CN113792624A - Early warning security monitoring method for bank ATM - Google Patents
Early warning security monitoring method for bank ATM Download PDFInfo
- Publication number
- CN113792624A CN113792624A CN202111001545.0A CN202111001545A CN113792624A CN 113792624 A CN113792624 A CN 113792624A CN 202111001545 A CN202111001545 A CN 202111001545A CN 113792624 A CN113792624 A CN 113792624A
- Authority
- CN
- China
- Prior art keywords
- image
- early warning
- gesture
- security monitoring
- current frame
- 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 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 230000006835 compression Effects 0.000 claims description 9
- 238000007906 compression Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 abstract description 3
- 239000003086 colorant Substances 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
- G07F19/20—Automatic teller machines [ATMs]
- G07F19/207—Surveillance aspects at ATMs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of ATM early warning, in particular to a bank ATM early warning security monitoring method, which comprises the following steps: s1, reading image: reading a video image collected by a camera; s2, preprocessing: processing a current frame in a video image, removing noise in the image and improving the definition of the image; s3, dynamic detection; s4, gesture recognition, wherein the method comprises the steps of collecting a real-time image by using a camera installed in the self-service bank, detecting the action of a person entering a lens in real time after reading the image by a background, and automatically alarming to ensure the personal safety of a teller once abnormity occurs; meanwhile, in order to improve the use under different scenes, gesture recognition is added, and when a specific alarm gesture is recognized, an alarm can be automatically given. In the detection and identification process, digital algorithms such as wavelet transformation, Gaussian denoising, template comparison and the like are applied to improve the identification accuracy under different environments.
Description
Technical Field
The invention relates to the technical field of ATM early warning, in particular to a bank ATM early warning security monitoring method.
Background
In the current society, robbery events of bank automatic teller machines occur continuously. At present, the security measures of many bank ATM adopt a camera, only by visual identification of monitoring personnel, alarm is given when encountering danger, so that the alarm is inevitable to be overlooked, especially at night, only video of case can be recorded, and the alarm cannot be rapidly given out when the case is sent, so that a plurality of cases to be robbed cannot be discovered in time, and difficulty is caused to arrest criminals and rescue the robbed persons.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a method for early warning, security and protection monitoring of a bank ATM.
In order to achieve the purpose, the invention adopts the following technical scheme:
a bank ATM early warning security monitoring method comprises the following steps:
s1, reading image: reading a video image collected by a camera;
s2, preprocessing: processing a current frame in a video image, removing noise in the image and improving the definition of the image;
s3, dynamic detection: analyzing and comparing the preprocessed real-time image, comparing the binarized images of the current frame and the previous frame, if the current threshold value is greater than a set value, considering that an emergency situation is met, alarming, and if the current threshold value is less than or equal to the set value, performing the next step;
s4, gesture recognition: and acquiring a target gesture area through the preprocessed real-time image, extracting current hand features, acquiring current frame gesture information, comparing the current frame gesture information with the alarm gesture information in the gallery, if the comparison result is consistent or approximate, determining that an emergency situation is met, and alarming is needed, and if the comparison result is different, re-performing the step S1.
Preferably, in the step S2, a median filtering method and a low-pass gaussian filtering method are adopted in the preprocessing process to process the current frame in the video image and remove noise in the image, so as to improve the clarity of the image.
Preferably, in the step S3, the image needs to be grayed and binarized, so as to compare the binarized images of the current frame and the previous frame.
Preferably, in the step S4, after the pre-processed real-time image is subjected to an expansion algorithm, a corrosion algorithm and a smoothing process, the hand is tracked and positioned, and a target gesture area is obtained; performing skin color segmentation: converting the RGB image into HSV space, and extracting an H channel image; and then, carrying out region segmentation: performing threshold segmentation on the image of the H channel to obtain a skin color area preliminarily; and then, carrying out feature extraction to obtain gesture information.
Preferably, in the step S4, the feature extraction module includes motion feature extraction and gesture recognition, and the feature extraction is used to check each pixel to determine whether the pixel represents a feature.
Preferably, the feature processing includes wavelet compression, gaussian denoising, and gesture recognition.
