CN113947620A - Design method of overflow management system for stall in market stall based on lineation detection - Google Patents
Design method of overflow management system for stall in market stall based on lineation detection Download PDFInfo
- Publication number
- CN113947620A CN113947620A CN202111233532.6A CN202111233532A CN113947620A CN 113947620 A CN113947620 A CN 113947620A CN 202111233532 A CN202111233532 A CN 202111233532A CN 113947620 A CN113947620 A CN 113947620A
- Authority
- CN
- China
- Prior art keywords
- background
- moving target
- frame
- image
- area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 238000013461 design Methods 0.000 title description 5
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 230000009467 reduction Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims 1
- 238000007726 management method Methods 0.000 description 25
- 239000011159 matrix material Substances 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000026676 system process Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20216—Image averaging
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of urban management and assessment, in particular to a method for designing a management system for overflow of stalls in a market stall based on lineation detection, which comprises the following steps: carrying out scribing operation on the video; step two: carrying out noise reduction and filtering processing on each frame of image of the scribing area video; step three: calculating a background by using an average iterative background method; step four: calculating the difference between the current picture and the background by the background difference so as to obtain a moving target of the area; step five: tracking the moving target by using a Kalman filtering tracking method, and detecting the moving target at a certain moment in a marking area by using an average value iteration background method and a background difference method; step six: automatically capturing and storing the scene photo, triggering an alarm after the moving target exceeds the marking area or stays in the marking area for the alarm time, recording the current time and the street position of the marking frame, and capturing and storing; step seven: and sending and storing the stored scene pictures to the case interface.
Description
Technical Field
The invention relates to the field of urban management and assessment, in particular to a method for designing a management system for overflow of stalls in a market stall based on lineation detection.
Background
In recent years, the urbanization of China is rapidly developed, the urban scale is continuously enlarged, the construction level is gradually improved, the task of guaranteeing the urban healthy operation is increasingly heavy, the requirements for strengthening and improving various urban management measures are increasingly urgent, and the status and the action of urban management work are increasingly prominent. The market stall business management is one of the main businesses of city management, and with the continuous expansion of market scale, the whole process manual management mode does not meet the actual working requirements, and the management measures such as responsibility, red black board, five-family joint guarantee and the like are all emergent to highlight the market stall management requirements.
With the epidemic prevention control level, the market share management enters a normalized prevention and control stage, and in order to further improve the control level of the share and consolidate the epidemic prevention effect, the market share management work of each region is strengthened from the aspects of environmental sanitation, operation order, operation time limit and the like.
Disclosure of Invention
The invention aims to provide a method for designing a management system for the overflow of a stall in a market stall based on lineation detection, which can solve the problems of high difficulty in stall management, difficult evidence collection and weak law enforcement force, such as stall overflow, overtime operation and the like in the management of the market stall.
The purpose of the invention is realized by the following technical scheme:
a method for designing a management system for detecting the overflow of a stall in a market stall based on marking comprises the following steps:
the method comprises the following steps: carrying out scribing operation on the video;
step two: carrying out noise reduction and filtering processing on each frame of image of the scribing area video;
step three: calculating a background by using an average iterative background method;
step four: calculating the difference between the current picture and the background by using a background difference method so as to obtain a moving target of the area;
step five: tracking the moving target by using a Kalman filtering tracking method, and detecting the moving target at a certain moment in a marking area by using an average value iteration background method and a background difference method;
step six: automatically capturing and storing the scene photo, triggering an alarm after the moving target exceeds the marking area or stays in the marking area for the alarm time, recording the current time and the street position of the marking frame, and capturing and storing;
step seven: sending and storing the stored scene pictures to a case interface;
the video marking operation in the first step is to input monitoring data, mark to obtain a coordinate interface, and set a warning line in a functional interface; the control function interface sends a scribing message to the server side, stores the scribing message in the server side and transmits scribing coordinate data into the server side; the server side starts to carry out line crossing behavior detection; if the line crossing behavior is found, the alarm information system is stored and automatically captured, otherwise, the detection is continued; the alarm trigger interface and the database interface are used for triggering variable data, generating and storing alarm information according to a detection result, calling a camera to take pictures of a site and storing the pictures;
the method for calculating the background by the mean value iteration background method comprises the following steps:
if i is the total frame number from the starting point of background calculation to the current frame, f (i) is the background data of the frame i, and Bi is the image data of the frame i, the background frame obtained by the average iterative background method can be represented as:
if f (i-1) is the background data obtained before the current frame and Bi is the image data of the ith frame, the background frame data obtained by the average value iteration background method can be represented as follows:
the method for calculating the difference between the current picture and the background by the background difference method to obtain the moving target of the area comprises the following steps:
