CN115019236A - Mobile phone playing and off-duty detection alarm system and method based on deep learning - Google Patents
Mobile phone playing and off-duty detection alarm system and method based on deep learning Download PDFInfo
- Publication number
- CN115019236A CN115019236A CN202210739096.8A CN202210739096A CN115019236A CN 115019236 A CN115019236 A CN 115019236A CN 202210739096 A CN202210739096 A CN 202210739096A CN 115019236 A CN115019236 A CN 115019236A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- target
- playing
- background management
- behaviors
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000013135 deep learning Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims description 33
- 230000006399 behavior Effects 0.000 claims description 32
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/22—Status alarms responsive to presence or absence of persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of image detection and identification, and discloses a mobile phone playing and off-post detection alarm system and method based on deep learning. The invention can automatically identify whether the employee plays the mobile phone or leaves the post, and can help the manager to supervise the working condition of the employee during working hours.
Description
Technical Field
The invention relates to the technical field of image detection and identification, in particular to a system and a method for playing a mobile phone and detecting and alarming off duty based on deep learning.
Background
In daily work, some employees have behaviors of playing mobile phones and leaving the post during working hours, so that the working efficiency is reduced, and the working environment of a company is seriously influenced. Typically, to deal with such problems, supervision is required by a manager. However, the manager cannot perform real-time supervision, and there may be a phenomenon that the manager opens one eye and closes one eye, or even congeals at the same time, which may damage the benefit of the company.
Disclosure of Invention
The invention mainly aims to provide a mobile phone playing and off-post detection alarm system and method based on deep learning, and aims to transmit real-time video data through a camera arranged on a station desktop or a ceiling, complete judgment on whether a worker plays a mobile phone or leaves a post, and help a manager to monitor the working condition of the worker during working hours in real time.
In order to achieve the purpose, the mobile phone playing and off-post detection alarm system based on deep learning comprises monitoring cameras, an image storage server and a background management server, wherein the monitoring cameras are respectively arranged above an office area and used for monitoring the behavior condition of personnel in the office area, the monitoring cameras are respectively in data connection with the image storage server, the image storage server is respectively in data connection with the background management server, the image storage server is used for detecting human bodies and mobile phone targets in images, marking the position information of the human bodies and the mobile phone targets, judging whether employees are playing mobile phones or off-post according to the position information of the human bodies and the mobile phones, uploading the result to the background management server after detecting the behaviors of the employees playing mobile phones and off-post, and the background management server is used for recording the behaviors and displaying the behaviors in real time, and the system alarms to inform an administrator, so that the administrator can monitor the running state of the system and the behavior of the office area staff in real time through a browser.
The invention also provides a method for playing mobile phones and detecting and alarming off duty based on deep learning, which is carried out by adopting the system and comprises the following steps:
the camera and the image algorithm server are accessed into the same monitoring intranet;
starting a background management server by an administrator, logging in a background management website, configuring parameters of an image algorithm server, and setting a video stream address of a monitoring camera;
the administrator starts the image storage server from the background management website;
after the camera transmits the monitoring picture to the image storage server, the image storage server inputs the image into a target detection algorithm, detects human bodies and mobile phone targets in the image in real time, and marks position information of the human bodies and the mobile phone targets;
the image storage server judges whether the employee plays the mobile phone or leaves the post according to the position information of the human body and the mobile phone, if the fact that the human body target exceeds a preset time threshold value is not detected on a work station of a certain employee, the employee is judged to be off the post, and if the situation that the mobile phone exceeds a preset time threshold value occurs in a human body frame marked by the certain employee through a target detection algorithm, the employee is judged to have a mobile phone playing behavior;
after detecting the behaviors of the staff playing the mobile phone and leaving the post, the image storage server uploads the result to the background management server, and the background management server records the behaviors and displays the behaviors in a webpage form;
and the manager monitors the working conditions of the staff in real time and in a past period of time through the background management website.
