CN113763683A - Method and device for reminding article leaving and storage medium - Google Patents
Method and device for reminding article leaving and storage medium Download PDFInfo
- Publication number
- CN113763683A CN113763683A CN202111055436.7A CN202111055436A CN113763683A CN 113763683 A CN113763683 A CN 113763683A CN 202111055436 A CN202111055436 A CN 202111055436A CN 113763683 A CN113763683 A CN 113763683A
- Authority
- CN
- China
- Prior art keywords
- article
- message
- reminding
- background server
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a device for reminding article leaving and a storage medium, and belongs to the field of video monitoring. Recording an indoor monitoring video image through a network camera; setting a legacy detection period, an alarm period and continuous hit times; the method comprises the steps of obtaining indoor monitoring video images recorded in the video acquisition step, drawing a designated area in the images as an article left image identification area, periodically detecting the image identification area, sending a hit message if article left is detected, and sending an alarm message if the number of times of sending the hit message reaches the number of continuous hits in an alarm period. The invention can improve the identification accuracy, reduce false alarm, record data and facilitate subsequent backtracking, and improve the processing efficiency and the customer satisfaction.
Description
Technical Field
The present invention relates to the field of video monitoring, and more particularly, to a method, an apparatus, and a storage medium for article leave-behind reminding.
Background
In the prior art, aiming at places such as banks and hotels, the problem of article leaving reminding of customers is mainly solved by checking video monitoring in security or actively checking the site of workers to find whether the problem of article leaving exists or not. The traditional processing flow of human intervention is bound to be low in efficiency, and the low efficiency problem is mainly reflected in that: in advance, whether articles are left or not needs to be manually identified; in fact, after artificial discovery, treatment and intervention are required by executing a plan prepared in advance; after the event, after the processing is finished, no good backtracking, recording and evaluating method exists, and a basis cannot be provided for subsequent similar events. The evaluation of the service quality of the network points by the customers is unsatisfactory, and the improvement of the comprehensive service level of the hall network points is not facilitated.
The invention of China discloses: a detection method and device for left articles in security monitoring are disclosed as follows: CN102063614B, published: 2015-06-03, discloses a method and a device for detecting a left article in security monitoring, comprising the following steps: dividing a scene plane into a plurality of areas; in a certain time interval, performing two-frame background storage and difference calculation on a certain relevant area of the plurality of areas; judging whether a target is left in the relevant area or not according to the difference calculation result, and judging whether the target is a left article or not; if the left-over article exists, extracting the left-over article and giving an alarm; and if no article is left, continuing to monitor other areas. However, the method does not distinguish the staff from the clients, and does not identify whether the left articles belong to the range needing reminding, so that false alarm is caused; the method also does not provide after-the-fact backtracking, has low processing efficiency and can reduce the satisfaction degree of customers.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems of false alarm, no backtracking after events, low processing efficiency and low customer satisfaction existing in the prior art, the invention provides a method, a device and a storage medium for reminding article leaving, which can realize that: the system can automatically sense in advance, intelligently distribute and inform related personnel, thereby greatly reducing the labor amount and improving the working efficiency of network points; performing intelligent analysis in the process, identifying abnormal behavior targets, performing manual secondary audit, and contributing to event accuracy and model optimization; and performing backtracking statistics after the fact, counting the occurrence and processing conditions of daily events, and summarizing the events into a report form to provide data basis for the complaining events and the employee assessment of the network points. Through the intelligent processing capacity of the intelligent video analysis system, personal article loss events of customers can be reduced, the influence of bank brands is improved, customer satisfaction can be improved, and the service quality and the customer stickiness of network points are improved.
2. Technical scheme
The purpose of the invention is realized by the following technical scheme.
A method of item leave alert comprising the steps of:
video acquisition: recording an indoor monitoring video image through a network camera as an input source for image identification;
setting parameters: setting a legacy detection period, an alarm period and continuous hit times;
image recognition: the method comprises the steps of obtaining indoor monitoring video images recorded in the video acquisition step, drawing a designated area in the images as an article left image identification area, and periodically detecting the image identification area, wherein the detection period is a set left detection period, if article left is detected, a hit message is sent, and if the number of times of sending the hit message reaches the continuous hit number in one alarm period, an alarm message is sent.
