CN111860192A - Moving object identification method and system - Google Patents
Moving object identification method and system Download PDFInfo
- Publication number
- CN111860192A CN111860192A CN202010590265.7A CN202010590265A CN111860192A CN 111860192 A CN111860192 A CN 111860192A CN 202010590265 A CN202010590265 A CN 202010590265A CN 111860192 A CN111860192 A CN 111860192A
- Authority
- CN
- China
- Prior art keywords
- moving object
- image
- time
- pixel
- determining
- 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 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012512 characterization method Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 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
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for identifying a moving object, wherein the method comprises the following steps: acquiring a real-time image of a monitoring area; preprocessing the real-time image to obtain a preprocessed image; marking the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to a time sequence; determining a moving object region according to the image time mark frames of two adjacent frames at a preset time interval; acquiring feature points of the edge contour according to the edge contour of the moving object region; determining a rectangular frame according to the feature points of the edge contour, wherein the feature points are all positioned on the contour of the rectangular frame; and taking the area surrounded by the rectangular frame as the moving object and displaying the rectangular frame on the real-time image. The invention can identify the moving object in the monitoring range in real time, track the moving object in real time, and has less calculation amount, thereby improving the efficiency of identifying the moving object, strong practicability and easy popularization and use.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and a system for identifying a moving object.
Background
In recent years, with the rapid development of the power industry, especially in the stage of entering an extra-high voltage power grid, the construction and development of the power grid are very important, so that intelligent digital safety control is required to be performed on the expansion of a power system, preset maintenance field personnel and machines, wherein the accurate screening of the personnel and machines in a working area is the most urgent requirement.
At present, the security prevention and control screening measures for power grid facilities and operators mainly focus on the following three aspects: (1) based on artificial real-time tracking detection; (2) based on infrared detection; (3) based on laser detection.
The method is mainly based on artificial real-time tracking detection, isolation and warning are mainly carried out according to a plane area, a specially-assigned person is dispatched to carry out monitoring, if the number of field operation surfaces is large, and the number of required operators is large, the real-time monitoring is difficult, and a monitoring blind area is caused.
The method is relatively simple based on the infrared ray detection principle, but has poor precision for multi-direction and multi-angle moving objects, and can not achieve real-time online discrimination of the objects.
The laser detection method is relatively less influenced by external light, but the amount of information acquired from the laser equipment is less, so that the method is less in the field of practical application.
Therefore, based on the above problems, how to find a real-time online monitoring and identifying method has become an urgent technical problem to be solved in the field.
Disclosure of Invention
The embodiment of the invention provides a method and a system for identifying a moving object, which aim to solve the problem that the monitoring and identification of the moving object on site of an electric power system in the prior art cannot be real-time and efficient at the same time.
In a first aspect, a method for identifying a moving object is provided, including:
acquiring a real-time image of a monitoring area;
preprocessing the real-time image to obtain a preprocessed image;
marking the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to a time sequence;
determining a moving object region according to the image time mark frames of two adjacent frames at a preset time interval;
acquiring feature points of the edge contour according to the edge contour of the moving object region, wherein the feature points comprise: the highest point, the lowest point, the leftmost point and the rightmost point;
determining a rectangular frame according to the feature points of the edge contour, wherein the feature points are all positioned on the contour of the rectangular frame;
and taking the area surrounded by the rectangular frame as the moving object and displaying the rectangular frame on the real-time image.
In a second aspect, there is provided an identification system for moving objects, comprising:
the acquisition module is used for acquiring a real-time image of the monitoring area;
the preprocessing module is used for preprocessing the real-time image to obtain a preprocessed image;
the identification module is used for identifying the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to a time sequence;
the first determining module is used for determining a moving object region according to the image time mark frames of two adjacent frames at a preset time interval;
an obtaining module, configured to obtain feature points of an edge contour of the moving object region according to the edge contour, where the feature points include: the highest point, the lowest point, the leftmost point and the rightmost point;
a second determining module, configured to determine a rectangular frame according to feature points of the edge contour, where the feature points are located on a contour of the rectangular frame;
and the display module is used for taking the area surrounded by the rectangular frame as the moving object and displaying the rectangular frame on the real-time image.