setting f (i) as a background obtained by using an average value iterative background method, setting Bt as a current frame image, performing gray subtraction operation on the current frame image and the background image, and taking an absolute value to obtain a differential image, namely a moving target;
diff＝|Bt-f(i)|；
the method for tracking the moving target by using the Kalman filtering tracking method comprises the following steps:
setting X (k) as a system state at the moment k, A as a state transition matrix, B as a control input matrix, U (k) as a control quantity of the system at the moment k, Z (k) as a measurement value at the moment k, H as a system measurement matrix, W (k) as system process noise, Gaussian white noise, covariance as Q, V (k) as measurement noise and Gaussian white noise, and covariance as R;
calculating a predicted value of the k-1-time-based state to the k-time system state:
X(k|k-1)＝AX(k-1|k-1)+BU(k)
calculating the predicted value of the covariance corresponding to X (k | k-1):
P(k|k-1)＝AP(k-1|k-1)AT+Q
and (3) calculation of gain:
Kg(k)＝P(k|k-1)H′/(HP(k|k-1)H′+R)
updating time k:
X(k|k)＝X(k|k-1)+Kg(k)(Z(k)-HX(k|k-1))
P(k|k)＝(I-Kg(k)H)P(k|k-1)。
drawings
The invention is described in further detail below with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a first flowchart of a method for designing a management system for overflow of a stall in a market based on a line drawing test according to the present invention;
FIG. 2 is a block diagram of a second embodiment of a method for overflow management system design in a market stall booth based on scribe detection according to the present invention;
fig. 3 is a flow chart of the present invention for detecting booth overflow using a system design method for detecting booth overflow in a market booth based on scribe detection.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
To explain how to solve the problems of difficult booth management, difficult evidence collection and weak law enforcement force, such as booth overflow, overtime operation and the like, in the market booth management, the following describes in detail the steps and functions of a design method of a system for managing booth overflow in a market booth based on line drawing detection:
a method for designing a management system for overflow of stalls in a market stall based on line drawing detection sequentially comprises the following steps:
the method comprises the following steps: carrying out scribing operation on the video;
step two: carrying out noise reduction and filtering processing on each frame of image of the scribing area video;
step three: calculating a background by using an average iterative background method;
step four: calculating the difference between the current picture and the background by using a background difference method so as to obtain a moving target of the area;
step five: tracking the moving target by using a Kalman filtering tracking method, and detecting the moving target at a certain moment in a marking area by using an average value iteration background method and a background difference method;
step six: automatically capturing and storing the scene photo, triggering an alarm after the moving target exceeds the marking area or stays in the marking area for the alarm time, recording the current time and the street position of the marking frame, and capturing and storing;
step seven: sending and storing the stored scene pictures to a case interface;
the method can analyze the overflow detection of the stall in the market stall through videos; guiding a first-line person of city management to aim at the standardized management scale of the management problem of the market share of the city appearance; the patrol enforcement force and resources are saved for relevant units of government departments; the system realizes automatic law enforcement and evidence collection, provides data support for law enforcement personnel and city management personnel, guides market share management, and promotes reasonable, standard and sanitary development; intelligent application expansion is provided for camera infrastructures such as urban management and municipal administration;
the video marking operation in the first step is to input monitoring data, mark to obtain a coordinate interface, and set a warning line in a functional interface; the control function interface sends a scribing message to the server side, stores the scribing message in the server side and transmits scribing coordinate data into the server side; the server side starts to carry out line crossing behavior detection; if the line crossing behavior is found, the alarm information system is stored and automatically captured, otherwise, the detection is continued; the alarm trigger interface and the database interface are used for triggering variable data, generating and storing alarm information according to a detection result, calling a camera to take pictures of a site and storing the pictures;
the market background is calculated by using an average value iterative background method, the street background is generally unchanged in a market share area video, vehicles of pedestrians and vehicles are staggered from one another, and the unchanged street background can be extracted quickly by using the image characteristic of the average value iterative background method; the influence of the long-time stagnation of the interferents on the background is used for updating the background; the method has the advantages that the simple use of the average background can occupy more processor time in each background updating process, so that the problems of system throughput reduction, real-time picture delay and the like are caused, the new background updating scheme dynamically and continuously calculates the background, and the time consumed by the background calculation of the original scheme is dispersed; the background frame can be quickly calculated only by recording the total frame number from the background calculation starting point to the current frame through a few memories, and the space-time complexity meets the actual requirement.
The method for calculating the background by the mean value iteration background method comprises the following steps:
if i is the total frame number from the starting point of background calculation to the current frame, f (i) is the background data of the frame i, and Bi is the image data of the frame i, the background frame obtained by the average iterative background method can be represented as:
if f (i-1) is the background data obtained before the current frame and Bi is the image data of the ith frame, the background frame data obtained by the average value iteration background method can be represented as follows:
calculating the difference value between the current picture and the background by adopting a background difference method so as to obtain a moving target of the area; in order to detect the moving target in the current frame, only the gray level subtraction operation is needed to be performed on the current frame and the background image, and the absolute value is taken.
