Moving target detection and identification method for video monitoring
A moving target, video monitoring technology, applied in character and pattern recognition, neural learning methods, instruments, etc., can solve the problem of not applying a variety of detection backgrounds and detection target general algorithms, to reduce energy consumption, speed, save The effect of computing resources
Pending Publication Date: 2021-12-03
北京神星科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] From the above analysis, it can be seen that the existing target detection and recognition methods do not have a general algorithm suitable for various detection backgrounds and detection targets. Traditional algorithms and deep learning algorithms have their own advantages and disadvantages.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0035] Such as figure 1 Shown, a kind of moving target detection and recognition method for video monitoring, comprises the following steps:
[0036] Step 1, training image target recognition model;
[0037] Step 2, obtain the real-time video stream, and perform image preprocessing;
[0038] Step 3, perform motion perception on the preprocessed image, and detect whether there is a moving target;
[0039] Step 4, using the image target recognition model to i...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a moving target detection and identification method for video monitoring. The method comprises the following steps: training an image target identification model; acquiring a real-time video stream, and performing image preprocessing; performing motion perception on the preprocessed image, and detecting whether a moving target exists or not; recognizing the moving target by using the image target recognition model; in the motion sensing process, adopting a locality sensitive hash algorithm, and obtaining a detection result by comparing locality sensitive hash vectors of two images. According to the method, whether the moving target appears in the monitoring range or not is judged stably and quickly; a target detection deep learning method of the moving target detection and recognition module is high in accuracy and speed, and can be deployed at the front end of a monitoring camera; and motion perception and target detection recognition are separated, so that computing resources can be greatly saved, and energy consumption is reduced.
Description
technical field [0001] The invention belongs to the technical field of video image processing, and in particular relates to a moving target detection and recognition method for video monitoring. Background technique [0002] Due to the high population density and complex social relations in modern society, people have to face more and more emergencies and abnormal events. Almost all public places have the need to deploy surveillance. Faced with massive video data, if you rely entirely on Manual monitoring is time-consuming and labor-intensive. Therefore, video surveillance must be intelligent, replace or assist manual surveillance, and be used to solve practical problems. [0003] The intelligent monitoring system generally uses the camera to shoot, obtain the video stream in real time, and then transmit the video data to the monitoring system processing module. At this time, the module will automatically detect, identify, track, etc. the target in the video, so as to find ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 张勤张勇
Owner 北京神星科技有限公司