CN110909722A - Anti-cheating camera based on target action detection - Google Patents
Anti-cheating camera based on target action detection Download PDFInfo
- Publication number
- CN110909722A CN110909722A CN201911371061.8A CN201911371061A CN110909722A CN 110909722 A CN110909722 A CN 110909722A CN 201911371061 A CN201911371061 A CN 201911371061A CN 110909722 A CN110909722 A CN 110909722A
- Authority
- CN
- China
- Prior art keywords
- cheating
- action
- video
- analysis system
- forbidden
- 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.)
- Withdrawn
Links
- 230000009471 action Effects 0.000 title claims abstract description 98
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004891 communication Methods 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims description 20
- 230000006399 behavior Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 230000006872 improvement Effects 0.000 description 6
- 241000209202 Bromus secalinus Species 0.000 description 3
- 208000008918 voyeurism Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Human Computer Interaction (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an anti-cheating camera based on target action detection, which comprises: the camera body is arranged in the examination room to shoot videos of people in the examination room and then output the videos; the recognition analysis system is in communication connection with the camera body, and is used for receiving the video output by the camera body, then recognizing and analyzing the personnel action in the video and outputting an analysis result; the cheating processing system is coupled to the recognition and analysis system and used for receiving the analysis result output by the recognition and analysis system and then executing the cheating processing action. The anti-cheating camera based on target action detection can effectively identify the action condition of the examinees in the current examination room through the identification analysis system and the cheating processing system, and analyzes the action, so that the effect of automatically judging whether the examinees cheat is achieved.
Description
Technical Field
The invention relates to a camera, in particular to an anti-cheating camera based on target action detection.
Background
The anti-cheating is an important additional performance in the examination process, if the examination can be cheated in the examination process, the examination loses fairness, the significance of the examination is lost, and therefore the anti-cheating management and control in the examination process are very strict at present.
At present, the existing cheating means are various and can be mainly divided into two categories, one category is cheating in the field, such as peeping, small copy and the like, the other category is cheating outside the field, communication is mainly carried out between the communication equipment and the outside, corresponding answers are provided through the outside, aiming at the two cheating modes, the two ways of preventing are mainly adopted in the prior art, monitoring and preventing are realized by arranging a camera and a prisoner for the cheating in the field, the cheating outside the field is realized by arranging a shielding device, the shielding device has extremely good effect by the two ways of almost eliminating the cheating outside the field, the mode of combining the camera and the prisoner needs to consume considerable manpower, because the prisoner is required to be arranged, and special personnel are required to be arranged to observe images shot by the camera, so that the APP based on the terminal with the camera and the system are provided in the prior art, the patent number is 2017114445470, the method is characterized in that an integral room model is built, then the visual field range of a user is analyzed, so that whether the user steals and cheats is automatically observed, but the method can only detect whether the user steals and cheats, only can detect the visual field change condition of the user, does not detect other limb actions of the user, and cannot effectively detect when the user reads in the original position and cheats in other modes, so that the anti-cheating performance is greatly reduced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an anti-cheating camera which has strong anti-cheating performance and is based on target action detection.
In order to achieve the purpose, the invention provides the following technical scheme: an anti-cheating camera based on target action detection, comprising:
the camera body is arranged in the examination room to shoot videos of people in the examination room and then output the videos;
the recognition analysis system is in communication connection with the camera body, and is used for receiving the video output by the camera body, then recognizing and analyzing the personnel action in the video and outputting an analysis result;
the cheating processing system is coupled with the recognition and analysis system and used for receiving the analysis result output by the recognition and analysis system and then executing the cheating processing action;
the identification and analysis system stores a plurality of pieces of cheating action data, identifies the action in the video after the video is received, compares the action with the cheating action data, judges that the video is suspected to be cheated if the action in the video is close to the action displayed by the cheating action data, and outputs the analysis result of the suspected cheating.
As a further improvement of the invention, the specific steps of the recognition analysis system are as follows:
identifying an examiner in a video, and identifying the head and arm actions of the examiner;
step two, constructing a fan-shaped area in front of the head of the examinee identified in the step one, and representing the visual field area of the examinee;
step three, constructing an action forbidden zone model by the cheating action data, and forming a hand staying forbidden zone, a head staying forbidden zone and a visual field forbidden zone in the identified video through the action forbidden zone model;
and step four, setting a stay time threshold, judging whether the time that the hands of the examiners stay in the hand stay forbidden region, the time that the heads stay in the head stay forbidden region and the time that the visual fields stay in the visual field forbidden region in the video exceed the stay time threshold, if so, judging the examinees to be suspected cheating behaviors, and outputting the analysis results of the suspected cheating behaviors.
