CN105488490A - Judge dressing detection method based on video - Google Patents
Judge dressing detection method based on video Download PDFInfo
- Publication number
- CN105488490A CN105488490A CN201510975030.9A CN201510975030A CN105488490A CN 105488490 A CN105488490 A CN 105488490A CN 201510975030 A CN201510975030 A CN 201510975030A CN 105488490 A CN105488490 A CN 105488490A
- Authority
- CN
- China
- Prior art keywords
- dressing
- emblem
- video
- judge
- personage
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a judge dressing detection method based on a video, comprising steps of using a DPM algorithm to identify a head portion and a shoulder portion in an interested area in the image to obtain a man scope in the video, performing detection and determination on the badge, the collar badge, the necktie and the clothes color in the clothes area through the clothes texture and color characteristics, and calculating the dressing energy and performing final determination according to the determination result of the independent characteristics. The judge dressing detection method based on the video determines whether the dressing of the person in the video accords with the requirement through the determination on the badge, the collar badge, the necktie and the clothes color according to the energy accumulation principle. The principle invention method comprises three parts which are people identification, independent characteristic determination and comprehensive energy calculation. The method is high in accuracy and low in miss rate.
Description
Technical field
The invention belongs to video detection technology field, relate to a kind of judge's dressing detection method based on video.
Background technology
In court, the dressing of judge whether specification can embody the seriousness of court, and bring deterrent also can to all kinds of personnel participating in court's trial, be the important component part of court's discipline.Judge should strictly observe dressing specification.Along with the carrying out of court's electronization upgrading, present most court requires that installing camera records court trial process.After having had high definition court's trial video, use computer generation to carry out dressing specification for people and be detected as in order to possibility.
Summary of the invention
The present invention, in order to solve above-mentioned problems of the prior art, provides a kind of judge's dressing detection method based on video.
The present invention for addressing this problem taked technical scheme is:
A kind of judge's dressing detection method based on video, the method comprises the steps: that the personage's head first using DPM algorithm to identify in image in area-of-interest takes on region, obtain the personage's scope in video, then to the method emblem in personage's clothes region, neck emblem, necktie with clothes color utilizes texture, color characteristic detects and judges, finally calculate dressing energy according to the judged result of these independent characteristics and finally judge.
Specifically, DPM algorithm is utilized first image to be checked to be carried out piecemeal, then HOG feature is extracted to each piece, calculate the distance of each block to center again to obtain the weight of each block, the HOG feature of these Weights is undertaken training and detecting by SVM cascade classifier, set up personage's head shoulder model, then use head shoulder model to detect at the area-of-interest of video to be measured, obtain the personage's scope in video.
HOG characteristic sum hsv color feature is utilized according to known method emblem, neck emblem, necktie Sample Storehouse, SVM cascade classifier and neural network is used to carry out model training respectively, then the personage's scope detected is utilized to infer the region such as collar, front, detect with SVM cascade classifier in that region, find doubtful method emblem, neck emblem, necktie region; Finally suspicious region is identified by neural network, judge that whether it be correct method emblem, neck emblem, necktie region.
According to the known clothes color gamut closing rule, by the personage's scope utilizing DPM algorithm to detect, carry out color cluster calculating, judge personage's clothes whether specification; Weight shared by different each independent characteristic of dressing type set, utilizes method emblem, neck emblem, necktie, clothes color judged result, calculates the energy of different dressing type; Finally, according to dressing energy, whether rule judgement is closed to personage's dressing.
The advantage that the present invention has and good effect are:
Judge's dressing detection method based on video of the present invention, by the independent judgement to independent characteristics such as method emblem, neck emblem, necktie and clothes colors, according to energy accumulation principle, judges whether the personnel's dressing in video meets the requirements.This invention comprises person recognition, independent characteristic judges and complex energy calculates three parts.This invention has compared with high-accuracy and lower loss.
Accompanying drawing explanation
Fig. 1 is the overall flow figure of the judge's dressing detection method based on video of the present invention;
Fig. 2 is that the present invention uses DPM algorithm to carry out the process flow diagram of piecemeal detection;
Fig. 3 is that the present invention extracts the process flow diagram of HOG feature to each piece.