Therefore, the embodiment of the invention can identify the moving object in the monitoring range in real time, track the moving object in real time, and has less calculation amount, thereby improving the efficiency of identifying the moving object, strong practicability and easy popularization and use.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a flowchart of an identification method of a moving object according to an embodiment of the present invention;
fig. 2 is a block diagram of a mobile object identification system according to an embodiment of the present invention.
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 some, not all, embodiments of the present invention. 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.
The embodiment of the invention discloses a method for identifying a moving object. As shown in fig. 1, the identification method includes the following steps:
Step S101: and acquiring a real-time image of the monitored area.
Specifically, a high-definition camera is arranged to collect a real-time video of a monitoring area, and the video is enhanced, restored, encoded, compressed and the like to obtain a real-time image. For example, the acquisition range of the camera is set in the field construction area of the power system, and the acquisition range is required to cover the area required to be monitored.
Step S102: and preprocessing the real-time image to obtain a preprocessed image.
Specifically, the pretreatment steps are as follows:
(1) and multiplying the first pixel value of each pixel point of the real-time image by a space conversion function to obtain a second pixel value of each pixel point.
Specifically, g (x, y) ═ f (x, y) × h (x, y). Wherein g (x, y) represents a second pixel value of the pixel point with the coordinate (x, y), f (x, y) represents a first pixel value of the pixel point with the coordinate (x, y), and h (x, y) represents a spatial transfer function of the pixel point with the coordinate (x, y). The spatial transfer function is an empirical value.
(2) And carrying out graying processing on the second pixel value of each pixel point to obtain a preprocessed image.
The graying processing may adopt any graying processing method, such as binarization processing, median filtering processing, and the like.
Step S103: and marking the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to the time sequence.
This step sequences each image frame in chronological order.
Step S104: and determining the moving object region according to the time mark frames of the two adjacent frames of images with the preset time interval.
Specifically, the steps include the following processes:
(1) and calculating to obtain the absolute value of the difference value of the pixel values of each pixel point of the time scale frames of the two adjacent frames of images.
When corresponding target movement occurs in the monitored scene, a relatively obvious difference can occur between two adjacent frames of images, so that a background area and a moving object area can be distinguished by calculating the absolute value of the difference value of pixel values of the two adjacent frames of images, namely Dn(x，y)＝|fn(x，y)-fn-1(x, y) |, wherein Dn(x, y) represents the absolute value of the difference, fn(x, y) represents the pixel value of a pixel point with coordinates (x, y) of the image time stamp frame of the current frame, fn-1(x, y) represents the pixel value of the pixel point with coordinates (x, y) of the image time scale frame of the previous frame of the current frame. It should be understood that when the image is grayed, the pixel values are grayscale values.
(2) And if the absolute value is not less than the preset threshold, determining the pixel point corresponding to the absolute value as the pixel point representing the moving object region.
Specifically, if the absolute value is not less than the preset threshold, the gray value of the pixel point is set to 255, i.e., Rn(x，y)＝(255，Dn(x, y) ≧ T), T represents a preset threshold, fromAnd the pixel point is white, namely foreground. Therefore, the pixel point is a pixel point representing the moving object region.
(3) And if the absolute value is smaller than the preset threshold, determining the pixel point corresponding to the absolute value as the pixel point representing the background.
Specifically, if the absolute value is smaller than the preset threshold, the gray value of the pixel point is set to 0, that is, Rn(x，y)＝(0，Dn(x，y)<T), T represents a preset threshold value, so that the pixel point appears black, i.e. background. Therefore, the pixel is a pixel representing the background.
In addition, the embodiments of the present invention divide the moving objects into two types, the first type is an instantaneous fast moving object or a short-distance moving object, and the second type is a slow moving object or a long-distance moving object. Therefore, the embodiment of the present invention distinguishes which type of moving object region the determined moving object region is by changing the preset time interval.
Specifically, when the preset time interval is 50ms, the determined moving object region is a first-type moving object region, i.e., an instantaneous fast-moving object or a short-distance moving object region.
Specifically, when the preset time interval is 500ms, the determined moving object region is the second type moving object region, i.e., the slow moving object region or the long-distance moving object region.
The instantaneous fast moving object and the slow moving object may have their speed ranges empirically determined. Similarly, the distance ranges may be empirically determined for the regions of short-range moving objects and the regions of long-range moving objects.
Step S105: and acquiring the characteristic points of the edge contour according to the edge contour of the moving object region.