Further, if the human body target is not detected on the work station of a certain employee and exceeds a preset time threshold, the employee is judged to be off duty, and the method comprises the following steps:
when the algorithm detects that a certain frame has abnormal behaviors, timing is started, the next frame is detected, when the abnormal behaviors are not detected in the certain frame, timing is not immediately ended, but is ended when the abnormal behaviors do not exist in N continuous frames, and whether the abnormal behaviors are real or not is judged according to whether the duration time of the abnormal behaviors exceeds a preset time threshold or not.
Further, the target detection algorithm detects human body and mobile phone targets in the image and marks the position information of the human body and the mobile phone targets, and comprises the following steps:
the camera is accessed to the network through a real-time streaming protocol (RTSP), and a video stream processing thread directly reads a video stream from the monitoring network and transmits the video stream to a Yolov5 target detection network after processing. The video stream processing thread consists of a write thread and a read thread, wherein the write thread is responsible for reading the monitoring picture and writing the monitoring picture into the queue, and the size of the queue is maintained to be 1 through a producer-consumer mode; the read thread reads the latest frame from the queue, and the frame is preprocessed and then transmitted to a Yolov5 target detection network;
the Yolov5 target detection network obtains the latest frame from the reading line, extracts the image characteristics through the convolutional neural network, and predicts the personnel target position, the mobile phone target position and the corresponding confidence in the frame. Screening is carried out according to the confidence coefficient threshold value, and results with lower confidence coefficients are removed to obtain a preliminary prediction result;
after a Yolov5 target detection network detects a mobile phone target, intercepting the mobile phone target, performing first-round screening by using a Resnet50 secondary classification network, and screening a part of targets with wrong identification;
and (3) carrying out a round of screening on the mobile phone target screened by Resnet50, firstly using Gaussian smooth filtering to eliminate Gaussian noise, then obtaining the edge feature by using a canny edge detection algorithm, and finally detecting the number of straight lines in the edge feature by using a Hough straight line detection algorithm. If the number of lines is less than a predetermined threshold, the objects are further filtered. In the step, non-mobile phone targets with more curves and fewer straight lines can be screened;
and after the final personnel target and the mobile phone target information are obtained, performing off-post judgment and mobile phone playing judgment according to the mutual position information of the personnel target and the mobile phone target. Off-post judgment: if no personnel target is detected on the station, judging that the station is off duty; and (4) judging when playing the mobile phone: if the location center of the mobile phone object is included in the person object, it is determined to play the mobile phone.
By adopting the technical scheme of the invention, the invention has the following beneficial effects: according to the technical scheme, the target detection technology is used for detecting the target information of the human body and the mobile phone, the behavior judgment of leaving the post and playing the mobile phone is obtained according to the mutual position relation of the target information and the mobile phone, and the supervision of a manager is assisted. And the identification detection result is uploaded to a background management server for processing and storage, so that management personnel can conveniently inquire through a webpage:
1. the accuracy is that after a target is detected by using Yolov5, accurate mobile phone target information is obtained through two rounds of screening of Resnet50 and linear detection;
2. the method comprises the steps of real-time performance, namely processing a video stream in a multi-thread mode, and detecting whether the behavior of playing a mobile phone and leaving a post exists in real time;
3. convenience, and the manager accesses the webpage through the browser to acquire the working state of the employee in real time and in a past period of time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a schematic diagram of an overall structure of a mobile phone playing and off-duty detection alarm system based on deep learning according to the present invention;
FIG. 2 is a frame flow chart of a method for playing mobile phones and detecting alarm off duty based on deep learning according to the present invention;
fig. 3 is a flowchart of a target detection algorithm of the method for playing a mobile phone and detecting an alarm off duty based on deep learning according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides a mobile phone playing and off-post detection alarm system based on deep learning.