Embodiment
Referring to the drawings and specific embodiments, the judge's dressing detection method based on video of the present invention is described in detail.Specific embodiment described below is only preferred forms of the present invention, and can not be interpreted as limitation of the present invention.
As shown in Figure 1, judge's dressing detection method based on video of the present invention, comprise the steps: that the personage's head first using DPM algorithm to identify in image in area-of-interest takes on region, obtain the personage's scope in video, then to the method emblem in personage's clothes region, neck emblem, necktie with clothes color utilizes texture, color characteristic detects and judges, finally calculate dressing energy according to the judged result of these independent characteristics and finally judge.
The first step that dressing detects finds people's object area, uses DPM algorithm to carry out training and the detection of personage's head shoulder model in the present invention.First image to be checked is carried out piecemeal by DPM algorithm, then extracts HOG feature to each piece, then calculates the distance of each block to center to obtain the weight of each block, the HOG feature of these Weights undertaken training and detecting by SVM cascade classifier.DPM algorithm as shown in Figure 2.
Gradient orientation histogram (HistogramofOrientedGradient, HOG) feature is a kind of character description method commonly used in computer vision and image processing field, and it extracts characteristic procedure as shown in Figure 3.Just can analyze personage's dressing after finding people's object area.
Dressing needs the independent characteristic detected to be method emblem, neck emblem, necktie and clothes color in detecting.The method that wherein method emblem, neck emblem, necktie adopt extraction HOG feature to carry out the training of SVM cascade model obtains corresponding prior model, and the position that then may exist at these independent characteristics is detected, and finds doubtful feature.Corresponding territory, left regio pectoris, method emblem, the shoulder central area that neck emblem and necktie correspondence vary in size.While use SVM cascade classifier carries out training, also need to use neural network to carry out the training of independent characteristic.After finding doubtful feature, re-use neural network and confirm, obtain method emblem, whether neck emblem, necktie exist.
Another independent characteristic that dressing detects is clothes color, the detection method of clothes color is, according to priori, obtain the hsv color spatial dimension of the clothes color of closing rule, then the people's object area obtained by DPM carries out cluster according to hsv color space, thus find maximum conjunction rule color region, judge whether this region meets personage and wear scope clothes to determine whether clothes color closes rule.
After the detection completing each independent characteristic, according to setting different energy of wearing each clothing type of weight calculation of each independent characteristic corresponding to type clothes, possess independent characteristic then energy increase, otherwise energy reduces.Regular judge's robe need possess neck emblem, method emblem, color characteristic, and trial clothes and trial in summer clothes need possess different method emblems and different colours feature.When energy continues to increase and exceedes certain threshold value, think that rule are closed in current people's dressing, when energy continues reduce and exceed certain threshold value, then think that current people's dressing in violation of rules and regulations, when energy is between two threshold values and when shaking, thinking there is no conclusion, according to detection Stringency, being classified as different conjunction rule and violation results by there is no conclusion.
The present invention utilizes high definition court's trial video, is automatically found judge position, then carries out the detection of dressing specification.This method supports the detection of multiple dressing type, comprises regular judge's robe, trial clothes, trial in summer clothes etc., and supports that independently method emblem, necktie detect.This method has higher accuracy and lower loss.And owing to employing the thought of energy accumulation, there is stronger robustness.
Claims (4)
1. the judge's dressing detection method based on video, it is characterized in that, the method comprises the steps: that the personage's head first using DPM algorithm to identify in image in area-of-interest takes on region, obtain the personage's scope in video, then to the method emblem in personage's clothes region, neck emblem, necktie with clothes color utilizes texture, color characteristic detects and judges, finally calculate dressing energy according to the judged result of these independent characteristics and finally judge.
2. the judge's dressing detection method based on video according to claim 1, it is characterized in that: first image to be checked is carried out piecemeal by DPM algorithm, then HOG feature is extracted to each piece, calculate the distance of each block to center again to obtain the weight of each block, the HOG feature of these Weights is undertaken training and detecting by SVM cascade classifier, set up personage's head shoulder model, then use head shoulder model to detect at the area-of-interest of video to be measured, obtain the personage's scope in video.