The edge profile of the moving object region can be obtained by existing image algorithms, for example, the Roberts edge detection algorithm. By which the edge profile of the moving object region can be determined. Each pixel point of the edge profile can be determined by the edge profile. The feature points are pixel points of the edge profile which can represent the edge profile features. The characteristic points of the embodiment of the invention comprise: the highest point, the lowest point, the leftmost point and the rightmost point can be determined by comparing the coordinates of each pixel point of the edge contour of the moving object region.
Step S106: and determining a rectangular frame according to the characteristic points of the edge contour.
The feature points are all located on the outline of the rectangular frame, namely the feature points are used as outline points on four outlines of the rectangular frame, namely the upper outline, the lower outline, the left outline and the right outline.
Step S107: the area surrounded by the rectangular frame is taken as a moving object and the rectangular frame is displayed on the real-time image.
Through the steps, monitoring personnel can track the moving object in real time, and warning is sent to field operation personnel in time according to the change of the rectangular frame.
In summary, the moving object identification method of the embodiment of the invention can identify the moving object in the monitoring range in real time, track the moving object in real time, and has less calculation amount, thereby improving the efficiency of identifying the moving object, strong practicability and easy popularization and use.
The embodiment of the invention also discloses a system for identifying the moving object. As shown in fig. 2, the identification system includes the following modules:
the acquisition module 201 is configured to acquire a real-time image of a monitored area.
The preprocessing module 202 is configured to preprocess the real-time image to obtain a preprocessed image.
And the identifying module 203 is configured to identify the preprocessed image by using a time stamp to obtain a plurality of time stamp frames of the image arranged in time sequence.
The first determining module 204 is configured to determine a moving object region according to two adjacent frames of image time scale frames at a preset time interval.
An obtaining module 205, configured to obtain feature points of an edge contour according to the edge contour of the moving object region.
Wherein, the characteristic point includes: highest point, lowest point, leftmost point and rightmost point.
A second determining module 206, configured to determine a rectangular frame according to the feature points of the edge contour.
Wherein, the characteristic points are all positioned on the outline of the rectangular frame.
And a display module 207 for taking the area surrounded by the rectangular frame as a moving object and displaying the rectangular frame on the real-time image.
The preprocessing module 202 includes:
and the conversion submodule is used for multiplying the first pixel value of each pixel point of the real-time image by the space conversion function to obtain the second pixel value of each pixel point.
And the graying sub-module is used for performing graying processing on the second pixel value of each pixel point to obtain a preprocessed image.
The first determination module 204 includes:
and the calculating submodule is used for calculating and obtaining the absolute value of the difference value of the pixel values of each pixel point of the time scale frames of the two adjacent frames of images.
And the first determining submodule is used for determining the pixel points corresponding to the absolute values as the pixel points representing the moving object region if the absolute values are not smaller than the preset threshold.
And the second determining submodule is used for determining the pixel points corresponding to the absolute values as the pixel points of the characterization background if the absolute values are smaller than the preset threshold.
Specifically, when the preset time interval is 50ms, the determined moving object region is the first type moving object region.
Specifically, when the preset time interval is 500ms, the determined moving object region is the second type moving object region.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
In summary, the moving object identification system of the embodiment of the invention can identify the moving object in the monitoring range in real time and track the moving object in real time, and has less calculation amount, thereby improving the efficiency of identifying the moving object, strong practicability and easy popularization and use.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for identifying a moving object, comprising:
Acquiring a real-time image of a monitoring area;
preprocessing the real-time image to obtain a preprocessed image;
marking the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to a time sequence;
determining a moving object region according to the image time mark frames of two adjacent frames at a preset time interval;
acquiring feature points of the edge contour according to the edge contour of the moving object region, wherein the feature points comprise: the highest point, the lowest point, the leftmost point and the rightmost point;
determining a rectangular frame according to the feature points of the edge contour, wherein the feature points are all positioned on the contour of the rectangular frame;
and taking the area surrounded by the rectangular frame as the moving object and displaying the rectangular frame on the real-time image.
2. The method for identifying moving objects according to claim 1, wherein said step of obtaining the preprocessed image comprises:
multiplying a first pixel value of each pixel point of the real-time image by a space conversion function to obtain a second pixel value of each pixel point;
and carrying out graying processing on the second pixel value of each pixel point to obtain the preprocessed image.
