CN112287760A - Behavior monitoring-based airport figure risk quantification method - Google Patents
Behavior monitoring-based airport figure risk quantification method Download PDFInfo
- Publication number
- CN112287760A CN112287760A CN202011027803.8A CN202011027803A CN112287760A CN 112287760 A CN112287760 A CN 112287760A CN 202011027803 A CN202011027803 A CN 202011027803A CN 112287760 A CN112287760 A CN 112287760A
- Authority
- CN
- China
- Prior art keywords
- risk
- behavior
- module
- image
- dangerous
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000011002 quantification Methods 0.000 title claims abstract description 14
- 230000006399 behavior Effects 0.000 claims abstract description 71
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 241000282414 Homo sapiens Species 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims abstract description 6
- 238000009432 framing Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 210000000887 face Anatomy 0.000 claims description 2
- 238000007689 inspection Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an airport figure risk quantification method based on behavior monitoring, wherein an airport figure risk quantification system based on behavior monitoring comprises an image acquisition module, an image identification module, a risk detection module and a data display module which are sequentially connected, wherein the image acquisition module comprises a high-definition camera and is used for acquiring video images of a designated area frame by frame; the image recognition module detects human bodies in the continuous frame images and recognizes the behavior danger points of the detected people; the danger detection module detects danger values and change conditions of character behaviors in continuous frame images based on the fact that the target detection frame is matched with the set threshold value to judge whether the characters in the video are dangerous or not; the data display module displays whether dangerous people exist in the video image area through the display and gives corresponding alarm prompts.
Description
Technical Field
The invention belongs to the technical field of action detection, and relates to an airport figure risk quantification method based on behavior monitoring.
Background
The places where people gather and circulate are beneficial to hiding and hiding dangerous people, so that security inspection is usually required, especially airports and stations gathering people all over the country and even people outside the sea. Conventional security inspection can only detect whether a passenger crimes, carries prohibited articles and the like, so that a small number of dangerous people with good camouflage can be caused to become 'missed fish'. The hazards posed by airport personnel once mixed in can be immeasurable and therefore require more rigorous security strategies to protect passengers and crew personal and property safety. Currently, researchers still have a blank field for the application of character risk quantification based on behavior monitoring to places such as airports, stations and the like. The development trend of the proposed security inspection technology is summarized by the invention, and the existing security inspection systems are divided into four main categories: a check-in system before passenger boarding, a non-passenger screening system, a baggage check-in system in a cabin and an identity card system in a restricted area.
1. Check-up system before passenger boarding
The basic functions of the current inspection system before boarding of passengers include: passenger flight basic information (flight number, seat number, destination, etc.), passenger valid identification document information (name, document number, etc.), passenger characteristics (passenger static face image), passenger attributes (normal, delayed, rechecked, checked, etc.). Since the detection object is static, there is a limit that the danger coefficient of the passenger cannot be well identified, and thus some disguised dangerous persons may be boarding.
2. Non-passenger screening system
Current non-passenger screening systems include basic functions: the flight information of passengers is read through the certificate scanning equipment, non-passenger personnel can be rapidly and accurately identified, and the screening efficiency of dangerous figures is greatly improved.
3. In-cabin baggage inspection system
Current in-cabin baggage inspection systems include the basic functions of: the X-ray machine is used to output the image of the inspected object, and the radiographic image can record the creation time (in seconds) of the baggage image, the size of the baggage, the weight of the baggage, and the like. The method can classify the checked prohibited articles and the checked articles in the luggage of the passenger, record the processing mode and check the post information.
4. Forbidden zone identity card system
The basic functions of the prior airport restricted area identity card system comprise: the equipment performs witness matching verification and passing authority verification and machine-reads the unmanned situation loophole. And performing sound-light early warning by auditing and checking, performing electronic management on the files, and checking in various machine-reading modes to ensure human-certificate matching and facilitate implementation according to local conditions. .