Further, the specific implementation of the periodic detection includes:
step a: when a person enters an identification area, acquiring person information through face identification, and acquiring a first image of the identification area;
step b: when the person is recognized to leave the recognition area, acquiring a second image of the recognition area;
step c: comparing the first image with the second image, if the articles are excessive, sending a hit message, and identifying the types of the left articles;
step d: and c, repeating the step c by re-acquiring the second image of the identification area at the interval of the remaining detection period.
Further, after the image recognition step, the method further comprises:
after the image recognition step, the method further comprises the following steps:
background server processing: after the background server receives the warning message, whether the personnel are cleaning personnel is judged, whether the type of the left-over article is in the range needing to be reminded is judged, and if the personnel are not the cleaning personnel and the type of the left-over article is in the range needing to be reminded, the warning message is sent to the mobile equipment.
Furthermore, the method for judging whether the personnel is the cleaning personnel by the background server comprises the following steps: the background server stores a staff database which comprises face photos of cleaning staff, and compares the staff information with the face photos of the cleaning staff in the staff database to judge whether the cleaning staff is a cleaning staff.
Furthermore, the method for the background server to judge whether the type of the left-over article is in the range needing reminding includes: setting key articles, identifying and learning whether the left articles belong to the key articles through a modeling machine, and if the left articles belong to the key articles, considering that the article types are in the range needing reminding.
Further, after the background server processing step, the method further comprises:
the background server receives an 'invalid' signal sent by the mobile equipment and sets the state of the reminding message as 'invalid';
the background server receives an effective signal sent by the mobile equipment, sets the state of the reminding message as 'to be processed', and sends the reminding message and the 'to be processed' state to the terminal display equipment;
the background server receives a processed signal sent by the mobile equipment, sets the state of the reminding message as processed, and sends the reminding message and the processed state thereof to the terminal display equipment;
furthermore, each reminding message is stored in the background server, and the occurrence and processing records of the events left by the articles can be checked at any time through the background server; and at the end of each day, the background server summarizes the data on the day, acquires monitoring video clips when abnormal events occur on the day and when the events are solved through the video recorder, and forms a running water and summary report form to be provided for the transportation and management department to inquire.
Furthermore, the background server continuously trains and optimizes the partial video clip input model when the abnormal event occurs and the event is solved.
An article leaving reminding device, characterized in that, the method for realizing the above article leaving reminding comprises:
the video acquisition module is used for acquiring monitoring video images as an input source of the image identification module;
the parameter setting module is used for setting a legacy detection period, an alarm period and continuous hit times;
the image identification module is used for acquiring indoor monitoring video images recorded in the video acquisition step, drawing a designated area in the images as an article left image identification area, periodically detecting the image identification area, sending a hit message if article left is detected, and sending an alarm message if the number of times of sending the hit message reaches the number of continuous hits in one alarm period;
and the background server is used for receiving the alarm message, judging whether the personnel is the cleaning personnel, judging whether the type of the left-over article is in the range needing to be reminded, and sending a reminding message.
A computer-readable storage medium storing a program, wherein the program when executed implements the method for item leaving reminder.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that: the abnormal behavior events of the network points are automatically identified through a video behavior analysis system, so that the working efficiency of the network points is improved; by combining automatic identification with secondary audit of workers, the success rate of event solving is improved, and processing or service quality is prevented from being influenced by the level of personal ability; the video behavior analysis system automatically identifies information such as the starting time, the ending time, the event state, a processing or service person and the like of an event or service, and automatically registers the system; the background flow and report inquiry system provided by the system can facilitate supervision of branch operation management departments and also can provide data basis for network complaint events and employee assessment.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is described in detail below with reference to the drawings and specific examples.
Examples
The embodiment of the invention provides a method for reminding article leaving, the flow of the method is shown in figure 1, and the specific implementation mode is as follows:
video acquisition: recording an indoor monitoring video image through a network camera as an input source for image identification; in this embodiment, a camera supporting the RTSP standard protocol and the h.264 encoding format is adopted, and the maximum resolution is 1080P.
