Automatic detection method of motor vehicle based on moving target tracking

An automatic detection and motor vehicle technology, applied in the electronic field, can solve problems such as excessive memory occupation, excessive records, and difficult access, and achieve the effect of reducing invalid data and reducing storage space requirements

Inactive Publication Date: 2018-03-27
汕头职业技术学院
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a kind of motor vehicle automatic detection method based on moving target tracking, to solve the problem of too many invalid video records of motor vehicle video in the prior art, difficult to consult, occupying too much memory, etc.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic detection method of motor vehicle based on moving target tracking
  • Automatic detection method of motor vehicle based on moving target tracking
  • Automatic detection method of motor vehicle based on moving target tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1 As shown, a motor vehicle detection method based on moving target tracking includes the following steps:

[0035] Step A1, obtain the video stream: cyclically extract the current frame image in the camera;

[0036] Step A2, video image preprocessing: converting the collected video stream into the required color space for processing, taking into account the noise of the image, and setting the region of interest of the image. Segment the foreground and background, threshold the binary image of the vehicle, and use the corrosion function to further find the binary contour to judge the width (width) and height (height) of the car;

[0037]Step A3, background initialization and update: within a certain period of time, the video image frames are taken for addition operation, the average value is obtained to obtain the background, and the background is updated in real time;

[0038] Step A4, extracting the moving vehicle in the foreground: using the backgrou...

Embodiment 2

[0049] Such as figure 2 Shown, a kind of video automatic video recording method based on detecting whether there is a vehicle of the present invention comprises the following steps:

[0050] Step B1: read the camera;

[0051] Step B2: cyclically extract the current frame image in the camera;

[0052] Step B3: Pass this frame image into the existing car detection function to obtain the number of cars detected in this frame image;

[0053] Step B4: Determine whether a car is detected in the frame image, and if so, trigger the recording function and start recording;

[0054] Step B5: After the recording function is triggered, the recording will continue for a set period of time. At this time, the current frame of the camera will be detected for a car. If a car is detected, the recording will continue until no vehicle appears in the current frame, and the recording will end.

[0055] Since the present invention uses the OpenCV computer vision open source library, in order to c...

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

No PUM Login to view more

Abstract

The invention belongs to the field of electronics, and in particular relates to an automatic detection method of a motor vehicle based on moving target tracking. The method includes the steps of processing an image of a camera, separating the foreground and the background, performing a thresholding processing to obtain a binarized image of a vehicle, searching for a binary contour by a corrosion function to determine the width and height that fit a car, determining whether the car is in the image by operation detection, and if so, triggering a video recording function; and if not, ending the video recording. Compared with the prior art, the method of the invention can only record valid data, records a video when a vehicle passes by and stops recording when no vehicle passes by, and can reduce a large amount of invalid data, reduce storage space requirements and achieve video recording of the car in a more efficient and targeted manner.

Description

technical field [0001] The invention belongs to the field of electronics, and in particular relates to an automatic detection method for motor vehicles based on moving target tracking. Background technique [0002] Car detection video is a method to find cars in the video to be detected or in the camera and feed back the number of cars to trigger the video. In recent years, car detection has received enough attention and attention in the field of computer vision. Due to differences in size, shape, and speed of movement of cars in videos or cameras, there are major changes in the shape of cars. Therefore, car detection has become a research difficulty in the field of computer vision. [0003] Nowadays, there are a lot of motor vehicles, and motor vehicle violations, including criminal investigation, require monitoring of motor vehicles. Too many motor vehicles, cameras and videos have brought a large amount of videos, making it difficult to check and consuming too much manpo...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06T5/00G06T7/11G06T7/194G06T7/254
CPCG06T5/002G06T7/11G06T7/194G06T7/254G06T2207/10016G06T2207/30252G06T2207/20104G06V20/46G06V20/584
Inventor 林哲吴佩君卢泽鸿朱文彬翁仕鹏
Owner 汕头职业技术学院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products