Disclosure of Invention
In order to solve the problems, the invention provides a behavior monitoring-based person risk quantification strategy, which can be applied to the field of security inspection of crowd gathering places such as airports and stations, and particularly relates to a method for distinguishing and judging dangerous persons with strong disguise, so that the accuracy of security detection is improved, real-time capture detection by a camera is adopted, the application scene of the detection technology is expanded, and the technology can be better suitable for real-time security detection of crowded places such as airports.
In order to achieve the purpose, the technical scheme of the invention is an airport figure risk quantification method based on behavior monitoring, the airport figure risk quantification system based on behavior monitoring comprises an image acquisition module, an image identification module, a risk detection module and a data display module which are sequentially connected, wherein the image acquisition module comprises a high-definition camera and is used for acquiring video images of a designated area frame by frame; the image recognition module detects human bodies in the continuous frame images and recognizes the behavior danger points of the detected people; the danger detection module detects danger values and change conditions of character behaviors in continuous frame images based on the fact that the target detection frame is matched with the set threshold value to judge whether the characters in the video are dangerous or not; the data display module displays whether dangerous persons exist in the video image area through the display and gives corresponding alarm prompts, and the method adopting the system comprises the following steps:
s10, acquiring images in the corresponding areas by using the cameras;
s20, carrying out human body identification framing;
s30, identifying and calculating behavior danger points;
and S40, sending out warning information to the situation of the dangerous person through the data display module.
Preferably, the framing for human body recognition includes the following steps:
s21, processing the video image by using the R-CNN algorithm, detecting the human in the image and framing by using a detection frame;
s22, calculating the character behaviors and the risk index lambda, scoring the character behaviors, recording 10 scores when any behavior in a preset risk behavior library is met, superposing multiple behavior scores, and if the behavior meets the lambda>λ1Then, the person is judged to be dangerous.
Preferably, the threshold λ1＝50。
Preferably, the performing behavior risk point identification and calculation includes the following steps:
s31, processing the human body image by using a MASK-RCNN algorithm, extracting a plurality of behavior danger points of the human body, and marking in sequence;
s32, a risk point is calculated, and it is determined whether there is a risk by setting the risk point to the risk index/10.
Preferably, the behavioral risk points include eyes, faces, hands, crotch, and feet.
Preferably, the data display module sends out warning information to the situation of the dangerous person, displays the position of the dangerous person in real time on a display screen, displays the warning information, and sends out sound alarm.
The invention provides an airport figure risk quantification technology based on behavior monitoring, which can effectively distinguish and judge various false falling actions and real falling actions, improves the falling detection accuracy, adopts real-time capture detection of a camera, enlarges the application scene of the detection technology, and can be better suitable for the falling action real-time detection of a building site.
The method has the following specific beneficial effects:
1. the invention relates to a strategy for quantifying the risk of a person based on behavior monitoring, which is characterized in that a camera is arranged on a specified occasion for shooting, and the behavior change of the person in continuous frames and the angle and position change of key points of human bones are detected, so that whether the person has the risk or not is comprehensively judged. The detection has good real-time performance and accuracy, and can be used for detecting a plurality of people in a picture at the same time.
2. The behavior monitoring-based person risk quantification strategy has the advantages of high detection speed, small detection error and capability of finding potential dangerous behaviors; no special requirements on human beings and environment are required in the detection process; the cost is low, and detection personnel do not need to use other equipment except a camera, a display, a host and related alarm equipment; traceability is realized, and pictures captured by the camera can be stored, so that subsequent playback and checking are facilitated; the application scene is extensive, is not restricted to the action control in airport, is applicable to occasions such as high-speed railway station, subway station, market equally.
Drawings
FIG. 1 is a flowchart illustrating the steps of a method for quantifying the risk of an airport character based on behavior monitoring according to an embodiment of the present invention;
fig. 2 is a flowchart of a risk determining step of the airport character risk quantifying method based on behavior monitoring according to the embodiment of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
On the contrary, the invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details.