Setting parameters: setting a legacy detection period, an alarm period and continuous hit times; the leave-behind detection period refers to the interval time between the time when the image recognition unit recognizes that the article leave-behind event occurs and the time when the image recognition unit continues to recognize whether the event still exists next time, and the setting can be adjusted according to the actual recognition requirements, so that the best recognition effect is achieved. The alarm period refers to the time difference between the time when the image recognition unit sends the article leaving message and the time when the article leaving still exists and the reminding message is continuously sent next time. The continuous hit number is that a fragment is hit when the article is left, and when the number of hits reaches a specified hit number, the article is considered to be left. The parameters can control the recall ratio and the precision ratio of the detection method, and when the detection is actually carried out, the sending-out requirement of the article leaving event can simultaneously meet the three parameters: setting that a legacy detection period arrives, an alarm period arrives and the continuous hit times are enough, and adjusting parameters according to actual conditions so as to obtain the best detection result.
Image recognition: acquiring an indoor monitoring video image recorded in the video acquisition step, drawing a specified area in the image as an article left image identification area, and then performing the following steps:
step a: when a person enters an identification area, acquiring person information through face identification, and acquiring a first image of the identification area;
step b: when the person is recognized to leave the recognition area, acquiring a second image of the recognition area;
step c: comparing the first image with the second image, if the articles are excessive, sending a hit message, and identifying the types of the left articles;
step d: and c, repeating the step c by re-acquiring the second image of the identification area at the interval of the remaining detection period.
If the number of times of sending the hit message reaches the continuous hit number in a set alarm period, sending the alarm message to a background server, wherein the alarm message comprises: personnel information, type of article left, image of article left.
After the background server receives the warning message, whether the personnel are cleaning personnel is judged, and then whether the type of the left-over article is in the range needing reminding is judged. And if the personnel is not the cleaning personnel and the types of the left-over articles belong to the range needing reminding, sending a reminding message to the mobile equipment. Because the cleaning personnel can temporarily leave articles such as sanitary wares when cleaning in the process, or can move the articles placed to the identification area, if not filter this scene at this moment, then can cause unnecessary wrong report to remind the message and send.
The method for judging whether the personnel is the cleaning personnel comprises the following steps: the background server stores a staff database which comprises face photos of cleaning staff, and compares the staff information with the face photos of the cleaning staff in the staff database to judge whether the cleaning staff is a cleaning staff.
The method for judging whether the type of the left-over article is in the range needing reminding comprises the following steps: key items are set as: the mobile phone, the wallet and the like identify and learn whether the left-over articles are key articles or not through the modeling machine. Does not belong to key objects, and does not need to be reminded. The modeling machine identification learning is the prior art, a model of key articles can be established through the machine learning, and whether the left articles are the key articles or not can be identified through the model. The concrete implementation method for establishing the model of the key articles comprises the following steps:
(1) adding a key object (such as a mobile phone) and uploading a plurality of sample pictures of the key object at the same time, wherein the sample pictures are required to be clear, and the object characteristics in the pictures are pointed clearly;
(2) uploading a large number of learning pictures for machine learning, and storing the learning pictures in a temporary library;
(3) and (3) carrying out validity identification on the learning picture: analyzing all learning pictures, comparing the learning pictures with sample pictures, picking out the pictures for manual confirmation if the difference between the learning pictures and the sample pictures is larger in characteristic difference, deleting invalid pictures, releasing the valid pictures until the picture comparison is completed, storing the pictures into a library to be learned, and deleting the corresponding pictures in a temporary library after the pictures are stored into the library to be learned; the accuracy of identification can be improved through manual confirmation;
(4) machine learning: machine learning is carried out on effective learning pictures, machine learning adopted by the embodiment is the prior art, a left-over article model can be established through the machine learning, pictures after learning can be moved to a modeling completion library, and the corresponding pictures in a library to be learned are deleted.
The background server sends the reminding message to the mobile device, the mobile device is generally held by a hall manager, and when the hall manager receives the reminding message, the hall manager can judge whether the reminding message is effective according to the message content and the actual scene on site. If the message is invalid, the mobile device sends an invalid signal to the background server, and the background sets the state of the reminding message to invalid.
