CN114708543B - Examination student positioning method in examination room monitoring video image - Google Patents
Examination student positioning method in examination room monitoring video image Download PDFInfo
- Publication number
- CN114708543B CN114708543B CN202210629393.7A CN202210629393A CN114708543B CN 114708543 B CN114708543 B CN 114708543B CN 202210629393 A CN202210629393 A CN 202210629393A CN 114708543 B CN114708543 B CN 114708543B
- Authority
- CN
- China
- Prior art keywords
- image data
- monitoring video
- examination room
- video image
- examinee
- 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.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of image processing, in particular to a method for positioning examinees in an examination room monitoring video image, which mainly comprises the steps of firstly carrying out frame selection marking based on head hair areas of the examinees on a large amount of examination room monitoring video image data containing different examination scenes and different examinees according to the ear visible conditions of the examinees in the examination room monitoring video image data, establishing an examinee head hair area data set, carrying out primary screening based on high false alarm rate target detection on the basis, finally establishing a model based on SSD deep learning target detection, positioning the head hair areas of the examinees, and finally realizing the positioning of the examinees.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a method for positioning an examinee in an examination room monitoring video image.
Background
Examination is widely used as an important examination and drawing means all over the world, because fairness and justness can be ensured to some extent. However, various cheating means exist for smooth examination passing, and the examination monitoring system is widely applied to various examinations for ensuring the fairness and justice principle of the examinations. However, the examination room has a video monitoring system, which does not mean that the cheating problem can be solved well.
Although the video monitoring can record the examination room information completely, whether the examination cheating behavior exists still needs a large amount of manpower input by related departments to carry out post-processing and examination on the video data, wherein the cheating behavior does not exist in a large proportion of videos, but each video section needs to be carefully examined by related personnel, so that a large amount of workload is generated, the requirement for automatically identifying the behavior of the examinee in the examination room monitoring video is generated, and the key problem which needs to be solved is how to position the examinee in the examination room monitoring video.
The examination room monitoring video detection and positioning methods can be roughly divided into methods based on background difference, methods based on template matching and methods based on image characteristics, and the methods have the problems of limited detection range, large dependence on examination room layout and the like.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for positioning an examinee in an examination room monitoring video image, which comprises the following steps:
step 1: performing frame selection marking based on the head hair area of the examinee on a large amount of examination room monitoring video image data containing different examination scenes and different examinees, and then establishing an examinee head hair area data set of the examination room monitoring video image data;
step 2: establishing a target detection deep learning model for positioning a hair area at the top of an examinee in examination room monitoring video image data, firstly screening pixel points which are possibly hairs in the examination room monitoring video image data to obtain preprocessed image data, and then carrying out deep learning target detection based on SSD on the preprocessed image data;
and step 3: the head hair area of the examinee of the established examination room monitoring video image dataDividing the data set in proportion to generate a training data set and a testing data set respectively, training and testing the established target detection deep learning model for positioning the head top hair region of the examinee in the examination room monitoring video image data to obtain a final target detection model;
And 4, step 4: inputting initial image data of examination room monitoring video into final target detection modelThen, the examinee positioning result in the examination room monitoring video image data is obtained.
Further, step 1: the method comprises the following steps of performing frame selection marking based on the head hair area of an examinee on a large number of examinee monitoring video image data containing different examination scenes and different examinees, and specifically comprises the following steps: and carrying out box marking based on the ear exposure condition of the examinee and based on the approximate image on the head and top hair area of the examinee in the examination room monitoring video image data.
Further, the head and top hair area of the examinee in the examination room monitoring video image data is subjected to frame marking based on the examinee ear exposure condition, and the ear exposure condition is divided into: two ears are exposed, one ear is exposed, and no ear is exposed.
Furthermore, the head top hair area of the examinee in the examination room monitoring video image data is marked by a box based on an approximate image, and particularly, the horizontal and vertical edges of the generated frame are parallel to the edges of the image data.
Furthermore, two ears of the examinee in the video image data are exposed, and the frame selection area is as follows: using the lowest point of the boundary between the hair and the forehead obtained by the edge detection as the bottom of the frame selection region, and the distance from the bottom of the frame selection region to the top of the hair obtained by the edge detectionSelecting the height as the frame, and taking the longest distance between the left and right sides of the hair and the backgroundDoubling the frame selection width to form frame selection area and variableAndare weighting coefficients.