The invention is first defined and explained below:
a target detection frame: detecting and identifying an appointed object in the image through a target detection model, and marking the object by using a rectangular frame, wherein the rectangular frame is a target detection frame;
behavior risk points: some key behaviors of a human body, such as surrounding without continuous observation and face shielding, are marked as key points, the behavior risk of the character can be effectively described by detecting the behavior risk points, and great help is provided for predicting whether the character can make dangerous behaviors.
Referring to fig. 1, which is a flow chart illustrating steps of a method for quantifying the risk of an airport figure based on behavior monitoring according to an embodiment of the present invention, the system for quantifying the risk of an airport figure based on behavior monitoring includes an image acquisition module, an image recognition module, a risk detection module and a data display module, which are sequentially connected, wherein the image acquisition module includes a high-definition camera to acquire video images of an appointed area frame by frame; the image recognition module detects human bodies in the continuous frame images and recognizes the behavior danger points of the detected people; the danger detection module detects danger values and change conditions of character behaviors in continuous frame images based on the fact that the target detection frame is matched with the set threshold value to judge whether the characters in the video are dangerous or not; the data display module displays whether dangerous persons exist in the video image area through the display and gives corresponding alarm prompts, and the method adopting the system comprises the following steps:
s10, acquiring images in the corresponding areas by using the cameras;
s20, carrying out human body identification framing;
s30, identifying and calculating behavior danger points;
and S40, sending out warning information to the situation of the dangerous person through the data display module.
Referring to fig. 2, judging whether there is a risk includes the steps of:
s21, processing the video image by using the R-CNN algorithm, detecting the human in the image and framing by using a detection frame;
s22, calculating the character behaviors and the risk index lambda, scoring the character behaviors, recording 10 scores when any behavior in a preset risk behavior library is met, superposing multiple behavior scores, and if the behavior meets the lambda>λ1Then, the person is judged to be dangerous.
The dangerous behavior library comprises the following behaviors or characteristics:
keeping beard more than 10cm for male, covering the face of female, and wearing black gown;
talking utterances and behavioral behavior are extremely inclined;
a plurality of people in the temporary accommodation place gather and move, the shape and the trace are suspicious, beds and pavements for a plurality of people to stay are arranged in the house, and the ages of the people are similar to the ages of the people in the house;
unwilling to provide personal identity documents, falsely using other personal identity documents or accidentally discarding and destroying the identity documents;
temporarily storing (storing) articles such as physical ability, fighting training equipment and the like;
the person moves to key and sensitive parts such as a political core area and a person intensive place for many times, and is suspected to be stepped on;
holding a family together, and finding that the fixed assets are sold and the door is closed abnormally;
utilize various opportunities to practise martial arts or engage in fitness activities;
purchasing or using a mobile phone 'black card' to communicate or surf the internet;
purchasing or driving a second hand vehicle;
the mobile phone has a plurality of mobile phones, a plurality of telephone cards or telephone cards and internet access cards which are used alternately;
the Zhongyunnan red river, the science of the Eden;
move to the interior once and have a plurality of movement tracks in the interior;
there are a large or small number of financial transactions;
other criminal president or criminal release religions besides terrorist activities;
with a set threshold lambda1Comparing if λ is satisfied>λ1Then, the person is judged to be dangerous.
In the specific embodiment, identity cards need to be brushed when entering an airport, whether a case bottom exists is judged when the identity cards are brushed, and different thresholds are set according to different crime records when the case bottom exists; and increasing the danger index according to the captured behaviors of the cameras, starting the cameras to track the positions of the cameras when a certain person reaches the threshold value of the person, and reminding people of needing to track the positions when the danger index reaches a certain degree.
S31, processing the human body image by using a MASK-RCNN algorithm, extracting a plurality of behavior danger points of the human body, and marking in sequence;
s32, a risk point is calculated, and it is determined whether there is a risk by setting the risk point to a risk coefficient/10.
The behavioral risk points include eyes, face, hands, crotch, and feet.
In S40, the data display module sends out warning information to the situation of the dangerous person, displays the position of the dangerous person on the display screen in real time, displays the warning information, and sends out an audio alarm.