3. The method for identifying a moving object according to claim 2, wherein the step of determining the area of the moving object comprises:
calculating to obtain the absolute value of the difference value of the pixel values of each pixel point of the two adjacent frames of the image time scale frames;
if the absolute value is not smaller than a preset threshold, determining the pixel point corresponding to the absolute value as a pixel point representing the moving object region;
and if the absolute value is smaller than a preset threshold, determining the pixel point corresponding to the absolute value as a pixel point of a characterization background.
4. The moving object identification method according to claim 3, characterized in that: when the preset time interval is 50ms, the determined moving object region is a first class moving object region.
5. The moving object identification method according to claim 3, characterized in that: and when the preset time interval is 500ms, determining the moving object region as a second type moving object region.
6. A system for identifying a moving object, comprising:
the acquisition module is used for acquiring a real-time image of the monitoring area;
the preprocessing module is used for preprocessing the real-time image to obtain a preprocessed image;
The identification module is used for identifying the preprocessed image by adopting a time mark to obtain a plurality of image time mark frames arranged according to a time sequence;
the first determining module is used for determining a moving object region according to the image time mark frames of two adjacent frames at a preset time interval;
an obtaining module, configured to obtain feature points of an edge contour of the moving object region according to the edge contour, where the feature points include: the highest point, the lowest point, the leftmost point and the rightmost point;
a second determining module, configured to determine a rectangular frame according to feature points of the edge contour, where the feature points are located on a contour of the rectangular frame;
and the display module is used for taking the area surrounded by the rectangular frame as the moving object and displaying the rectangular frame on the real-time image.
7. The mobile object identification system of claim 6, wherein the preprocessing module comprises:
the conversion submodule is used for multiplying the first pixel value of each pixel point of the real-time image by a space conversion function to obtain a second pixel value of each pixel point;
and the graying sub-module is used for performing graying processing on the second pixel value of each pixel point to obtain the preprocessed image.
8. The identification system of the moving object according to claim 7, wherein the first determination module comprises:
the calculation submodule is used for calculating and obtaining the absolute value of the difference value of the pixel values of each pixel point of the two adjacent frames of the image time scale frames;
the first determining submodule is used for determining the pixel points corresponding to the absolute values as the pixel points representing the moving object region if the absolute values are not smaller than a preset threshold;
and the second determining submodule is used for determining the pixel points corresponding to the absolute values as the pixel points representing the background if the absolute values are smaller than a preset threshold.
9. The identification system of the moving object according to claim 8, characterized in that: when the preset time interval is 50ms, the determined moving object region is a first class moving object region.
10. The identification system of the moving object according to claim 8, characterized in that: and when the preset time interval is 500ms, determining the moving object region as a second type moving object region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590265.7A CN111860192A (en) | 2020-06-24 | 2020-06-24 | Moving object identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590265.7A CN111860192A (en) | 2020-06-24 | 2020-06-24 | Moving object identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860192A true CN111860192A (en) | 2020-10-30 |
Family
ID=72989479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010590265.7A Pending CN111860192A (en) | 2020-06-24 | 2020-06-24 | Moving object identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860192A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577833A (en) * | 2012-08-01 | 2014-02-12 | 复旦大学 | Abnormal intrusion detection method based on motion template |
| CN104239865A (en) * | 2014-09-16 | 2014-12-24 | 宁波熵联信息技术有限公司 | Pedestrian detecting and tracking method based on multi-stage detection |
| CN104613928A (en) * | 2015-02-09 | 2015-05-13 | 中国人民解放军63863部队 | Automatic tracking and air measurement method for optical pilot balloon theodolite |