As shown in fig. 1, in an embodiment of the present invention, the system for monitoring mobile phone playing and off-duty detection and alarm based on deep learning includes monitoring cameras, an image storage server and a background management server, the monitoring cameras are respectively disposed above an office area, the monitoring cameras are used for monitoring behavior of people in the office area, the monitoring cameras are all in data connection with the image storage server, the image storage server is respectively in data connection with the background management server, the image storage server is used for detecting human bodies and mobile phone targets in images, marking position information of the human bodies and the mobile phone targets, determining whether employees are playing mobile phones or off-duty according to the position information of the human bodies and the mobile phones, after detecting the behaviors of the employees playing mobile phones and off-duty, uploading the results to the background management server, the background management server is used for recording the behaviors and displaying the behaviors in real time, and the system alarms to inform an administrator, so that the administrator can monitor the running state of the system and the behavior of the office area staff in real time through a browser.
As shown in fig. 2, the invention further provides a method for playing a mobile phone and detecting off duty and alarming based on deep learning, which is performed by adopting the system and comprises the following steps:
s100: the camera and the image algorithm server are accessed into the same monitoring intranet;
s200: starting a background management server by an administrator, logging in a background management website, configuring parameters of an image algorithm server, and setting a video stream address of a monitoring camera;
s300: the administrator starts the image storage server from the background management website;
s400: after the camera transmits the monitoring picture to the image storage server, the image storage server inputs the image into a target detection algorithm, detects human bodies and mobile phone targets in the image in real time, and marks position information of the human bodies and the mobile phone targets;
s500: the image storage server judges whether the employee plays the mobile phone or leaves the post according to the position information of the human body and the mobile phone, if the fact that the human body target exceeds a preset time threshold value is not detected on a work station of a certain employee, the employee is judged to be off the post, and if the situation that the mobile phone exceeds a preset time threshold value occurs in a human body frame marked by the certain employee through a target detection algorithm, the employee is judged to have a mobile phone playing behavior;
s600: after detecting the behaviors of the employees in playing mobile phones and leaving the post, the image storage server uploads the results to the background management server, and the background management server records the behaviors and displays the behaviors in a webpage mode;
s700: and the manager monitors the working conditions of the staff in real time and in a past period of time through the background management website.
Specifically, a delayed termination mechanism is introduced in consideration of the possibility of misjudgment of the algorithm with a certain probability. When the algorithm detects that a certain frame has abnormal behaviors (playing a mobile phone and leaving the post), timing is started, and the next frame is detected; when the abnormal behavior is not detected in a certain frame, timing is not immediately finished, but is finished when the abnormal behavior does not exist in the continuous N frames; and then, judging whether the abnormal behavior is a real abnormal behavior according to whether the duration time of the abnormal behavior exceeds a preset time threshold. The mechanism is beneficial to increasing the tolerance to the misjudgment rate of the algorithm and improving the detection accuracy.
Specifically, the target detection algorithm comprises two parts of human target detection and mobile phone target detection. Human body target detection and mobile phone target detection are based on a Yolov5 network framework, and monitoring data of different visual angles in multiple scenes are used for manufacturing an original data set for neural network training. Meanwhile, in order to increase the accuracy of mobile phone target detection, after a mobile phone target is detected, secondary screening is performed by using a Resnet50 secondary classification network and a straight line detection method.
Specifically, as shown in fig. 3, the target detection algorithm detects human bodies and mobile phone targets in the images, and labels their position information, including the following steps:
the camera is accessed to the network through a real-time streaming protocol (RTSP), and a video stream processing thread directly reads a video stream from the monitoring network and transmits the video stream to a Yolov5 target detection network after processing. The video stream processing thread consists of a write thread and a read thread, wherein the write thread is responsible for reading the monitoring picture and writing the monitoring picture into the queue, and the size of the queue is maintained to be 1 through a producer-consumer mode; the read thread reads the latest frame from the queue, and the frame is transmitted to a Yolov5 target detection network after being preprocessed;
the Yolov5 target detection network obtains the latest frame from the reading line, and the image characteristics are extracted through the convolutional neural network, and the personnel target position, the mobile phone target position and the corresponding confidence coefficient in the frame are predicted. Screening is carried out according to the confidence coefficient threshold value, and results with lower confidence coefficients are removed to obtain a preliminary prediction result;
after a Yolov5 target detection network detects a mobile phone target, intercepting the mobile phone target, performing first-round screening by using a Resnet50 secondary classification network, and screening a part of targets with wrong identification;
and (3) carrying out a round of screening on the mobile phone target screened by Resnet50, firstly using Gaussian smooth filtering to eliminate Gaussian noise, then obtaining the edge feature by using a canny edge detection algorithm, and finally detecting the number of straight lines in the edge feature by using a Hough straight line detection algorithm. If the number of lines is less than a predetermined threshold, the objects are further filtered. In the step, non-mobile phone targets with more curves and fewer straight lines can be screened;
and after the final personnel target and the mobile phone target information are obtained, performing off-post judgment and mobile phone playing judgment according to the mutual position information of the personnel target and the mobile phone target. Off-post judgment: if no personnel target is detected on the station, judging that the station is off duty; and (4) judging when playing the mobile phone: if the position center of the mobile phone target is contained in the personnel target, the mobile phone is judged to be played.