As a further improvement of the present invention, the motion forbidden zone model in the third step further forms a forbidden motion in the identified video, and when the motion of the examiner in the video approaches the forbidden motion within a period of time, the suspected cheating behavior is determined, and an analysis result of the suspected cheating is output.
As a further improvement of the present invention, the action of the cheating processing system to perform the cheating processing is specifically as follows:
step 31, copying and intercepting video data when suspected cheating analysis results output by the identification and analysis system are intercepted;
step 32, sending the intercepted video data to a invigilator mobile terminal for the invigilator to analyze and judge whether the cheating behavior is detected;
and step 33, if the invigilator determines that the video data are not cheating, discarding the video data, and if the invigilator determines that the video data are cheating, storing the video data into an external cheating evidence base.
As a further improvement of the present invention, the cheating action data is obtained by extracting the video and image of the cheating evidence in the external cheating evidence base, and the specific steps of the identification and analysis system for storing the cheating action data are as follows:
step 21, carrying a deep learning neural network in the recognition analysis system, and adjusting to a learning mode;
and step 22, inputting the extracted video and image into a deep learning neural network to train the deep learning neural network.
The method has the advantages that through the arrangement of the camera body, the action video of the examinee can be acquired through a mode of shooting an examination room, then the action of the examinee in the video can be effectively analyzed and identified through the identification and analysis system, whether the examinee has cheating behaviors or not is automatically judged, and therefore compared with the mode that only the visual field area of the examinee can be judged in the prior art, the action of the examinee is analyzed and judged, cheating actions can be well identified, and the accuracy of an existing anti-cheating system is greatly improved.
Drawings
FIG. 1 is a block diagram of an anti-cheating camera based on target action detection in accordance with the present invention;
fig. 2 is a schematic view of a model when the camera body is mounted on a ceiling.
Detailed Description
The invention will be further described in detail with reference to the following examples, which are given in the accompanying drawings.
Referring to fig. 1 to 2, an anti-cheating camera based on target motion detection according to the present embodiment includes: the camera body 1 is arranged in an examination room to shoot videos of people in the examination room and then output the videos;
the recognition analysis system 2 is in communication connection with the camera body 1, receives the video output by the camera body 1, recognizes and analyzes the action of people in the video, and outputs an analysis result;
the cheating processing system 3 is coupled to the recognition and analysis system 2 and is used for receiving the analysis result output by the recognition and analysis system 2 and then executing the cheating processing action;
wherein, the identification and analysis system 2 stores a plurality of cheating action data, after receiving the video, the action in the video is identified and compared with the cheating action data, if the action in the video is close to the action shown by the cheating action data, the action is judged to be suspected cheating, and the analysis result of suspected cheating is output, in the process of using the camera of the embodiment, only the camera body 1 is required to be installed in the examination room and then is connected with the identification and analysis system 2 and the cheating processing system 3 in sequence, when the operation is carried out, the action video of the personnel in the current examination room is shot in real time mainly through the shooting action of the camera body 1, then the action video is transmitted into the identification and analysis system 2, the action of the examinee in the video is analyzed and judged through the identification and analysis action of the identification and analysis system 2, and whether the action in the video has cheating action is analyzed and judged, then through the action of the cheating processing system 3, the processing action can be generated when the cheating action is judged, the participation of people is further reduced, compared with the prior art that the method of only detecting the visual field area is adopted, the detection on the actions of other limbs of the examinee is added, the performance of the whole anti-cheating camera is greatly improved, wherein the camera body 1 in the embodiment can be formed by combining a rail laid on the ceiling of the examination room and a head part arranged on the rail in a sliding manner, the head part can freely move on the ceiling of the examination room through the rail, so that when the condition that the cheating of a certain examinee is possibly judged, the head part can move to the upper part of the examinee through the rail, the examinee can be shot in further detail, and the effect of shooting a clearer video is realized, the rails are distributed according to the seats in the examination room and are connected with each other through a connecting passage, so that the effect that the head of any examination person can move to the head can be realized.