Preferably, the wavelet compression can effectively compress the data to the minimum, can enable the information to be processed quickly, and is convenient for a data transmission compression method to ensure the real-time performance and the accuracy of the robot on target monitoring.
Preferably, the gaussian filtering is used to perform weighted average on the whole image, the value of each pixel point is obtained by performing weighted average on the value of each pixel point and other pixel values in the neighborhood, and the specific operation of the gaussian filtering is as follows: and scanning each pixel in the image by using the template, and replacing the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template.
Preferably, the gesture recognition is to realize recognition of picking and high efficiency of implementation by solving the problem of palm tracking and positioning on the basis of the existing gesture recognition, perform binarization processing on the image by a self-adaptive threshold value, extract pixel points of all colors and similar colors in the image, acquire a target picking area after expansion algorithm, corrosion algorithm and smoothing processing, recognize according to the characteristics of the target area, determine the current gesture and acquire gesture information.
The invention has the beneficial effects that: the method provided by the invention is characterized in that a camera installed in the self-service bank is used for acquiring a real-time image, the action of a person entering a lens is detected in real time after the image is read by a background, and an alarm is automatically given to ensure the personal safety of a teller once abnormality occurs; meanwhile, in order to improve the use under different scenes, gesture recognition is added, and when a specific alarm gesture is recognized, an alarm can be automatically given. In the detection and identification process, digital algorithms such as wavelet transformation, Gaussian denoising, template comparison and the like are applied to improve the identification accuracy under different environments.
Drawings
FIG. 1 is a general design flow chart of a method for early warning, security and protection monitoring of a bank ATM machine according to the present invention;
FIG. 2 is a dynamic detection flow chart of a method for early warning security monitoring of a bank ATM according to the present invention;
fig. 3 is a gesture recognition flowchart of a method for early warning security monitoring of a bank ATM according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1-3, a method for early warning security monitoring of a bank ATM comprises the following steps:
s1, reading image: reading a video image collected by a camera;
s2, preprocessing: processing a current frame in a video image, removing noise in the image and improving the definition of the image;
s3, dynamic detection: analyzing and comparing the preprocessed real-time image, comparing the binarized images of the current frame and the previous frame, if the current threshold value is greater than a set value, considering that an emergency situation is met, alarming, and if the current threshold value is less than or equal to the set value, performing the next step;
s4, gesture recognition: and acquiring a target gesture area through the preprocessed real-time image, extracting current hand features, acquiring current frame gesture information, comparing the current frame gesture information with the alarm gesture information in the gallery, if the comparison result is consistent or approximate, determining that an emergency situation is met, and alarming is needed, and if the comparison result is different, re-performing the step S1.
Further, in step S2, a median filtering method and a low-pass gaussian filtering method are used in the preprocessing process to process the current frame in the video image and remove noise in the image, so as to improve the clarity of the image.
Further, in step S3, the image needs to be grayed and binarized, so as to compare the binarized images of the current frame and the previous frame.
Further, in the step S4, the preprocessed real-time image is subjected to dilation algorithm, erosion algorithm and smoothing processing, and then the hand is tracked and positioned to obtain a target gesture area; performing skin color segmentation: converting the RGB image into HSV space, and extracting an H channel image; and then, carrying out region segmentation: performing threshold segmentation on the image of the H channel to obtain a skin color area preliminarily; and then, carrying out feature extraction to obtain gesture information.
Further, in step S4, the feature extraction module includes motion feature extraction and gesture recognition, and the feature extraction is used to check each pixel to determine whether the pixel represents a feature.
Further, the feature processing comprises wavelet compression, Gaussian denoising and gesture recognition.
Furthermore, wavelet compression can effectively compress data to the minimum, information can be rapidly processed, and a data transmission compression method is convenient to ensure real-time performance and accuracy of the robot on target monitoring.
Further, gaussian filtering is used for performing weighted average on the whole image, the value of each pixel point is obtained by performing weighted average on the value of each pixel point and other pixel values in the neighborhood, and the specific operation of gaussian filtering is as follows: and scanning each pixel in the image by using the template, and replacing the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template.