The method for calculating the difference between the current picture and the background by the background difference method to obtain the moving target of the area comprises the following steps:
setting f (i) as a background obtained by using an average iterative background method, setting Bt as a current frame image, performing gray subtraction on the current frame image and the background image, and taking an absolute value to obtain a differential image, namely a moving target;
diff＝|Bt-f(i)|；
finally, tracking the moving target by using a Kalman filtering tracking method, detecting the moving target at a certain moment in a market stall area by using an average value iteration background method and a background difference method, wherein in an actual video, the moving target is in continuous motion, and the actual time of the moving target moving in a marking area can be accurately detected only by accurately tracking the target; the Kalman filter is utilized to realize the tracking of the target, and the target can be accurately controlled, so that the tracking triggering alarm is realized.
The method for tracking the moving target by using Kalman filtering comprises the following steps:
setting X (k) as a system state at the moment k, A as a state transition matrix, B as a control input matrix, U (k) as a control quantity of the system at the moment k, Z (k) as a measurement value at the moment k, H as a system measurement matrix, W (k) as system process noise, Gaussian white noise, covariance as Q, V (k) as measurement noise and Gaussian white noise, and covariance as R;
calculating a predicted value of the k-1-time-based state to the k-time system state:
X(k|k-1)＝AX(k-1|k-1)+BU(k)
calculating the predicted value of the covariance corresponding to X (k | k-1):
P(k|k-1)＝AP(k-1|k-1)AT+Q
and (3) calculation of gain:
Kg(k)＝P(k|k-1)H′/(HP(k|k-1)H′+R)
updating time k:
X(k|k)＝X(k|k-1)+Kg(k)(Z(k)-HX(k|k-1))
P(k|k)＝(I-Kg(k)H)P(k|k-1)；
as shown in fig. 2 and 3, automatically capturing and storing the scene photo, triggering the alarm after the moving object exceeds the marking area or stays in the marking area for the alarm time, recording the current time and the street position of the marking frame, and capturing and storing; not only can the region planning be set, but also the staying time in the region can be set, so that the method can be suitable for overflow detection of the stall in the market stall.
Claims (10)
1. A method for designing a management system for overflow of stalls in a market stall based on line drawing detection is characterized by comprising the following steps: the method comprises the following steps in sequence: performing video scribing operation; performing video noise reduction and filtering processing; calculating a background; obtaining a moving target; tracking a moving target; and storing the live photos.
2. The method of claim 1, wherein the method further comprises the step of: the video marking operation is to input monitoring data, mark to obtain a coordinate interface, and set a warning line in the functional interface.
3. The method of claim 1, wherein the method further comprises the step of: the video noise reduction filtering processing is to perform noise reduction filtering processing on each frame of image of the scribing area video.
4. The method of claim 1, wherein the method further comprises the step of: the background was calculated by the mean iterative background method.
5. The method of claim 4, wherein the method further comprises the step of: the method for calculating the background by the mean value iteration background method comprises the following steps:
if i is the total frame number from the starting point of background calculation to the current frame, f (i) is the background data of the frame i, and Bi is the image data of the frame i, the background frame obtained by the average iterative background method can be represented as:
if f (i-1) is the background data obtained before the current frame and Bi is the image data of the ith frame, the background frame data obtained by the average value iteration background method can be represented as follows:
6. the method of claim 1, wherein the method further comprises the step of: the method for obtaining the moving target is to calculate the difference value between the current picture and the background by a background difference method so as to obtain the moving target of the area.
7. The method of claim 6, wherein the method further comprises the step of: the method for calculating the moving target by the background difference method comprises the following steps:
setting f (i) as a background obtained by using an average value iterative background method, setting Bt as a current frame image, performing gray subtraction operation on the current frame image and the background image, and taking an absolute value to obtain a differential image, namely a moving target;
diff＝|Bt-f(i)|。
8. the method of claim 1, wherein the method further comprises the step of: and tracking the moving target by using a Kalman filtering tracking method.
9. The method of claim 1, wherein the method further comprises the step of: and the stored scene picture is that after the moving target exceeds the marking area in the marking area or stays in the marking area for the time of a touch alarm, the alarm is triggered, the current time and the street position of the marking frame are recorded, and the moving target is captured and stored.