Specifically, the invention utilizes a target detection technology to detect human body and mobile phone target information, obtains behavior judgment of leaving behind and playing the mobile phone according to the mutual position relation of the human body and the mobile phone target information, and assists managers to supervise. Moreover, the identification and detection results are uploaded to a background management server for processing and storage, so that management personnel can conveniently inquire the identification and detection results through a webpage:
1. the accuracy is that after a target is detected by using Yolov5, accurate mobile phone target information is obtained through two rounds of screening of Resnet50 and linear detection;
2. the method comprises the steps of real-time performance, namely processing a video stream in a multi-thread mode, and detecting whether the behavior of playing a mobile phone and leaving a post exists in real time;
3. convenience, and the manager accesses the webpage through the browser to acquire the working state of the employee in real time and in a past period of time.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (4)
1. A mobile phone playing and off-post detection alarm system based on deep learning is characterized by comprising monitoring cameras, an image storage server and a background management server, wherein the monitoring cameras are respectively arranged above an office area and used for monitoring the behavior of personnel in the office area, the monitoring cameras are all in data connection with the image storage server, the image storage server is respectively in data connection with the background management server, the image storage server is used for detecting human bodies and mobile phone targets in images, marking the position information of the human bodies and the mobile phone targets, judging whether employees are playing mobile phones or off-post according to the position information of the human bodies and the mobile phones, uploading the results to the background management server after detecting the behaviors of the employees playing mobile phones and off-post, and the background management server is used for recording the behaviors and displaying the behaviors in real time, and the system alarms to inform an administrator, so that the administrator can monitor the running state of the system and the behavior of the office area staff in real time through a browser.
2. A method for playing mobile phones and detecting and alarming off duty based on deep learning is characterized in that the method is carried out by adopting the system as claimed in claim 1, and comprises the following steps:
the camera and the image algorithm server are accessed into the same monitoring intranet;
starting a background management server by an administrator, logging in a background management website, configuring parameters of an image algorithm server, and setting a video stream address of a monitoring camera;
the administrator starts the image storage server from the background management website;
after the camera transmits the monitoring picture to the image storage server, the image storage server inputs the image into a target detection algorithm, detects human bodies and mobile phone targets in the image in real time, and marks position information of the human bodies and the mobile phone targets;
the image storage server judges whether the employee plays the mobile phone or leaves the post according to the position information of the human body and the mobile phone, if the fact that the human body target exceeds a preset time threshold value is not detected on a work station of a certain employee, the employee is judged to be off the post, and if the situation that the mobile phone exceeds a preset time threshold value occurs in a human body frame marked by the certain employee through a target detection algorithm, the employee is judged to have a mobile phone playing behavior;
after detecting the behaviors of the staff playing the mobile phone and leaving the post, the image storage server uploads the result to the background management server, and the background management server records the behaviors and displays the behaviors in a webpage form;
and the manager monitors the working conditions of the staff in real time and in a past period of time through the background management website.