Furthermore, the gesture recognition is that on the basis of the existing gesture recognition, the recognition of picking and the high efficiency of implementation are realized by solving the problem of palm tracking and positioning, the image is subjected to binarization processing by a self-adaptive threshold value, pixel points of all colors and similar colors in the image are extracted, then a target picking area is obtained after expansion algorithm, corrosion algorithm and smoothing processing, then recognition is carried out according to the characteristics of the target area, the current gesture is determined, and gesture information is obtained
In the embodiment, the method provided by the invention is characterized in that a camera installed in the self-service bank is used for acquiring a real-time image, the action of a person entering a lens is detected in real time after the image is read by a background, and an alarm is automatically given to ensure the personal safety of a teller once abnormity occurs; meanwhile, in order to improve the use under different scenes, gesture recognition is added, and when a specific alarm gesture is recognized, an alarm can be automatically given. In the detection and identification process, digital algorithms such as wavelet transformation, Gaussian denoising, template comparison and the like are applied to improve the identification accuracy under different environments.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (9)
1. A bank ATM early warning security monitoring method is characterized by comprising the following steps:
s1, reading image: reading a video image collected by a camera;
s2, preprocessing: processing a current frame in a video image, removing noise in the image and improving the definition of the image;
s3, dynamic detection: analyzing and comparing the preprocessed real-time image, comparing the binarized images of the current frame and the previous frame, if the current threshold value is greater than a set value, considering that an emergency situation is met, alarming, and if the current threshold value is less than or equal to the set value, performing the next step;
s4, gesture recognition: and acquiring a target gesture area through the preprocessed real-time image, extracting current hand features, acquiring current frame gesture information, comparing the current frame gesture information with the alarm gesture information in the gallery, if the comparison result is consistent or approximate, determining that an emergency situation is met, and alarming is needed, and if the comparison result is different, re-performing the step S1.
2. The method for bank ATM machine early warning security monitoring according to claim 1, wherein in the step S2, a median filtering method and a low-pass Gaussian filtering method are adopted in the preprocessing process, the current frame in the video image is processed, and the noise in the image is removed, so that the image clarity is improved.
3. The method for early warning, security and protection monitoring of an ATM machine of a bank as claimed in claim 1, wherein in the step S3, the image needs to be grayed and binarized, so as to compare the binarized image of the current frame with the binarized image of the previous frame.
4. The bank ATM machine early warning security monitoring method according to claim 1, wherein in the step S4, after the pre-processed real-time image is processed by an expansion algorithm, a corrosion algorithm and a smoothing process, the hand is tracked and positioned to obtain a target gesture area; performing skin color segmentation: converting the RGB image into HSV space, and extracting an H channel image; and then, carrying out region segmentation: performing threshold segmentation on the image of the H channel to obtain a skin color area preliminarily; and then, carrying out feature extraction to obtain gesture information.
5. An ATM early warning security monitoring method for banks as claimed in claim 4, wherein in step S4, the feature extraction module includes action feature extraction and gesture recognition, the feature extraction is used to check each pixel to determine whether the pixel represents a feature.
6. The method for bank ATM machine early warning security monitoring as claimed in claim 5, wherein the feature processing includes wavelet compression, Gaussian denoising and gesture recognition.
7. The method as claimed in claim 6, wherein the wavelet compression can compress the data to the minimum effectively, so that the information can be processed rapidly, and the data transmission compression method is convenient to ensure the real-time and accuracy of the target monitoring of the robot.
8. The bank ATM machine early warning security monitoring method according to claim 6, characterized in that Gaussian filtering is used for weighted average of the whole image, the value of each pixel point is obtained by weighted average of itself and other pixel values in the neighborhood, and the specific operation of Gaussian filtering is as follows: and scanning each pixel in the image by using the template, and replacing the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template.