10. The method of claim 1, wherein the method further comprises the step of: and sending and storing the stored scene photos to the case interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233532.6A CN113947620A (en) | 2021-10-22 | 2021-10-22 | Design method of overflow management system for stall in market stall based on lineation detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233532.6A CN113947620A (en) | 2021-10-22 | 2021-10-22 | Design method of overflow management system for stall in market stall based on lineation detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113947620A true CN113947620A (en) | 2022-01-18 |
Family
ID=79332190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111233532.6A Pending CN113947620A (en) | 2021-10-22 | 2021-10-22 | Design method of overflow management system for stall in market stall based on lineation detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113947620A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222214A (en) * | 2011-05-09 | 2011-10-19 | 苏州易斯康信息科技有限公司 | Fast object recognition algorithm |
| CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
| CN108198206A (en) * | 2017-12-22 | 2018-06-22 | 湖南源信光电科技股份有限公司 | The multi-object tracking method combined based on multiple features combining and Camshift algorithms |
| CN108921083A (en) * | 2018-06-28 | 2018-11-30 | 浙江工业大学 | Illegal flowing street pedlar recognition methods based on deep learning target detection |
| CN111444818A (en) * | 2020-03-24 | 2020-07-24 | 哈尔滨工程大学 | CNN-based market stall violation stall detection method |
| CN113095301A (en) * | 2021-05-21 | 2021-07-09 | 南京甄视智能科技有限公司 | Road occupation operation monitoring method, system and server |
| CN113378659A (en) * | 2021-05-24 | 2021-09-10 | 上海可深信息科技有限公司 | Method for identifying busy operation |
-
2021
- 2021-10-22 CN CN202111233532.6A patent/CN113947620A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222214A (en) * | 2011-05-09 | 2011-10-19 | 苏州易斯康信息科技有限公司 | Fast object recognition algorithm |
| CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
| CN108198206A (en) * | 2017-12-22 | 2018-06-22 | 湖南源信光电科技股份有限公司 | The multi-object tracking method combined based on multiple features combining and Camshift algorithms |
| CN108921083A (en) * | 2018-06-28 | 2018-11-30 | 浙江工业大学 | Illegal flowing street pedlar recognition methods based on deep learning target detection |
| CN111444818A (en) * | 2020-03-24 | 2020-07-24 | 哈尔滨工程大学 | CNN-based market stall violation stall detection method |
| CN113095301A (en) * | 2021-05-21 | 2021-07-09 | 南京甄视智能科技有限公司 | Road occupation operation monitoring method, system and server |
| CN113378659A (en) * | 2021-05-24 | 2021-09-10 | 上海可深信息科技有限公司 | Method for identifying busy operation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Vision-based tower crane tracking for understanding construction activity | |
| KR100995218B1 (en) | A computer-implemented process for creating an enhanced data stream of whiteboard content, system and computer-readable recording medium | |
| CN109977782B (en) | Cross-store operation behavior detection method based on target position information reasoning | |
| CN105791774A (en) | Surveillance video transmission method based on video content analysis | |
| KR100834550B1 (en) | Detecting method at automatic police enforcement system of illegal-stopping and parking vehicle and system thereof | |
| CN111259868B (en) | Reverse vehicle detection method, system and medium based on convolutional neural network | |
| TW201322144A (en) | Apparatus and method for foreground detection | |
| CN106295598A (en) | A kind of across photographic head method for tracking target and device | |
| CN110659546B (en) | Illegal booth detection method and device | |
| KR102579542B1 (en) | Crowd density-based hazardous area automated alert system | |
| KR100820952B1 (en) | Detecting method at automatic police enforcement system of illegal-stopping and parking vehicle using single camera and system thereof | |
| KR20190111585A (en) | Situational recognition system for construction site based vision and method, and method for productivity analysis of earthwork using it | |
| CN111476160A (en) | Loss function optimization method, model training method, target detection method, and medium | |
| CN106504274A (en) | A kind of visual tracking method and system based under infrared camera | |
| CN116434159A (en) | Traffic flow statistics method based on improved YOLO V7 and Deep-Sort | |
| JP2019154027A (en) | Method and device for setting parameter for video monitoring system, and video monitoring system | |
| Zhang et al. | New mixed adaptive detection algorithm for moving target with big data | |
| Tao et al. | Smoky vehicle detection based on range filtering on three orthogonal planes and motion orientation histogram | |
| WO2023173616A1 (en) | Crowd counting method and apparatus, electronic device and storage medium | |
| CN113139434A (en) | City management event processing method and device, electronic equipment and readable storage medium | |
| CN102789645B (en) | Multi-objective fast tracking method for perimeter precaution | |
| CN103425958A (en) | Method for detecting non-movable objects in video | |
| CN113947620A (en) | Design method of overflow management system for stall in market stall based on lineation detection | |
| CN111242010A (en) | Method for judging and identifying identity of litter worker based on edge AI | |
| CN115909140A (en) | Video target segmentation method and system based on high-order video monitoring |
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 |