The invention innovatively provides a novel safety detection algorithm combining character behavior, dress-up and danger coefficients, and carries out more accurate distinguishing judgment on the disguised dangerous character and the normal passenger by setting a danger coefficient threshold and adding a plurality of behavior condition constraints. Compared with the prior safety detection-based technology, the method for monitoring the behavior is higher in recognition degree and better in accuracy, and the risk of the human beings is quantified by the method for monitoring the behavior.
Innovative attempts have been made to apply behavior monitoring to airports, and to monitor in real time whether dangerous persons are mixed in the airport using a person risk quantification strategy based on behavior monitoring. The detection technology is innovatively applied to airports, the technical level of airport safety protection is improved, and better guarantee is provided for the life and property safety of passengers and crew members.
The behavior monitoring module, the danger index judging module and the warning module are innovatively combined for use, and a set of complete automatic real-time behavior detection system is realized. Compared with the traditional special person responsible for monitoring the video, the safety detection system provided by the invention can automatically complete detection and early warning of the behavior risk index of the person, reduces the manpower input, enhances the coupling degree of the behavior monitoring module and the risk index judging module, and improves the real-time monitoring effect.
Claims (6)
1. The airport figure risk quantification method based on behavior monitoring is characterized in that an airport figure risk quantification system based on behavior monitoring comprises an image acquisition module, an image identification module, a risk detection module and a data display module which are sequentially connected, wherein the image acquisition module comprises a high-definition camera and is used for acquiring video images of a designated area frame by frame; the image recognition module detects human bodies in the continuous frame images and recognizes the behavior danger points of the detected people; the danger detection module detects danger values and change conditions of character behaviors in continuous frame images based on the fact that the target detection frame is matched with the set threshold value to judge whether the characters in the video are dangerous or not; the data display module displays whether dangerous persons exist in the video image area through the display and gives corresponding alarm prompts, and the method adopting the system comprises the following steps:
s10, acquiring images in the corresponding areas by using the cameras;
s20, carrying out human body identification framing;
s30, identifying and calculating behavior danger points;
and S40, sending out warning information to the situation of the dangerous person through the data display module.
2. The method of claim 1, wherein the performing human identification framing comprises:
s21, processing the video image by using the R-CNN algorithm, detecting the human in the image and framing by using a detection frame;
s22, calculating the character behaviors and the risk index lambda, scoring the character behaviors, recording 10 scores when any behavior in a preset risk behavior library is met, superposing multiple behavior scores, and if the behavior meets the lambda>λ1Then, the person is judged to be dangerous.
3. Method according to claim 2, characterized in that said threshold λ1＝50。
4. The method of claim 3, wherein the performing behavioral risk point identification and calculation comprises the steps of:
s31, processing the human body image by using a MASK-RCNN algorithm, extracting a plurality of behavior danger points of the human body, and marking in sequence;
s32, a risk point is calculated, and it is determined whether there is a risk by setting the risk point to the risk index/10.