If the message is valid, the mobile device sends a valid signal to the background server, the state of the reminding message is set to be 'pending', and the reminding message and the 'pending' state of the reminding message are sent to the terminal display device, wherein the terminal display device is installed in a management department and used for checking for management personnel. The terminal display equipment displays the text content: "consult room with items left over, pending! ".
The hall manager who holds mobile device is after leaving behind article thing owner, and mobile device sends "handled" signal for backend server, and backend server sets up the state of reminding the message as "handled" to with reminding message and its "handled" state transmission to terminal display device, terminal display device display literal content: and processed, so as to be audited by a manager.
Every reminding message is stored in the background server, and the occurrence and processing records of the events left by the articles can be checked at any time through the background server. And the background server can collect the data of the day at the end of each day, acquire partial video clips when abnormal events occur and the events are solved on the day through the video recorder, and form a running water and collection report so as to be convenient for the management department to inquire.
And inputting the video clips when the events occur and are processed into the model for continuous training and optimization.
The invention and its embodiments have been described above schematically, without limitation, and the invention can be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The representation in the drawings is only one of the embodiments of the invention, the actual construction is not limited thereto, and any reference signs in the claims shall not limit the claims concerned. Therefore, if a person skilled in the art receives the teachings of the present invention, without inventive design, a similar structure and an embodiment to the above technical solution should be covered by the protection scope of the present patent. Furthermore, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Several of the elements recited in the product claims may also be implemented by one element in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (10)
1. A method of item leave reminding, comprising the steps of:
video acquisition: recording an indoor monitoring video image through a network camera as an input source for image identification;
setting parameters: setting a legacy detection period, an alarm period and continuous hit times;
image recognition: the method comprises the steps of obtaining indoor monitoring video images recorded in the video acquisition step, drawing a designated area in the images as an article left image identification area, and periodically detecting the image identification area, wherein the detection period is a set left detection period, if article left is detected, a hit message is sent, and if the number of times of sending the hit message reaches the continuous hit number in one alarm period, an alarm message is sent.
2. The method for reminding of leaving behind an item according to claim 1, wherein the specific implementation of the periodic detection comprises:
step a: when a person enters an identification area, acquiring person information through face identification, and acquiring a first image of the identification area;
step b: when the person is recognized to leave the recognition area, acquiring a second image of the recognition area;
step c: comparing the first image with the second image, if the articles are excessive, sending a hit message, and identifying the types of the left articles;
step d: and c, repeating the step c by re-acquiring the second image of the identification area at the interval of the remaining detection period.
3. The method of claim 1, further comprising, after the step of image recognition:
background server processing: after the background server receives the warning message, whether the personnel are cleaning personnel is judged, whether the type of the left-over article is in the range needing to be reminded is judged, and if the personnel are not the cleaning personnel and the type of the left-over article is in the range needing to be reminded, the warning message is sent to the mobile equipment.
4. The method for reminding the leaving of the article according to claim 3, wherein the method for the background server to judge whether the person is a cleaner comprises the following steps: the background server stores a staff database which comprises face photos of cleaning staff, and compares the staff information with the face photos of the cleaning staff in the staff database to judge whether the cleaning staff is a cleaning staff.
5. The method for reminding the leaving of the article according to claim 3, wherein the method for the background server to judge whether the type of the article left is within the range of reminding is as follows: setting key articles, establishing an identification model through machine learning, identifying whether the left articles belong to the key articles, and if the left articles belong to the key articles, considering that the article types are in a range needing reminding.
6. The method of claim 3, further comprising, after the background server processing step:
the background server receives an 'invalid' signal sent by the mobile equipment and sets the state of the reminding message as 'invalid';
the background server receives an effective signal sent by the mobile equipment, sets the state of the reminding message as 'to be processed', and sends the reminding message and the 'to be processed' state to the terminal display equipment;
the background server receives the processed signal sent by the mobile equipment, sets the state of the reminding message as processed, and sends the reminding message and the processed state thereof to the terminal display equipment.