Further, if an ear of the examinee in the video image data is exposed, the framing area is: using the middle point between the highest point and the lowest point of the junction between the hair and the forehead as the bottom of the framed selection area, and the distance from the bottom of the framed selection area to the top of the hairHeight is selected as the longest distance between the edge of one exposed ear and hair and the edge of the other side hair and backgroundDoubling the frame selection width to form frame selection area and variableAndare weighting coefficients.
Furthermore, the examinee does not expose ears in the video image data, the highest point of the junction of the hair and the forehead is taken as the bottom of the frame selection area, the distance from the bottom of the frame selection area to the top of the hair is taken as the frame selection height, and the horizontal width displayed by the forehead in the image data is taken as the frame selection width to form the frame selection area.
Further, step 2: screening pixel points which may be hairs in the examination room monitoring video image data to obtain preprocessed image data, wherein the specific method comprises the following steps: firstly, the image data is grayed to obtain the grayscale image data(ii) a Then, the pixel value of each pixel point in the gray image data is calculated according toPerforming inversion to obtain grayscale inverted image dataIn which、As image data、The abscissa of (A) isOn the ordinate ofThe gray value of the pixel point; inverting gray scale image dataCFAR target detection with high false alarm rate is carried out to obtain screened image data, and a threshold value is setCarrying out binarization processing on the screened image data to obtain preprocessed image data。
Further, step 2: performing SSD-based deep learning target detection on the preprocessed image data, specifically: image data of binary detection resultAnd as an index image, mapping coordinates of non-0 pixel value pixel points in the index image in the image to corresponding examination room monitoring video image data, and establishing a target detection model for positioning the hair region of the examination room monitoring video image data based on an SSD target detection framework by taking the mapped pixel points as anchor frame center points.
Further, step 4: inputting initial image data of examination room monitoring video into final target detection modelThen, obtaining the examinee positioning result in the examination room monitoring video image data, specifically: inputting initial image data of examination room monitoring video into final target detection modelIn the method, the result of the hair region selection is obtained, and each selection region is expanded downwards to the self rangeAnd obtaining an updated region frame selection result, and determining the updated region frame selection result as a test taker positioning result.
The invention solves the following technical problems:
1. the frame selection marking method based on the examinee hair area is provided for the examinee monitoring video image data according to the ear visible condition of the examinee in the examinee monitoring video image data, and accuracy and reliability of the examinee hair area data set are improved.
2. The primary screening of target detection based on high false alarm rate is carried out on the pixel points which are probably hairs in the examination room monitoring video image data, so that the accuracy of examination of the hair region of the examinee is effectively improved.
3. The binary detection result of the monitoring video image data of the examination room is used as an index image, and the anchor frame selection is carried out on the basis of the index image, so that the accuracy of the examination room hair region detection is improved, and the complexity of a target detection model is reduced.
Drawings
Fig. 1 is a flow chart of a method for positioning examinees in an examination room monitoring video image.
Detailed Description
In the following, the technical solution in the embodiment of the present invention will be clearly and completely described with reference to the drawings in the embodiment of the present invention, and a flow chart of the method is shown in fig. 1, and includes the following steps:
a method for positioning examinees in an examination room monitoring video image comprises the following steps:
step 1: performing frame selection marking based on the head hair area of the examinee on a large amount of examination room monitoring video image data containing different examination scenes and different examinees, and then establishing an examinee head hair area data set of the examination room monitoring video image data;
and 2, step: establishing a target detection deep learning model for positioning a hair area at the top of an examinee in examination room monitoring video image data, firstly screening pixel points which are possibly hairs in the examination room monitoring video image data to obtain preprocessed image data, and then carrying out deep learning target detection based on SSD on the preprocessed image data;
and step 3: dividing an examinee's head top hair region data set of the established examination room monitoring video image data in proportion to generate a training data set and a testing data set respectively, training and testing the established target detection deep learning model for positioning the examinee's head top hair region in the examination room monitoring video image data to obtain a final target detection model;
And 4, step 4: inputting initial image data of examination room monitoring video into final target detection modelThen, the examinee positioning result in the examination room monitoring video image data is obtained.
Further, step 1: the method comprises the following steps of performing frame selection marking based on the head hair area of an examinee on a large amount of examination room monitoring video image data containing different examination scenes and different examinees, and specifically comprises the following steps: and carrying out frame marking on the head and top hair area of the examinee in the examination room monitoring video image data based on the ear exposure condition of the examinee and based on the approximate image.
Further, the head and top hair area of the examinee in the examination room monitoring video image data is subjected to frame marking based on the examinee ear exposure condition, and the ear exposure condition is divided into: two ears are exposed, one ear is exposed, and no ear is exposed.