5. The method of claim 4, wherein the behavioral risk points include eyes, faces, hands, crotch, and feet.
6. The method as claimed in claim 1, wherein the data display module sends out warning information for the situation of the dangerous person, displays the position of the dangerous person in real time on a display screen, displays the warning information, and sends out an audio alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027803.8A CN112287760A (en) | 2020-09-26 | 2020-09-26 | Behavior monitoring-based airport figure risk quantification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027803.8A CN112287760A (en) | 2020-09-26 | 2020-09-26 | Behavior monitoring-based airport figure risk quantification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287760A true CN112287760A (en) | 2021-01-29 |
Family
ID=74421479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011027803.8A Pending CN112287760A (en) | 2020-09-26 | 2020-09-26 | Behavior monitoring-based airport figure risk quantification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287760A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554261A (en) * | 2021-05-24 | 2021-10-26 | 浙江大华技术股份有限公司 | Abnormal object identification method, abnormal object identification device, electronic device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460362A (en) * | 2018-03-23 | 2018-08-28 | 成都品果科技有限公司 | A kind of system and method for detection human body |
| CN109214274A (en) * | 2018-07-19 | 2019-01-15 | 国政通科技有限公司 | A kind of airport security management system |
| CN109784149A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | A kind of detection method and system of skeleton key point |
| CN109920208A (en) * | 2019-01-31 | 2019-06-21 | 深圳绿米联创科技有限公司 | Tumble prediction technique, device, electronic equipment and system |
| CN110096606A (en) * | 2018-12-27 | 2019-08-06 | 深圳云天励飞技术有限公司 | A kind of expatriate's management method, device and electronic equipment |
| CN111242025A (en) * | 2020-01-13 | 2020-06-05 | 佛山科学技术学院 | Action real-time monitoring method based on YOLO |
-
2020
- 2020-09-26 CN CN202011027803.8A patent/CN112287760A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460362A (en) * | 2018-03-23 | 2018-08-28 | 成都品果科技有限公司 | A kind of system and method for detection human body |
| CN109214274A (en) * | 2018-07-19 | 2019-01-15 | 国政通科技有限公司 | A kind of airport security management system |
| CN109784149A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | A kind of detection method and system of skeleton key point |
| CN110096606A (en) * | 2018-12-27 | 2019-08-06 | 深圳云天励飞技术有限公司 | A kind of expatriate's management method, device and electronic equipment |
| CN109920208A (en) * | 2019-01-31 | 2019-06-21 | 深圳绿米联创科技有限公司 | Tumble prediction technique, device, electronic equipment and system |
| CN111242025A (en) * | 2020-01-13 | 2020-06-05 | 佛山科学技术学院 | Action real-time monitoring method based on YOLO |
Non-Patent Citations (1)
| Title |
|---|
| 黄心汉, vol. 1, 国防工业出版社, pages: 112 - 113 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554261A (en) * | 2021-05-24 | 2021-10-26 | 浙江大华技术股份有限公司 | Abnormal object identification method, abnormal object identification device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214274B (en) | Airport security management system | |
| US7683929B2 (en) | System and method for video content analysis-based detection, surveillance and alarm management | |
| KR101610657B1 (en) | Three-dimensional virtual entrance control and communicable disease control system and method based on entrance control data | |
| US20070122003A1 (en) | System and method for identifying a threat associated person among a crowd | |
| Liao et al. | A localized approach to abandoned luggage detection with foreground-mask sampling | |
| CN108256459A (en) | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically | |
| US20040240542A1 (en) | Method and apparatus for video frame sequence-based object tracking | |
| CN105868689A (en) | Cascaded convolutional neural network based human face occlusion detection method | |
| US20130216107A1 (en) | Method of surveillance by face recognition | |
| CN108009488A (en) | The street security joint defense system of Behavior-based control analysis | |
| US20210364356A1 (en) | System and method for using artificial intelligence to enable elevated temperature detection of persons using commodity-based thermal cameras | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| Patil et al. | Suspicious movement detection and tracking based on color histogram | |
| Nandhini et al. | An Improved Crime Scene Detection System Based on Convolutional Neural Networks and Video Surveillance | |
| CN113033521A (en) | Perimeter dynamic early warning method and system based on target analysis | |
| CN111462417A (en) | Multi-information verification system and multi-information verification method for unmanned bank | |
| CN112287760A (en) | Behavior monitoring-based airport figure risk quantification method | |
| KR101113515B1 (en) | Video index system using surveillance camera and the method thereof | |
| KR20190072323A (en) | Image Monitoring System and Method for Monitoring Image | |
| JP6650659B2 (en) | Suspicious person detection device and program | |
| CN109977806A (en) | Realize the system and method for IDC computer room disengaging personnel's fine-grained management | |
| CN113223081A (en) | High-altitude parabolic detection method and system based on background modeling and deep learning | |
| Dirgantara et al. | Design of Face Recognition Security System on Public Spaces | |
| Minar et al. | Intruder detection for automated access control systems with Kinect device | |
| CN112699745A (en) | Method for positioning trapped people on fire scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |
|
| RJ01 | Rejection of invention patent application after publication |