9. The method for early warning, security and protection monitoring of the bank ATM according to claim 6 is characterized in that the gesture recognition is to realize the recognition of picking and the high efficiency of implementation by solving the problem of palm tracking and positioning on the basis of the existing gesture recognition, the image is subjected to binarization processing by a self-adaptive threshold value, all color and color-like pixel points in the image are extracted, then a target picking area is obtained after expansion algorithm, corrosion algorithm and smoothing processing, then the recognition is carried out according to the characteristics of the target area, the current gesture is determined, and the gesture information is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001545.0A CN113792624A (en) | 2021-08-30 | 2021-08-30 | Early warning security monitoring method for bank ATM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001545.0A CN113792624A (en) | 2021-08-30 | 2021-08-30 | Early warning security monitoring method for bank ATM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113792624A true CN113792624A (en) | 2021-12-14 |
Family
ID=79182380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111001545.0A Pending CN113792624A (en) | 2021-08-30 | 2021-08-30 | Early warning security monitoring method for bank ATM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792624A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230419280A1 (en) * | 2022-06-23 | 2023-12-28 | Truist Bank | Gesture recognition for advanced security |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059896A (en) * | 2007-05-16 | 2007-10-24 | 华为技术有限公司 | Detecting alarm method and alarm system |
| CN101344980A (en) * | 2008-08-21 | 2009-01-14 | 中国工商银行股份有限公司 | Safety detection system and method for ATM equipment |
| CN102542673A (en) * | 2010-12-30 | 2012-07-04 | 广州市浩云安防科技股份有限公司 | Automatic teller machine (ATM) pre-warning method and system based on computer vision |
| CN104834922A (en) * | 2015-05-27 | 2015-08-12 | 电子科技大学 | Hybrid neural network-based gesture recognition method |
| CN105930786A (en) * | 2016-04-18 | 2016-09-07 | 西北工业大学 | Abnormal behavior detection method for bank self-service hall |
| WO2016184431A1 (en) * | 2015-05-20 | 2016-11-24 | 王向恒 | Local calculation-based video monitoring method and terminal thereof |
| CN106981163A (en) * | 2017-03-26 | 2017-07-25 | 天津普达软件技术有限公司 | A kind of personnel invade abnormal event alarming method |
| CN108846356A (en) * | 2018-06-11 | 2018-11-20 | 南京邮电大学 | A method of the palm of the hand tracing and positioning based on real-time gesture identification |
| CN109040669A (en) * | 2018-06-28 | 2018-12-18 | 国网山东省电力公司菏泽供电公司 | Intelligent substation video fence method and system |
| CN110675582A (en) * | 2018-07-03 | 2020-01-10 | 北京蜂盒科技有限公司 | Automatic alarm method and device |
| CN110996052A (en) * | 2019-11-26 | 2020-04-10 | 绍兴天宏激光科技有限公司 | Emergency alarm method and system based on image recognition |
| CN111027395A (en) * | 2019-11-13 | 2020-04-17 | 珠海亿智电子科技有限公司 | Gesture recognition method and device, terminal equipment and computer readable storage medium |
| CN111127830A (en) * | 2018-11-01 | 2020-05-08 | 奇酷互联网络科技（深圳）有限公司 | Alarm method, alarm system and readable storage medium based on monitoring equipment |
| CN113055743A (en) * | 2021-03-10 | 2021-06-29 | 珠海安士佳电子有限公司 | Method and system for intelligently pushing video |
| CN113222582A (en) * | 2021-05-10 | 2021-08-06 | 广东便捷神科技股份有限公司 | Face payment retail terminal |
-
2021
- 2021-08-30 CN CN202111001545.0A patent/CN113792624A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059896A (en) * | 2007-05-16 | 2007-10-24 | 华为技术有限公司 | Detecting alarm method and alarm system |
| CN101344980A (en) * | 2008-08-21 | 2009-01-14 | 中国工商银行股份有限公司 | Safety detection system and method for ATM equipment |
| CN102542673A (en) * | 2010-12-30 | 2012-07-04 | 广州市浩云安防科技股份有限公司 | Automatic teller machine (ATM) pre-warning method and system based on computer vision |
| WO2016184431A1 (en) * | 2015-05-20 | 2016-11-24 | 王向恒 | Local calculation-based video monitoring method and terminal thereof |
| CN104834922A (en) * | 2015-05-27 | 2015-08-12 | 电子科技大学 | Hybrid neural network-based gesture recognition method |