As a specific embodiment of the improvement, the specific steps of the recognition analysis system 2 are as follows: identifying an examiner in a video, and identifying the head and arm actions of the examiner; step two, constructing a fan-shaped area in front of the head of the examinee identified in the step one, and representing the visual field area of the examinee;
step three, constructing an action forbidden zone model by the cheating action data, and forming a hand staying forbidden zone, a head staying forbidden zone and a visual field forbidden zone in the identified video through the action forbidden zone model;
step four, setting a stay time threshold, judging whether the time of the hands of the examinees staying in the hand stay forbidden area, the time of the heads staying in the head stay forbidden area and the time of the visual field staying in the visual field forbidden area in the video exceed the stay time threshold, if the stay time threshold is exceeded, judging the examinees to be suspected cheating behaviors, and outputting analysis results of the suspected cheating behaviors, wherein in the process of preparing cheating by the examinees, the answers need to be checked, the visual field areas of the examinees are necessarily concentrated in one area for a period of time, so that the detection of whether the examinees have cheating behaviors can be effectively realized through the arrangement of the visual field forbidden area, and when the examinees steal and cheating books occur, the books are inevitably checked by the presence of proctor in a low head checking mode, and the books are simultaneously gripped by hands, so the combined action of the hand stay forbidden area and the head stay forbidden area is realized, the cheating mode of checking the small copy and books at the lower head can be effectively detected, the cheating is realized by touching the marks with hands (such as braille), the hands are inevitably under the examination desk for a long time at the moment, and therefore the cheating mode of the examination personnel can be more comprehensively identified and judged by setting the hand stop forbidden zone, the head stop forbidden zone, the visual field forbidden zone and the time threshold.
In one embodiment of improvement, the forbidden action zone model in the step three also forms forbidden actions in the identified video, and when the actions of the examiners in the video are close to the forbidden actions within a period of time, then the suspected cheating behavior is judged, the analysis result of the suspected cheating is output, and if the suspected cheating behavior is the same, the cheater can repeatedly do the same action within a period of time, such as looking down at the head, then the head-up writing is carried out, so that the behavior of the cheater at the moment can repeatedly act in the processes of head-up writing answers and head-down peeping, therefore, if the method of staying in the forbidden zone is adopted, the staying time cannot reach the time threshold, the problem that the cheating personnel can not be identified can be effectively identified by combining the method with the staying forbidden zone.
As an improved specific embodiment, the action of the cheating processing system 3 to perform the cheating process is specifically as follows:
step 31, copying and intercepting video data when the suspected cheating analysis result output by the identification and analysis system 2 is intercepted;
step 32, sending the intercepted video data to a invigilator mobile terminal for the invigilator to analyze and judge whether the cheating behavior is detected;
and step 33, if the invigilator determines that the video data is a non-cheating behavior, discarding the video data, if the invigilator determines that the video data is a cheating behavior, storing the video data in an external cheating evidence base, judging the cheating actions identified and analyzed by the identification and analysis system 2 into suspected cheating actions for the sake of judgment rigor, and then confirming the cheating modes in a manual confirmation mode, so that the fairness of final cheating judgment is ensured, and meanwhile, the video data suspected to be cheated is timely and effectively intercepted and can also be used as enough evidence for subsequently judging the cheating.
As an improved specific implementation manner, the cheating action data is obtained by extracting the cheating evidence videos and images of the past years in the external cheating evidence base, and the specific steps of storing the cheating action data in the recognition and analysis system 2 are as follows:
step 21, carrying a deep learning neural network in the recognition and analysis system 2, and adjusting to a learning mode;
and step 22, inputting the extracted videos and images into a deep learning neural network to train the deep learning neural network, so that the cheating action data can be input in a deep learning neural network self-learning mode, only the cheating evidence videos and images in the past year need to be directly input into the system to train without additional operation, and compared with a mode of manual setting, the storage process is simpler and more convenient, the cheating actions which can be identified by the final result are as many as possible, and meanwhile, when new cheating actions occur, the system can be subjected to timely learning training, the advancement of the system is kept, and the identification performance of the system is kept.