Furthermore, the head top hair area of the examinee in the examination room monitoring video image data is marked by a box based on an approximate image, and particularly, the horizontal and vertical edges of the generated frame are parallel to the edges of the image data.
Furthermore, two ears of the examinee in the video image data are exposed, and the frame selection area is as follows: using the lowest point of the boundary between the hair and the forehead obtained by the edge detection as the bottom of the frame selection region, and the distance from the bottom of the frame selection region to the top of the hair obtained by the edge detectionSelecting the height as the frame, and taking the longest distance between the left and right sides of the hair and the backgroundDoubling the frame selection width to form frame selection area and variableAndare weighting coefficients.
Further, if an ear of the examinee in the video image data is exposed, the framing area is: using the middle point between the highest point and the lowest point of the junction between the hair and the forehead as the bottom of the framed selection area, and the distance from the bottom of the framed selection area to the top of the hairHeight is selected as the longest distance between the edge of one exposed ear and hair and the edge of the other side hair and backgroundDoubling the frame selection width to form frame selection area and variableAndare weighting coefficients.
Furthermore, the examinee does not expose ears in the video image data, the highest point of the junction of the hair and the forehead is taken as the bottom of the frame selection area, the distance from the bottom of the frame selection area to the top of the hair is taken as the frame selection height, and the horizontal width displayed by the forehead in the image data is taken as the frame selection width to form the frame selection area.
Further, step 2: screening pixel points which are possibly hairs in examination room monitoring video image data to obtain preprocessed image data, wherein the specific method comprises the following steps: firstly, the image data is grayed to obtain the grayscale image data(ii) a Then, the pixel value of each pixel point in the gray image data is calculated according toPerforming inversion to obtain grayscale inverted image dataWherein、As a number of imagesAccording to、On the abscissa ofOn the ordinate ofThe gray value of the pixel point; inverting gray scale image dataCarrying out CFAR target detection with high false alarm rate to obtain screened image data, and setting a threshold valueCarrying out binarization processing on the screened image data to obtain preprocessed image data。
Further, step 2: performing SSD-based deep learning target detection on the preprocessed image data, specifically: image data of binary detection resultAnd as an index image, mapping coordinates of non-0 pixel value pixel points in the index image in the image to corresponding examination room monitoring video image data, and establishing a target detection model for positioning the hair region of the examination room monitoring video image data based on an SSD target detection framework by taking the mapped pixel points as anchor frame center points.
Further, step 4: inputting initial image data of examination room monitoring video into final target detection modelIn (1),then obtaining the examinee positioning result in the examination room monitoring video image data, which specifically comprises the following steps: inputting initial image data of examination room monitoring video into final target detection modelIn the method, the result of the hair region selection is obtained, and each selection region is expanded downwards to the self rangeAnd obtaining an updated region frame selection result, and determining the updated region frame selection result as a test taker positioning result.
It should be apparent that the described embodiments are only some embodiments of the present invention, and not all embodiments. Other embodiments, which can be derived by one of ordinary skill in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Claims (9)
1. A method for positioning examinees in an examination room monitoring video image is characterized by comprising the following steps:
step 1: the method comprises the following steps of performing frame selection marking based on the head hair area of an examinee on a large number of examinee monitoring video image data containing different examination scenes and different examinees, and specifically comprises the following steps: carrying out box marking based on the ear exposure condition of the examinee and based on the approximate image on the head and hair area of the examinee in the monitoring video image data of the examination room; then establishing a data set of the head hair area of the examinee of the examination room monitoring video image data;
step 2: establishing a target detection deep learning model for positioning a hair area at the top of an examinee in examination room monitoring video image data, firstly screening pixel points which are possibly hairs in the examination room monitoring video image data to obtain preprocessed image data, and then carrying out deep learning target detection based on SSD on the preprocessed image data;
and step 3: dividing the data set of the head top hair area of the examinee of the established examination room monitoring video image data according to the proportion to respectively generate a training data set and a test data setTraining and testing the established target detection deep learning model for positioning the hair area at the top of the examinee in the examination room monitoring video image data to obtain a final target detection model M ssd ;
And 4, step 4: inputting initial image data of examination room monitoring video into final target detection model M ssd Then, the examinee positioning result in the examination room monitoring video image data is obtained.