3. The method for playing mobile phones and detecting and alarming off duty based on deep learning as claimed in claim 2, wherein if the human body target is not detected on the workstation of a certain employee for more than a preset time threshold, then the employee is determined to be off duty, comprising the following steps:
when the algorithm detects that a certain frame has abnormal behaviors, timing is started, the next frame is detected, when the abnormal behaviors are not detected in the certain frame, timing is not immediately ended, but is ended when the abnormal behaviors do not exist in N continuous frames, and whether the abnormal behaviors are real or not is judged according to whether the duration time of the abnormal behaviors exceeds a preset time threshold or not.
4. The method for playing mobile phone and detecting alarm off duty based on deep learning as claimed in claim 2, wherein the target detection algorithm detects human body and mobile phone target in the image and labels their position information, comprising the following steps:
the camera is accessed to the network through a real-time streaming protocol (RTSP), and a video stream processing thread directly reads a video stream from the monitoring network and transmits the video stream to a Yolov5 target detection network after processing. The video stream processing thread consists of a write thread and a read thread, wherein the write thread is responsible for reading the monitoring picture and writing the monitoring picture into the queue, and the size of the queue is maintained to be 1 through a producer-consumer mode; the read thread reads the latest frame from the queue, and the frame is transmitted to a Yolov5 target detection network after being preprocessed;
the Yolov5 target detection network obtains the latest frame from the reading line, extracts the image characteristics through the convolutional neural network, and predicts the personnel target position, the mobile phone target position and the corresponding confidence in the frame. Screening is carried out according to the confidence coefficient threshold value, and results with lower confidence coefficients are removed to obtain a preliminary prediction result;
after a Yolov5 target detection network detects a mobile phone target, intercepting the mobile phone target, performing first-round screening by using a Resnet50 secondary classification network, and screening a part of targets with wrong identification;
and (3) carrying out a round of screening on the mobile phone target screened by Resnet50, firstly using Gaussian smooth filtering to eliminate Gaussian noise, then obtaining the edge feature by using a canny edge detection algorithm, and finally detecting the number of straight lines in the edge feature by using a Hough straight line detection algorithm. If the number of lines is less than a predetermined threshold, the objects are further filtered. In the step, non-mobile phone targets with more curves and fewer straight lines can be screened;
and after the final personnel target and the mobile phone target information are obtained, performing off-post judgment and mobile phone playing judgment according to the mutual position information of the personnel target and the mobile phone target. Off-post judgment: if no personnel target is detected on the station, judging that the station is off duty; and (4) judging when playing the mobile phone: if the position center of the mobile phone target is contained in the personnel target, the mobile phone is judged to be played.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210739096.8A CN115019236B (en) | 2022-06-27 | Deep learning-based mobile phone playing and off-duty detection alarm system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210739096.8A CN115019236B (en) | 2022-06-27 | Deep learning-based mobile phone playing and off-duty detection alarm system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115019236A true CN115019236A (en) | 2022-09-06 |
| CN115019236B CN115019236B (en) | 2024-11-08 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050957A (en) * | 2023-02-23 | 2023-05-02 | 南京未来物联科技有限公司 | Warehouse logistics management system and method combining image identification and personnel positioning |
| CN117253176A (en) * | 2023-11-15 | 2023-12-19 | 江苏海内软件科技有限公司 | Safe production Al intelligent detection method based on video analysis and computer vision |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000172850A (en) * | 1998-12-09 | 2000-06-23 | Canon Inc | Device and method for processing picture |
| CN106936964A (en) * | 2016-12-14 | 2017-07-07 | 浙江大学 | A kind of mobile phone screen angular-point detection method based on Hough transformation template matches |