3. the judge's dressing detection method based on video according to claim 2, it is characterized in that: utilize HOG characteristic sum hsv color feature according to known method emblem, neck emblem, necktie Sample Storehouse, SVM cascade classifier and neural network is used to carry out model training respectively, then the personage's scope detected is utilized to infer the region such as collar, front, detect with SVM cascade classifier in that region, find doubtful method emblem, neck emblem, necktie region; Finally suspicious region is identified by neural network, judge that whether it be correct method emblem, neck emblem, necktie region.
4. the judge's dressing detection method based on video according to claim 3, is characterized in that: according to the known clothes color gamut closing rule, by the personage's scope utilizing DPM algorithm to detect, carry out color cluster calculating, judges personage's clothes whether specification; Weight shared by different each independent characteristic of dressing type set, utilizes method emblem, neck emblem, necktie, clothes color judged result, calculates the energy of different dressing type; Finally, according to dressing energy, whether rule judgement is closed to personage's dressing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510975030.9A CN105488490A (en) | 2015-12-23 | 2015-12-23 | Judge dressing detection method based on video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510975030.9A CN105488490A (en) | 2015-12-23 | 2015-12-23 | Judge dressing detection method based on video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105488490A true CN105488490A (en) | 2016-04-13 |
Family
ID=55675462
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510975030.9A Pending CN105488490A (en) | 2015-12-23 | 2015-12-23 | Judge dressing detection method based on video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105488490A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107305636A (en) * | 2016-04-22 | 2017-10-31 | 株式会社日立制作所 | Target identification method, Target Identification Unit, terminal device and target identification system |
CN107679524A (en) * | 2017-10-31 | 2018-02-09 | 天津天地伟业信息系统集成有限公司 | A kind of detection method of the safety cap wear condition based on video |
CN107832728A (en) * | 2017-11-21 | 2018-03-23 | 天津英田视讯科技有限公司 | A kind of judge based on video makes a phone call Activity recognition method |
CN107909580A (en) * | 2017-11-01 | 2018-04-13 | 深圳市深网视界科技有限公司 | A kind of pedestrian wears color identification method, electronic equipment and storage medium clothes |
CN107920223A (en) * | 2016-10-08 | 2018-04-17 | 杭州海康威视数字技术股份有限公司 | A kind of object behavior detection method and device |
CN108010063A (en) * | 2017-12-27 | 2018-05-08 | 天津天地伟业投资管理有限公司 | A kind of moving target based on video enters or leaves the detection method in region |
CN108052900A (en) * | 2017-12-12 | 2018-05-18 | 成都睿码科技有限责任公司 | A kind of method by monitor video automatic decision dressing specification |
CN109145947A (en) * | 2018-07-17 | 2019-01-04 | 昆明理工大学 | A kind of Fashionable women dress image fine grit classification method based on component detection and visual signature |
CN109271846A (en) * | 2018-08-01 | 2019-01-25 | 深圳云天励飞技术有限公司 | Personal identification method, apparatus and storage medium |
CN109446932A (en) * | 2018-10-11 | 2019-03-08 | 武汉微道云信息科技有限公司 | A kind of dressing inspection method, device, terminal device and computer storage medium |
CN110427808A (en) * | 2019-06-21 | 2019-11-08 | 武汉倍特威视系统有限公司 | Police uniform recognition methods based on video stream data |
CN110456955A (en) * | 2019-08-01 | 2019-11-15 | 腾讯科技(深圳)有限公司 | Exposure dress ornament detection method, device, system, equipment and storage medium |
CN110503058A (en) * | 2019-08-27 | 2019-11-26 | 上海交通大学苏州人工智能研究院 | A kind of dressing compliance detection method |
CN110705505A (en) * | 2019-10-14 | 2020-01-17 | 国网山东省电力公司泰安供电公司 | Intelligent identification device, method and system for service specification of electric power business hall |
CN112084986A (en) * | 2020-09-16 | 2020-12-15 | 国网福建省电力有限公司营销服务中心 | Real-time safety helmet detection method based on image feature extraction |
CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN113379144A (en) * | 2021-06-24 | 2021-09-10 | 深圳开思信息技术有限公司 | Store purchase order generation method and system for online automobile distribution purchase platform |
CN113538455A (en) * | 2021-06-15 | 2021-10-22 | 聚好看科技股份有限公司 | Three-dimensional hairstyle matching method and electronic equipment |
CN114241521A (en) * | 2021-12-13 | 2022-03-25 | 北京华夏电通科技股份有限公司 | Method, device and equipment for identifying court trial video picture normal area |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521565A (en) * | 2011-11-23 | 2012-06-27 | 浙江晨鹰科技有限公司 | Garment identification method and system for low-resolution video |
US8498448B2 (en) * | 2011-07-15 | 2013-07-30 | International Business Machines Corporation | Multi-view object detection using appearance model transfer from similar scenes |
CN103745226A (en) * | 2013-12-31 | 2014-04-23 | 国家电网公司 | Dressing safety detection method for worker on working site of electric power facility |
CN104268900A (en) * | 2014-09-26 | 2015-01-07 | 中安消技术有限公司 | Motion object detection method and device |
CN104318198A (en) * | 2014-02-28 | 2015-01-28 | 郑州金惠计算机系统工程有限公司 | Identification method and device suitable for substation robot patrolling |
CN104504381A (en) * | 2015-01-09 | 2015-04-08 | 博康智能网络科技股份有限公司 | Non-rigid target detection method and system thereof |
-
2015
- 2015-12-23 CN CN201510975030.9A patent/CN105488490A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8498448B2 (en) * | 2011-07-15 | 2013-07-30 | International Business Machines Corporation | Multi-view object detection using appearance model transfer from similar scenes |
CN102521565A (en) * | 2011-11-23 | 2012-06-27 | 浙江晨鹰科技有限公司 | Garment identification method and system for low-resolution video |
CN103745226A (en) * | 2013-12-31 | 2014-04-23 | 国家电网公司 | Dressing safety detection method for worker on working site of electric power facility |
CN104318198A (en) * | 2014-02-28 | 2015-01-28 | 郑州金惠计算机系统工程有限公司 | Identification method and device suitable for substation robot patrolling |
CN104268900A (en) * | 2014-09-26 | 2015-01-07 | 中安消技术有限公司 | Motion object detection method and device |
CN104504381A (en) * | 2015-01-09 | 2015-04-08 | 博康智能网络科技股份有限公司 | Non-rigid target detection method and system thereof |
Non-Patent Citations (1)
Title |
---|
PEDRO F. FELZENSZWALB: "Object Detection with Discriminatively Trained Part-Based Models", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107305636A (en) * | 2016-04-22 | 2017-10-31 | 株式会社日立制作所 | Target identification method, Target Identification Unit, terminal device and target identification system |
CN107920223A (en) * | 2016-10-08 | 2018-04-17 | 杭州海康威视数字技术股份有限公司 | A kind of object behavior detection method and device |
CN107679524A (en) * | 2017-10-31 | 2018-02-09 | 天津天地伟业信息系统集成有限公司 | A kind of detection method of the safety cap wear condition based on video |
CN107909580A (en) * | 2017-11-01 | 2018-04-13 | 深圳市深网视界科技有限公司 | A kind of pedestrian wears color identification method, electronic equipment and storage medium clothes |
CN107832728A (en) * | 2017-11-21 | 2018-03-23 | 天津英田视讯科技有限公司 | A kind of judge based on video makes a phone call Activity recognition method |
CN108052900A (en) * | 2017-12-12 | 2018-05-18 | 成都睿码科技有限责任公司 | A kind of method by monitor video automatic decision dressing specification |
CN108010063A (en) * | 2017-12-27 | 2018-05-08 | 天津天地伟业投资管理有限公司 | A kind of moving target based on video enters or leaves the detection method in region |
CN109145947A (en) * | 2018-07-17 | 2019-01-04 | 昆明理工大学 | A kind of Fashionable women dress image fine grit classification method based on component detection and visual signature |
CN109145947B (en) * | 2018-07-17 | 2022-04-12 | 昆明理工大学 | Fashion women's dress image fine-grained classification method based on part detection and visual features |
CN109271846A (en) * | 2018-08-01 | 2019-01-25 | 深圳云天励飞技术有限公司 | Personal identification method, apparatus and storage medium |
CN109446932A (en) * | 2018-10-11 | 2019-03-08 | 武汉微道云信息科技有限公司 | A kind of dressing inspection method, device, terminal device and computer storage medium |
CN110427808A (en) * | 2019-06-21 | 2019-11-08 | 武汉倍特威视系统有限公司 | Police uniform recognition methods based on video stream data |