In summary, the anti-cheating camera in this embodiment is configured by combining the recognition analysis system 2 and the cheating processing system 3, so that whether an examinee has a cheating behavior can be effectively determined by recognizing the actions of the examinee, and thus, compared with a method of determining only a visual field area in the prior art, the method has a wider determination range and a more accurate recognition result.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (5)
1. The utility model provides an prevent camera of practising fraud based on target action detects which characterized in that: the method comprises the following steps:
the camera body (1) is arranged in an examination room and is used for shooting videos of people in the examination room and outputting the videos;
the recognition analysis system (2) is in communication connection with the camera body (1) and is used for receiving the video output by the camera body (1), recognizing and analyzing the action of people in the video and outputting an analysis result;
the cheating processing system (3) is coupled with the recognition and analysis system (2) and is used for receiving the analysis result output by the recognition and analysis system (2) and then executing the cheating processing action;
the identification and analysis system (2) stores a plurality of cheating action data, identifies the action in the video after the video is received, compares the action with the cheating action data, judges that the video is suspected to be cheated if the action in the video is close to the action displayed by the cheating action data, and outputs the analysis result of the suspected cheating.
2. The anti-cheating camera based on target action detection of claim 1, wherein: the identification and analysis system (2) comprises the following specific steps:
identifying an examiner in a video, and identifying the head and arm actions of the examiner;
step two, constructing a fan-shaped area in front of the head of the examinee identified in the step one, and representing the visual field area of the examinee;
step three, constructing an action forbidden zone model by the cheating action data, and forming a hand staying forbidden zone, a head staying forbidden zone and a visual field forbidden zone in the identified video through the action forbidden zone model;
and step four, setting a stay time threshold, judging whether the time that the hands of the examiners stay in the hand stay forbidden region, the time that the heads stay in the head stay forbidden region and the time that the visual fields stay in the visual field forbidden region in the video exceed the stay time threshold, if so, judging the examinees to be suspected cheating behaviors, and outputting the analysis results of the suspected cheating behaviors.
3. The anti-cheating camera based on target action detection of claim 2, wherein: and the action forbidden zone model in the third step also forms forbidden actions in the identified video, and when the actions of the examiners in the video are close to the forbidden actions within a period of time, the suspected cheating actions are judged, and the analysis result of the suspected cheating is output.
4. The anti-cheating camera based on target action detection of claim 1, 2 or 3, wherein: the action of the cheating processing system (3) for cheating processing is as follows:
step 31, copying and intercepting video data when the suspected cheating analysis result output by the identification and analysis system (2) is intercepted;
step 32, sending the intercepted video data to a invigilator mobile terminal for the invigilator to analyze and judge whether the cheating behavior is detected;
and step 33, if the invigilator determines that the video data are not cheating, discarding the video data, and if the invigilator determines that the video data are cheating, storing the video data into an external cheating evidence base.
5. The anti-cheating camera based on target action detection of claim 1, 2 or 3, wherein: the cheating action data are obtained by extracting the cheating evidence videos and images of the past years in the external cheating evidence base, and the specific steps of storing the cheating action data in the recognition analysis system (2) are as follows:
step 21, carrying a deep learning neural network in the recognition analysis system (2) and adjusting to a learning mode;
and step 22, inputting the extracted video and image into a deep learning neural network to train the deep learning neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911371061.8A CN110909722A (en) | 2019-12-26 | 2019-12-26 | Anti-cheating camera based on target action detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911371061.8A CN110909722A (en) | 2019-12-26 | 2019-12-26 | Anti-cheating camera based on target action detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110909722A true CN110909722A (en) | 2020-03-24 |
Family
ID=69828156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911371061.8A Withdrawn CN110909722A (en) | 2019-12-26 | 2019-12-26 | Anti-cheating camera based on target action detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909722A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084994A (en) * | 2020-09-21 | 2020-12-15 | 哈尔滨二进制信息技术有限公司 | Online invigilation remote video cheating research and judgment system and method |