| CN105930786A (en) * | 2016-04-18 | 2016-09-07 | 西北工业大学 | Abnormal behavior detection method for bank self-service hall |
| CN106981163A (en) * | 2017-03-26 | 2017-07-25 | 天津普达软件技术有限公司 | A kind of personnel invade abnormal event alarming method |
| CN108846356A (en) * | 2018-06-11 | 2018-11-20 | 南京邮电大学 | A method of the palm of the hand tracing and positioning based on real-time gesture identification |
| CN109040669A (en) * | 2018-06-28 | 2018-12-18 | 国网山东省电力公司菏泽供电公司 | Intelligent substation video fence method and system |
| CN110675582A (en) * | 2018-07-03 | 2020-01-10 | 北京蜂盒科技有限公司 | Automatic alarm method and device |
| CN111127830A (en) * | 2018-11-01 | 2020-05-08 | 奇酷互联网络科技（深圳）有限公司 | Alarm method, alarm system and readable storage medium based on monitoring equipment |
| CN111027395A (en) * | 2019-11-13 | 2020-04-17 | 珠海亿智电子科技有限公司 | Gesture recognition method and device, terminal equipment and computer readable storage medium |
| CN110996052A (en) * | 2019-11-26 | 2020-04-10 | 绍兴天宏激光科技有限公司 | Emergency alarm method and system based on image recognition |
| CN113055743A (en) * | 2021-03-10 | 2021-06-29 | 珠海安士佳电子有限公司 | Method and system for intelligently pushing video |
| CN113222582A (en) * | 2021-05-10 | 2021-08-06 | 广东便捷神科技股份有限公司 | Face payment retail terminal |
Non-Patent Citations (2)
| Title |
|---|
| YAN REN ET AL.: "Design of Intelligent Robot for Bank Early Warning and Security Based on Robot Vision", 《2021 INTERNATIONAL CONFERENCE OF OPTICAL IMAGING AND MEASUREMENT (ICOIM)》, 2 September 2021 (2021-09-02), pages 174 - 177 * |
| 任雁等: "基于机器人视觉的银行预警安防智能机器人设计", 《科技创新与应用》, vol. 12, no. 01, 8 January 2022 (2022-01-08), pages 95 - 98 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230419280A1 (en) * | 2022-06-23 | 2023-12-28 | Truist Bank | Gesture recognition for advanced security |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056079B (en) | A kind of occlusion detection method of image capture device and human face five-sense-organ | |
| US7215798B2 (en) | Method for forgery recognition in fingerprint recognition by using a texture classification of gray scale differential images | |
| CN103942850B (en) | Based on medical personnel's monitoring method on duty of video analysis and RFID technique | |
| CN110991348B (en) | Face micro-expression detection method based on optical flow gradient amplitude characteristics | |
| WO2018161849A1 (en) | Alarm system for falling in water based on image water texture and method therefor | |
| WO2018056355A1 (en) | Monitoring device | |
| CN110059634B (en) | Large-scene face snapshot method | |
| JP5726596B2 (en) | Image monitoring device | |
| Vijaykumar et al. | Rail defect detection using Gabor filters with texture analysis | |
| Bashbaghi et al. | Watch-list screening using ensembles based on multiple face representations | |
| CN112396011A (en) | Face recognition system based on video image heart rate detection and living body detection | |
| CN111401308B (en) | Fish behavior video identification method based on optical flow effect | |
| CN111860143A (en) | Real-time flame detection method for inspection robot | |
| CN114241370A (en) | Intrusion identification method and device based on digital twin transformer substation and computer equipment | |
| CN113792624A (en) | Early warning security monitoring method for bank ATM | |
| KR101243294B1 (en) | Method and apparatus for extracting and tracking moving objects | |
| CN108596057B (en) | Information security management system based on face recognition | |
| Wu et al. | Video surveillance object recognition based on shape and color features | |
| CN111681239A (en) | Bridge structure health intelligent monitoring system | |
| Ramkumar et al. | A novel iris recognition algorithm | |
| KR102423934B1 (en) | Smart human search integrated solution through face recognition and multiple object tracking technology of similar clothes color | |
| Wang et al. | A robust algorithm for shadow removal of foreground detection in video surveillance | |
| CN113537165B (en) | Detection method and system for pedestrian alarm | |
| Zaharin et al. | Comparison of human detection using background subtraction and frame difference | |
| CN112004056A (en) | Intelligent video analysis method with strong anti-interference capability |
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 |