| CN111191576A (en) * | 2019-12-27 | 2020-05-22 | 长安大学 | Personnel behavior target detection model construction method, intelligent analysis method and system |
| CN111681474A (en) * | 2020-06-17 | 2020-09-18 | 中国银行股份有限公司 | Online live broadcast teaching method and device, computer equipment and readable storage medium |
| CN112634302A (en) * | 2020-12-28 | 2021-04-09 | 航天科技控股集团股份有限公司 | Method for detecting edge of moving end type rectangular object based on deep learning |
| CN112651273A (en) * | 2020-08-21 | 2021-04-13 | 广州市昇博电子科技有限公司 | AI intelligent camera tracking method |
| CN113420693A (en) * | 2021-06-30 | 2021-09-21 | 成都新潮传媒集团有限公司 | Door state detection method and device, and car passenger flow statistical method and equipment |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000172850A (en) * | 1998-12-09 | 2000-06-23 | Canon Inc | Device and method for processing picture |
| CN106936964A (en) * | 2016-12-14 | 2017-07-07 | 浙江大学 | A kind of mobile phone screen angular-point detection method based on Hough transformation template matches |
| CN111191576A (en) * | 2019-12-27 | 2020-05-22 | 长安大学 | Personnel behavior target detection model construction method, intelligent analysis method and system |
| CN111681474A (en) * | 2020-06-17 | 2020-09-18 | 中国银行股份有限公司 | Online live broadcast teaching method and device, computer equipment and readable storage medium |
| CN112651273A (en) * | 2020-08-21 | 2021-04-13 | 广州市昇博电子科技有限公司 | AI intelligent camera tracking method |
| CN112634302A (en) * | 2020-12-28 | 2021-04-09 | 航天科技控股集团股份有限公司 | Method for detecting edge of moving end type rectangular object based on deep learning |
| CN113420693A (en) * | 2021-06-30 | 2021-09-21 | 成都新潮传媒集团有限公司 | Door state detection method and device, and car passenger flow statistical method and equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050957A (en) * | 2023-02-23 | 2023-05-02 | 南京未来物联科技有限公司 | Warehouse logistics management system and method combining image identification and personnel positioning |
| CN117253176A (en) * | 2023-11-15 | 2023-12-19 | 江苏海内软件科技有限公司 | Safe production Al intelligent detection method based on video analysis and computer vision |
| CN117253176B (en) * | 2023-11-15 | 2024-01-26 | 江苏海内软件科技有限公司 | Safe production Al intelligent detection method based on video analysis and computer vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11704936B2 (en) | Object tracking and best shot detection system | |
| CN110390229B (en) | Face picture screening method and device, electronic equipment and storage medium | |
| US20110228984A1 (en) | Systems, methods and articles for video analysis | |
| WO2020094088A1 (en) | Image capturing method, monitoring camera, and monitoring system | |
| US20090212946A1 (en) | System and Method for Detecting an Invalid Camera in Video Surveillance | |
| CN113411542A (en) | Intelligent working condition monitoring equipment | |
| CN112465871B (en) | Evaluation method and system for accuracy of visual tracking algorithm | |
| US20200349360A1 (en) | Population density determination from multi-camera sourced imagery | |
| CN107705326A (en) | A kind of intrusion detection method that crosses the border in security sensitive region | |
| CN112329691A (en) | Monitoring video analysis method and device, electronic equipment and storage medium | |
| CN110781853A (en) | Crowd abnormality detection method and related device | |
| CN111461078A (en) | Anti-fishing monitoring method based on computer vision technology | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN110458144A (en) | Object area intrusion detection method, system, device and readable storage medium storing program for executing | |
| CN111339811A (en) | Image processing method, device, equipment and storage medium | |
| CN115083004A (en) | Identity recognition method and device and computer readable storage medium | |
| CN114359817A (en) | People flow measuring method based on entrance and exit pedestrian identification | |
| CN115019236B (en) | Deep learning-based mobile phone playing and off-duty detection alarm system and method | |
| CN113869115A (en) | Method and system for processing face image | |
| CN113989732A (en) | Real-time monitoring method, system, equipment and readable medium based on deep learning | |
| CN115019236A (en) | Mobile phone playing and off-duty detection alarm system and method based on deep learning | |
| CN108960165A (en) | A kind of stadiums population surveillance method based on intelligent video identification technology | |
| CN112633157A (en) | AGV working area safety real-time detection method and system | |
| CN112883866A (en) | Method, system and storage medium for detecting regional invasion in real time | |
| CN110889326A (en) | Human body detection-based queue-jumping behavior monitoring and warning system, method, device and storage medium |
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 |