7. The method for reminding the leaving of the article according to claim 6, wherein each reminding message is stored in the background server, and the occurrence and processing records of the event of leaving the article can be checked at any time through the background server; and at the end of each day, the background server summarizes the data on the day, acquires monitoring video clips when abnormal events occur on the day and when the events are solved through the video recorder, and forms a running water and summary report form to be provided for the transportation and management department to inquire.
8. The method for reminding of leaving behind an item according to claim 7, wherein the background server further continuously trains and optimizes the video images input into the recognition model when the abnormal event occurs and when the event is resolved.
9. An article leave alert device, characterized in that, the method for implementing the article leave alert according to any one of claims 1 to 5, comprises:
the video acquisition module is used for acquiring monitoring video images as an input source of the image identification module;
the parameter setting module is used for setting a legacy detection period, an alarm period and continuous hit times;
the image identification module is used for acquiring indoor monitoring video images recorded in the video acquisition step, drawing a designated area in the images as an article left image identification area, periodically detecting the image identification area, sending a hit message if article left is detected, and sending an alarm message if the number of times of sending the hit message reaches the number of continuous hits in one alarm period;
and the background server is used for receiving the alarm message, judging whether the personnel is the cleaning personnel, judging whether the type of the left-over article is in the range needing to be reminded, and sending a reminding message.
10. A computer-readable storage medium storing a program which, when executed, implements a method of leaving an alert on an item according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111055436.7A CN113763683A (en) | 2021-09-09 | 2021-09-09 | Method and device for reminding article leaving and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111055436.7A CN113763683A (en) | 2021-09-09 | 2021-09-09 | Method and device for reminding article leaving and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113763683A true CN113763683A (en) | 2021-12-07 |
Family
ID=78794311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111055436.7A Pending CN113763683A (en) | 2021-09-09 | 2021-09-09 | Method and device for reminding article leaving and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113763683A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035448A (en) * | 2022-06-09 | 2022-09-09 | 济南银捷实业有限公司 | Protection cabin article retention and on-site unmanned algorithm model training and logic judgment method |
| CN115103155A (en) * | 2022-05-30 | 2022-09-23 | 广州工商学院 | A public video surveillance system based on big data |
| CN115662090A (en) * | 2022-10-21 | 2023-01-31 | 北京云迹科技股份有限公司 | Article loss reminding method and device, electronic equipment and computer readable medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520938A (en) * | 2008-12-31 | 2009-09-02 | 上海序参量科技发展有限公司 | Object identification based reminder for forgotten articles and realization method thereof |
| US20120320199A1 (en) * | 2011-06-06 | 2012-12-20 | Malay Kundu | Notification system and methods for use in retail environments |
| CN105681475A (en) * | 2016-03-31 | 2016-06-15 | 上海上实龙创智慧能源科技股份有限公司 | Internet of things and Internet communication-based left item detection method and device |
| CN107169885A (en) * | 2016-03-08 | 2017-09-15 | 湖南餐启科技有限公司 | A kind of customer's article leaves detection method and system |
| CN207909318U (en) * | 2018-02-07 | 2018-09-25 | 中国石油化工股份有限公司 | Article leaves intelligent detecting prewarning system in a kind of high risk zone |
| CN109243104A (en) * | 2018-06-28 | 2019-01-18 | 平安科技（深圳）有限公司 | Event-handling method and ATM |
| CN111062273A (en) * | 2019-12-02 | 2020-04-24 | 青岛联合创智科技有限公司 | Tracing detection and alarm method for left-over articles |
| CN111415347A (en) * | 2020-03-25 | 2020-07-14 | 上海商汤临港智能科技有限公司 | Legacy object detection method and device and vehicle |
| CN112699769A (en) * | 2020-12-25 | 2021-04-23 | 北京竞业达数码科技股份有限公司 | Detection method and system for left-over articles in security monitoring |
| CN112733611A (en) * | 2020-12-15 | 2021-04-30 | 建信金融科技有限责任公司 | Legacy article detection method and device, electronic equipment and storage medium |