CN110456955B (en) * | 2019-08-01 | 2022-03-29 | 腾讯科技(深圳)有限公司 | Exposed clothing detection method, device, system, equipment and storage medium |
CN110456955A (en) * | 2019-08-01 | 2019-11-15 | 腾讯科技(深圳)有限公司 | Exposure dress ornament detection method, device, system, equipment and storage medium |
CN110503058A (en) * | 2019-08-27 | 2019-11-26 | 上海交通大学苏州人工智能研究院 | A kind of dressing compliance detection method |
CN110705505A (en) * | 2019-10-14 | 2020-01-17 | 国网山东省电力公司泰安供电公司 | Intelligent identification device, method and system for service specification of electric power business hall |
CN112084986A (en) * | 2020-09-16 | 2020-12-15 | 国网福建省电力有限公司营销服务中心 | Real-time safety helmet detection method based on image feature extraction |
CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN112200051B (en) * | 2020-09-30 | 2023-09-29 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN113538455A (en) * | 2021-06-15 | 2021-10-22 | 聚好看科技股份有限公司 | Three-dimensional hairstyle matching method and electronic equipment |
CN113538455B (en) * | 2021-06-15 | 2023-12-12 | 聚好看科技股份有限公司 | Three-dimensional hairstyle matching method and electronic equipment |
CN113379144A (en) * | 2021-06-24 | 2021-09-10 | 深圳开思信息技术有限公司 | Store purchase order generation method and system for online automobile distribution purchase platform |
CN113379144B (en) * | 2021-06-24 | 2021-11-30 | 深圳开思信息技术有限公司 | Store purchase order generation method and system for online automobile distribution purchase platform |
CN114241521A (en) * | 2021-12-13 | 2022-03-25 | 北京华夏电通科技股份有限公司 | Method, device and equipment for identifying court trial video picture normal area |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105488490A (en) | Judge dressing detection method based on video | |
CN110443137B (en) | Multi-dimensional identity information identification method and device, computer equipment and storage medium | |
CN104463146B (en) | Posture identification method and device based on near-infrared TOF camera depth information | |
CN105740945B (en) | A kind of people counting method based on video analysis | |
WO2020253062A1 (en) | Method and apparatus for detecting image border | |
US10691947B2 (en) | Monitoring device | |
CN108629319B (en) | Image detection method and system | |
CN109002801B (en) | Face shielding detection method and system based on video monitoring | |
CN105574515B (en) | A kind of pedestrian recognition methods again under non-overlapping visual field | |
CN105844242A (en) | Method for detecting skin color in image | |
CN102609684B (en) | Human body posture detection method and device | |
CN103020596A (en) | Method for identifying abnormal human behaviors in power production based on block model | |
JP7183089B2 (en) | Information processing device, information processing system, information processing method, and program | |
CN103034852A (en) | Specific color pedestrian detecting method in static video camera scene | |
CN105069816B (en) | A kind of method and system of inlet and outlet people flow rate statistical | |
CN104484645A (en) | Human-computer interaction-oriented '1' gesture-recognition method and system | |
CN109215010A (en) | A kind of method and robot face identification system of picture quality judgement | |
CN101996317B (en) | Method and device for identifying markers in human body | |
CN110211251A (en) | Face recognition method, face recognition device, storage medium and face recognition terminal | |
Lian et al. | Matching of tracked pedestrians across disjoint camera views using CI-DLBP | |
CN114022845A (en) | Real-time detection method and computer readable medium for electrician insulating gloves | |
CN107832728A (en) | A kind of judge based on video makes a phone call Activity recognition method | |
CN104463144A (en) | Method and system for detecting head and shoulders of pedestrian in image based on local main direction and energy analysis strategy | |
CN102254148A (en) | Method for identifying human faces in real time under multi-person dynamic environment | |
CN105791815B (en) | A kind of TV line automatic judging methods |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160413 |
|
RJ01 | Rejection of invention patent application after publication |