| CN107909599A (en) * | 2017-10-24 | 2018-04-13 | 天津大学 | A kind of object detecting and tracking system |
| WO2018082332A1 (en) * | 2016-11-07 | 2018-05-11 | 深圳光启合众科技有限公司 | Image processing method and device, and robot |
| CN108537212A (en) * | 2018-07-04 | 2018-09-14 | 南京邮电大学 | Students ' behavior detection method based on estimation |
| CN109492553A (en) * | 2018-10-25 | 2019-03-19 | 上海理工大学 | A kind of the motion target area rapid extracting method and system of video sequence image |
| CN110246153A (en) * | 2019-04-30 | 2019-09-17 | 安徽四创电子股份有限公司 | A kind of moving target real-time detection tracking based on video monitoring |
| CN110298323A (en) * | 2019-07-02 | 2019-10-01 | 中国科学院自动化研究所 | Detection method of fighting based on video analysis, system, device |
| CN111008621A (en) * | 2020-03-10 | 2020-04-14 | 浙江清鹤科技有限公司 | Object tracking method and device, computer equipment and storage medium |
-
2020
- 2020-06-24 CN CN202010590265.7A patent/CN111860192A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577833A (en) * | 2012-08-01 | 2014-02-12 | 复旦大学 | Abnormal intrusion detection method based on motion template |
| CN104239865A (en) * | 2014-09-16 | 2014-12-24 | 宁波熵联信息技术有限公司 | Pedestrian detecting and tracking method based on multi-stage detection |
| CN104613928A (en) * | 2015-02-09 | 2015-05-13 | 中国人民解放军63863部队 | Automatic tracking and air measurement method for optical pilot balloon theodolite |
| WO2018082332A1 (en) * | 2016-11-07 | 2018-05-11 | 深圳光启合众科技有限公司 | Image processing method and device, and robot |
| CN107909599A (en) * | 2017-10-24 | 2018-04-13 | 天津大学 | A kind of object detecting and tracking system |
| CN108537212A (en) * | 2018-07-04 | 2018-09-14 | 南京邮电大学 | Students ' behavior detection method based on estimation |
| CN109492553A (en) * | 2018-10-25 | 2019-03-19 | 上海理工大学 | A kind of the motion target area rapid extracting method and system of video sequence image |
| CN110246153A (en) * | 2019-04-30 | 2019-09-17 | 安徽四创电子股份有限公司 | A kind of moving target real-time detection tracking based on video monitoring |
| CN110298323A (en) * | 2019-07-02 | 2019-10-01 | 中国科学院自动化研究所 | Detection method of fighting based on video analysis, system, device |
| CN111008621A (en) * | 2020-03-10 | 2020-04-14 | 浙江清鹤科技有限公司 | Object tracking method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 饶俊等: "《计算机图像和视频处理实验教程》", 中国铁道出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| François et al. | Adaptive color background modeling for real-time segmentation of video streams | |
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| CN102663743B (en) | Personage's method for tracing that in a kind of complex scene, many Kameras are collaborative | |
| CN111882816B (en) | Danger alarm method, medium and system for transformer substation | |
| Velastin et al. | A motion-based image processing system for detecting potentially dangerous situations in underground railway stations | |
| RU2009102124A (en) | VIDEO INFORMATION PROCESSING DEVICE FOR ALARM SYSTEM | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN115861236A (en) | Method and device for determining dripping event, storage medium and electronic device | |
| CN103425960A (en) | Method for detecting fast-moving objects in video | |
| CN111860392B (en) | Thermodynamic diagram statistical method based on target detection and foreground detection | |
| CN111860192A (en) | Moving object identification method and system | |
| CN115797411B (en) | Method for online recognition of hydropower station cable bridge deformation by utilizing machine vision | |
| CN112532927A (en) | Intelligent safety management and control system for construction site | |
| CN111582076A (en) | Picture freezing detection method based on pixel motion intelligent perception | |
| Chen et al. | Automatic head detection for passenger flow analysis in bus surveillance videos | |
| JP6831396B2 (en) | Video monitoring device | |
| CN113920535B (en) | Electronic region detection method based on YOLOv5 | |
| CN103714552B (en) | Motion shadow removing method and device and intelligent video analysis system | |
| CN115657021A (en) | Fire detection method for movable robot and movable robot | |
| CN111401276B (en) | Safety helmet wearing identification method and system | |
| CN113869245A (en) | Method and device for identifying safety region | |
| KR20150033047A (en) | Method and Apparatus for Preprocessing Image for Detecting Objects | |
| CN109855534B (en) | Method, system, medium and equipment for judging position of chassis handcart of switch cabinet | |
| CN111881829A (en) | Method and device for detecting personnel and calculating personnel number in public place and monitoring equipment | |
| Maharjan et al. | Automatic Vehicle Detection and Road Traffic Congestion Mapping with Image Processing Technique |
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 |