-
2021
- 2021-09-09 CN CN202111055436.7A patent/CN113763683A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520938A (en) * | 2008-12-31 | 2009-09-02 | 上海序参量科技发展有限公司 | Object identification based reminder for forgotten articles and realization method thereof |
| US20120320199A1 (en) * | 2011-06-06 | 2012-12-20 | Malay Kundu | Notification system and methods for use in retail environments |
| CN107169885A (en) * | 2016-03-08 | 2017-09-15 | 湖南餐启科技有限公司 | A kind of customer's article leaves detection method and system |
| CN105681475A (en) * | 2016-03-31 | 2016-06-15 | 上海上实龙创智慧能源科技股份有限公司 | Internet of things and Internet communication-based left item detection method and device |
| CN207909318U (en) * | 2018-02-07 | 2018-09-25 | 中国石油化工股份有限公司 | Article leaves intelligent detecting prewarning system in a kind of high risk zone |
| CN109243104A (en) * | 2018-06-28 | 2019-01-18 | 平安科技（深圳）有限公司 | Event-handling method and ATM |
| CN111062273A (en) * | 2019-12-02 | 2020-04-24 | 青岛联合创智科技有限公司 | Tracing detection and alarm method for left-over articles |
| CN111415347A (en) * | 2020-03-25 | 2020-07-14 | 上海商汤临港智能科技有限公司 | Legacy object detection method and device and vehicle |
| CN112733611A (en) * | 2020-12-15 | 2021-04-30 | 建信金融科技有限责任公司 | Legacy article detection method and device, electronic equipment and storage medium |
| CN112699769A (en) * | 2020-12-25 | 2021-04-23 | 北京竞业达数码科技股份有限公司 | Detection method and system for left-over articles in security monitoring |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115103155A (en) * | 2022-05-30 | 2022-09-23 | 广州工商学院 | A public video surveillance system based on big data |
| WO2023231082A1 (en) * | 2022-05-30 | 2023-12-07 | 广州工商学院 | Public video surveillance system based on big data |
| CN115035448A (en) * | 2022-06-09 | 2022-09-09 | 济南银捷实业有限公司 | Protection cabin article retention and on-site unmanned algorithm model training and logic judgment method |
| CN115662090A (en) * | 2022-10-21 | 2023-01-31 | 北京云迹科技股份有限公司 | Article loss reminding method and device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113763683A (en) | Method and device for reminding article leaving and storage medium | |
| CN110705482A (en) | Personnel behavior alarm prompt system based on video AI intelligent analysis | |
| WO2017117879A1 (en) | Personal identification processing method, apparatus and system | |
| CN202282837U (en) | Video quality diagnosis system | |
| CN109272598A (en) | Substation conventional inspection system based on Bluetooth iBeacon intelligent terminal and method thereof | |
| CN111950470A (en) | A kind of intelligent monitoring method, device, computer equipment and storage medium | |
| CN113239750A (en) | System, method, equipment and application for detecting personnel behaviors in electric power business hall | |
| CN112418091B (en) | Big data-based smart campus security data processing method | |
| CN112672010A (en) | Video generation system based on face recognition | |
| CN116483810A (en) | Data management method based on public security big data processing technical guidelines | |
| CN107920223A (en) | A kind of object behavior detection method and device | |
| CN113869259A (en) | Closed-loop disposal system and disposal method for garbage illegal release event | |
| CN115661732A (en) | Garbage classification and supervision method based on AI intelligent recognition system | |
| CN201876710U (en) | Detection remote supervising system of motor vehicle | |
| CN116385959A (en) | Belt corridor global smoke real-time detection method based on deep learning | |
| CN118400495B (en) | Security monitoring system, method, computer equipment and storage medium | |
| CN111163490A (en) | Method for analyzing household residents based on mobile phone mac | |
| CN114155612A (en) | Restaurant personnel non-standard behavior model training method, detection method and processing equipment | |
| CN114897345A (en) | Method and device for automatically generating index scores based on employee data | |
| CN110019947A (en) | A kind of data extraction method and device | |
| CN114663834B (en) | On-site monitoring method for express storage | |
| CN110060437A (en) | Regional Management System | |
| CN110737697A (en) | Internal control management system of labor arbitration information platform | |
| CN111259799A (en) | A list warning system based on face recognition camera | |
| CN115098708A (en) | Intelligent campus remote supervision system and method based on multimedia technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211207 |
|
| RJ01 | Rejection of invention patent application after publication |