2. The method according to claim 1, wherein the examination room monitoring video image is characterized in that the examination room monitoring video image data is subjected to examination room ear exposure condition-based frame marking on the top of the head and hair area of the examinee, and the ear exposure condition is divided into: two ears are exposed, one ear is exposed, and no ear is exposed.
3. The method according to claim 1, wherein the top hair area of the head of the examinee in the examination room monitoring video image data is marked by a box based on the approximate image, and the horizontal and vertical edges of the generated frame are parallel to the edges of the image data.
4. The method according to claim 2, wherein if two ears of the examinee are exposed in the video image data, the frame selection area is: taking the lowest point of the boundary between the hair and the forehead obtained by the edge detection as the bottom of the frame selection area, and taking the distance alpha from the bottom of the frame selection area to the top of the hair obtained by the edge detection 1 Selecting the height as a frame, and taking the beta of the longest distance between the left side and the right side of the hair and the background 1 Doubling the frame selection width to form a frame selection area, and changing the variable alpha 1 And beta 1 Are weighting coefficients.
5. The method as claimed in claim 2, wherein if an ear of the examinee appears in the video image data, the selection area is: with the highest point of the hair-forehead junction andthe middle value point between the lowest points is the bottom of the frame selection area, and the distance alpha from the bottom of the frame selection area to the top of the hair 2 Selecting the height as the frame, and exposing the longest distance beta between the border of one ear and hair and the border of the other hair and background 2 Doubling the frame selection width to form a frame selection area, and changing the variable alpha 2 And beta 2 Are weighting coefficients.
6. The method as claimed in claim 2, wherein the examinee in the video image data has no exposed ear, the highest point of the junction between the hair and the forehead is the bottom of the frame selection area, the distance from the bottom of the frame selection area to the topmost point of the hair is the frame selection height, and the horizontal width of the forehead displayed in the image data is the frame selection width, thereby forming the frame selection area.
7. The method for locating the examinee in the examination room monitoring video image according to claim 1, characterized in that the step 2: screening pixel points which are possibly hairs in examination room monitoring video image data to obtain preprocessed image data, wherein the specific method comprises the following steps: firstly, carrying out gray processing on image data to obtain gray image data I g (ii) a Then, the pixel value of each pixel point in the gray image data is according to I c (i,j)=255-I g (I, j) inverting to obtain grayscale inverted image data I c In which I g (i,j)、I c (I, j) is image data I g 、I c The horizontal coordinate in the gray value is i, and the vertical coordinate is j; inverting the grayscale image data I c Carrying out CFAR target detection with high false alarm rate to obtain screened image data, setting a threshold th, carrying out binarization processing on the screened image data to obtain preprocessed image data I t 。
8. The method for locating the examinee in the examination room monitoring video image according to claim 1, characterized in that the step 2: performing SSD-based deep learning target detection on the preprocessed image data, specifically: detecting the binary valueResulting image data I t And as an index image, mapping coordinates of non-0 pixel value pixel points in the index image in the image to corresponding examination room monitoring video image data, and establishing a target detection model for positioning the hair region of the examination room monitoring video image data based on an SSD target detection framework by taking the mapped pixel points as anchor frame center points.
9. The method for locating the examinee in the examination room monitoring video image according to claim 1, characterized in that the step 4: inputting initial image data of examination room monitoring video into final target detection model M ssd Then, obtaining the examinee positioning result in the examination room monitoring video image data, specifically: inputting initial image data of examination room monitoring video into final target detection model M ssd And obtaining a hair area framing result, expanding each framing area downwards by Q times of the range of the framing area to obtain an updated area framing result, and determining the updated area framing result as a test taker positioning result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210629393.7A CN114708543B (en) | 2022-06-06 | 2022-06-06 | Examination student positioning method in examination room monitoring video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210629393.7A CN114708543B (en) | 2022-06-06 | 2022-06-06 | Examination student positioning method in examination room monitoring video image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114708543A CN114708543A (en) | 2022-07-05 |
CN114708543B true CN114708543B (en) | 2022-08-30 |
Family
ID=82177605