| CN112446295A (en) * | 2020-10-30 | 2021-03-05 | 四川天翼网络服务有限公司 | Examination cheating behavior analysis method and system |
| CN112926453A (en) * | 2021-02-26 | 2021-06-08 | 电子科技大学 | Examination room cheating behavior analysis method based on motion feature enhancement and long-term time sequence modeling |
| CN113515976A (en) * | 2020-04-10 | 2021-10-19 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
| KR102321917B1 (en) * | 2020-07-13 | 2021-11-04 | 주식회사 두두아이티 | System for video remote management and supervision of online test |
| CN114051118A (en) * | 2021-10-25 | 2022-02-15 | 重庆中科云从科技有限公司 | Examination room monitoring system |
| CN115394026A (en) * | 2022-07-15 | 2022-11-25 | 安徽电信规划设计有限责任公司 | Intelligent monitoring method and system based on 5G technology |
| CN117152688A (en) * | 2023-10-31 | 2023-12-01 | 江西拓世智能科技股份有限公司 | Intelligent classroom behavior analysis method and system based on artificial intelligence |
| CN117221519A (en) * | 2023-11-07 | 2023-12-12 | 哈尔滨学院 | Induction alarm system for preventing cheating in examination |
-
2019
- 2019-12-26 CN CN201911371061.8A patent/CN110909722A/en not_active Withdrawn
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515976A (en) * | 2020-04-10 | 2021-10-19 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
| CN113515976B (en) * | 2020-04-10 | 2023-08-29 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
| KR102321917B1 (en) * | 2020-07-13 | 2021-11-04 | 주식회사 두두아이티 | System for video remote management and supervision of online test |
| CN112084994A (en) * | 2020-09-21 | 2020-12-15 | 哈尔滨二进制信息技术有限公司 | Online invigilation remote video cheating research and judgment system and method |
| CN112446295A (en) * | 2020-10-30 | 2021-03-05 | 四川天翼网络服务有限公司 | Examination cheating behavior analysis method and system |
| CN112926453A (en) * | 2021-02-26 | 2021-06-08 | 电子科技大学 | Examination room cheating behavior analysis method based on motion feature enhancement and long-term time sequence modeling |
| CN112926453B (en) * | 2021-02-26 | 2022-08-05 | 电子科技大学 | Examination room cheating behavior analysis method based on motion feature enhancement and long-term time sequence modeling |
| CN114051118A (en) * | 2021-10-25 | 2022-02-15 | 重庆中科云从科技有限公司 | Examination room monitoring system |
| CN115394026A (en) * | 2022-07-15 | 2022-11-25 | 安徽电信规划设计有限责任公司 | Intelligent monitoring method and system based on 5G technology |
| CN117152688A (en) * | 2023-10-31 | 2023-12-01 | 江西拓世智能科技股份有限公司 | Intelligent classroom behavior analysis method and system based on artificial intelligence |
| CN117221519A (en) * | 2023-11-07 | 2023-12-12 | 哈尔滨学院 | Induction alarm system for preventing cheating in examination |
| CN117221519B (en) * | 2023-11-07 | 2024-01-30 | 哈尔滨学院 | Induction alarm system for preventing cheating in examination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909722A (en) | Anti-cheating camera based on target action detection | |
| CN105791299A (en) | Unattended monitoring type intelligent on-line examination system | |
| CN107491717A (en) | The detection method that cheats at one's exam and device | |
| CN109726663A (en) | Online testing monitoring method, device, computer equipment and storage medium | |
| CN104751110B (en) | A kind of biopsy method and device | |
| CN111523444B (en) | Classroom behavior detection method based on improved Openpost model and facial micro-expression | |
| CN107220590A (en) | A kind of anti-cheating network research method based on In vivo detection, apparatus and system | |
| Hu et al. | Research on abnormal behavior detection of online examination based on image information | |
| CN109298785A (en) | A kind of man-machine joint control system and method for monitoring device | |
| CN110090424A (en) | A kind of judgment system for the examination of football around rod | |
| CN106791633A (en) | Intelligence invigilator's system and method | |
| CN111291613B (en) | Classroom performance evaluation method and system | |
| CN111382672A (en) | Cheating monitoring method and device for online examination | |
| CN109308581A (en) | A kind of examination cloud platform system based on block chain | |
| CN110781762A (en) | Examination cheating detection method based on posture | |
| CN107133611A (en) | A kind of classroom student nod rate identification with statistical method and device | |
| CN110349460A (en) | A kind of online education and examination system | |
| KR100998617B1 (en) | Central control type cbt system and method thereof | |
| CN110723621A (en) | Device and method for detecting smoking in elevator car based on deep neural network | |
| CN111523445A (en) | Examination behavior detection method based on improved Openpos model and facial micro-expression | |
| CN113052127A (en) | Behavior detection method, behavior detection system, computer equipment and machine readable medium | |
| CN113794759B (en) | Examination cloud platform system based on block chain | |
| CN112419814A (en) | Sports score test system | |
| CN116206258A (en) | Remote examination room monitoring system and method based on examination room behavior detection statistics | |
| CN109583397B (en) | Implementation method of artificial intelligent judgment system for elevator examination |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200324 |