on gait feature and pedestrian's weight identification feature |
| CN110852219A (en) * | 2019-10-30 | 2020-02-28 | 广州海格星航信息科技有限公司 | Multi-pedestrian cross-camera online tracking system |
-
2020
- 2020-10-28 CN CN202011170373.5A patent/CN112287815A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150042674A (en) * | 2013-10-10 | 2015-04-21 | 재단법인대구경북과학기술원 | Multimodal user recognition robust to environment variation |
| CN109583278A (en) * | 2017-09-29 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | Method, apparatus, system and the computer equipment of recognition of face alarm |
| CN110188691A (en) * | 2019-05-30 | 2019-08-30 | 银河水滴科技（北京）有限公司 | A kind of motion track determines method and device |
| CN110287890A (en) * | 2019-06-26 | 2019-09-27 | 银河水滴科技（北京）有限公司 | A kind of recognition methods and device based on gait feature and pedestrian's weight identification feature |
| CN110852219A (en) * | 2019-10-30 | 2020-02-28 | 广州海格星航信息科技有限公司 | Multi-pedestrian cross-camera online tracking system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269091A (en) * | 2021-05-26 | 2021-08-17 | 广州瀚信通信科技股份有限公司 | Personnel trajectory analysis method, equipment and medium for intelligent park |
| CN118135462A (en) * | 2024-03-29 | 2024-06-04 | 北京积加科技有限公司 | Stranger intrusion detection method and device based on face and gait recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Salimi et al. | Visual-based trash detection and classification system for smart trash bin robot | |
| CN109271554B (en) | Intelligent video identification system and application thereof | |
| CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
| CN110414441B (en) | Pedestrian track analysis method and system | |
| CN108009482A (en) | One kind improves recognition of face efficiency method | |
| CN105631430A (en) | Matching method and apparatus for face image | |
| CN108898093A (en) | A kind of face identification method and the electronic health record login system using this method | |
| CN105389562A (en) | Secondary optimization method for monitoring video pedestrian re-identification result based on space-time constraint | |
| CN111127830A (en) | Alarm method, alarm system and readable storage medium based on monitoring equipment | |
| CN106169071A (en) | A kind of Work attendance method based on dynamic human face and chest card recognition and system | |
| CN110728252B (en) | Face detection method applied to regional personnel motion trail monitoring | |
| CN107230267A (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| CN113743256A (en) | Construction site safety intelligent early warning method and device | |
| CN111325133B (en) | Image processing system based on artificial intelligent recognition | |
| CN108960047A (en) | Face De-weight method in video monitoring based on the secondary tree of depth | |
| CN112287815A (en) | Intelligent security personnel deployment and control system and method for complex scene | |
| CN110415152A (en) | A kind of safety monitoring system | |
| CN111091025A (en) | Image processing method, device and equipment | |
| Vashistha et al. | An architecture to identify violence in video surveillance system using ViF and LBP | |
| CN116189052A (en) | Security method, system, intelligent terminal and storage medium based on video stream analysis | |
| CN114581990A (en) | Intelligent running test method and device | |
| CN113869127A (en) | Human behavior detection method, monitoring device, electronic device, and medium | |
| Arisandi et al. | Human Detection and Identification for Home Monitoring System | |
| CN112330742A (en) | Method and device for recording activity routes of key personnel in public area |
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 |