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210629393.7A Active CN114708543B (en) | 2022-06-06 | 2022-06-06 | Examination student positioning method in examination room monitoring video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114708543B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116310806B (en) * | 2023-02-28 | 2023-08-29 | 北京理工大学珠海学院 | Intelligent agriculture integrated management system and method based on image recognition |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430809A (en) * | 1992-07-10 | 1995-07-04 | Sony Corporation | Human face tracking system |
CN105678213A (en) * | 2015-12-20 | 2016-06-15 | 华南理工大学 | Dual-mode masked man event automatic detection method based on video characteristic statistics |
CN106991360A (en) * | 2016-01-20 | 2017-07-28 | 腾讯科技(深圳)有限公司 | Face identification method and face identification system |
CN107451555A (en) * | 2017-07-27 | 2017-12-08 | 安徽慧视金瞳科技有限公司 | A kind of hair based on gradient direction divides to determination methods |
CN108260918A (en) * | 2018-02-09 | 2018-07-10 | 武汉技兴科技有限公司 | A kind of human hair information collecting method, device and intelligent clipping device |
CN109711377A (en) * | 2018-12-30 | 2019-05-03 | 陕西师范大学 | Standardize examinee's positioning and method of counting in the single-frame images of examination hall monitoring |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112686965A (en) * | 2020-12-25 | 2021-04-20 | 百果园技术(新加坡)有限公司 | Skin color detection method, device, mobile terminal and storage medium |
-
2022
- 2022-06-06 CN CN202210629393.7A patent/CN114708543B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430809A (en) * | 1992-07-10 | 1995-07-04 | Sony Corporation | Human face tracking system |
CN105678213A (en) * | 2015-12-20 | 2016-06-15 | 华南理工大学 | Dual-mode masked man event automatic detection method based on video characteristic statistics |
CN106991360A (en) * | 2016-01-20 | 2017-07-28 | 腾讯科技(深圳)有限公司 | Face identification method and face identification system |
CN107451555A (en) * | 2017-07-27 | 2017-12-08 | 安徽慧视金瞳科技有限公司 | A kind of hair based on gradient direction divides to determination methods |
CN108260918A (en) * | 2018-02-09 | 2018-07-10 | 武汉技兴科技有限公司 | A kind of human hair information collecting method, device and intelligent clipping device |
CN109711377A (en) * | 2018-12-30 | 2019-05-03 | 陕西师范大学 | Standardize examinee's positioning and method of counting in the single-frame images of examination hall monitoring |
Non-Patent Citations (2)
Title |
---|
Teaching Assistant and Class Attendance Analysis Using Surveillance Camera;Xiaofei Peng等;《IFTC 2018: Digital TV and Multimedia Communication》;20190511;413–422 * |
基于视频的人体检测与计数技术研究;王红梅;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20120515(第05期);I138-1385 * |
Also Published As
Publication number | Publication date |
---|---|
CN114708543A (en) | 2022-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11551433B2 (en) | Apparatus, method and computer program for analyzing image | |
US9977966B2 (en) | System and method for identifying, analyzing, and reporting on players in a game from video | |
CN107240047B (en) | Score evaluation method and device for teaching video | |
CN102622508B (en) | Image processing apparatus and image processing method | |
CN108229526A (en) | Network training, image processing method, device, storage medium and electronic equipment | |
CN109635875A (en) | A kind of end-to-end network interface detection method based on deep learning | |
CN104202547B (en) | Method, projection interactive approach and its system of target object are extracted in projected picture | |
WO2022001571A1 (en) | Computing method based on super-pixel image similarity | |
CN110837795A (en) | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video | |
CN110689000B (en) | Vehicle license plate recognition method based on license plate sample generated in complex environment | |
CN108846828A (en) | A kind of pathological image target-region locating method and system based on deep learning | |
WO2021068781A1 (en) | Fatigue state identification method, apparatus and device | |
CN106611160A (en) | CNN (Convolutional Neural Network) based image hair identification method and device | |
CN108305253A (en) | A kind of pathology full slice diagnostic method based on more multiplying power deep learnings | |
CN114708543B (en) | Examination student positioning method in examination room monitoring video image | |
CN112215217B (en) | Digital image recognition method and device for simulating doctor to read film | |
CN111709914A (en) | Non-reference image quality evaluation method based on HVS characteristics | |
CN111339902A (en) | Liquid crystal display number identification method and device of digital display instrument | |
WO2023160666A1 (en) | Target detection method and apparatus, and target detection model training method and apparatus | |
CN113705349A (en) | Attention power analysis method and system based on sight estimation neural network | |
CN111062953A (en) | Method for identifying parathyroid hyperplasia in ultrasonic image | |
CN113782184A (en) | Cerebral apoplexy auxiliary evaluation system based on facial key point and feature pre-learning | |
Kovalev et al. | Biomedical image recognition in pulmonology and oncology with the use of deep learning | |
KR20100010973A (en) | Method for automatic classifier of lung diseases | |
CN113743378A (en) | Fire monitoring method and device based on video |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |