Unlock instant, AI-driven research and patent intelligence for your innovation.

A Binocular Vision Image Edge Detection and Target Tracking Method

An image edge and target tracking technology, applied in the field of image processing, can solve the problems of data loss, inaccurate precision, and broken edges cannot be effectively processed, and achieve the effect of improving accuracy and high reliability

Active Publication Date: 2022-02-11
NANJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, binocular vision is a commonly used method for target detection and tracking technology, but the current technology cannot effectively deal with discontinuous points and broken edges in the detection, and the accuracy of obtaining three-dimensional information from two-dimensional images will be inaccurate. accuracy, data loss, 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
  • A Binocular Vision Image Edge Detection and Target Tracking Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in further detail below in conjunction with accompanying drawing and the practical application that detects in electrified railway catenary power supply line parameter, as figure 1 Shown, the present invention comprises the following steps:

[0021] Step 1: Collect images and shoot them with the left and right line array cameras to obtain a grayscale image including the power supply line. The sensor converts the analog signal into a digital signal to obtain the grayscale value of each pixel in the image.

[0022] Step 2: Perform background subtraction method target detection on the grayscale image collected by the line array camera to obtain the edge information of the power supply line in the image.

[0023] Step 3: If the gray difference between the left and right cameras fails to detect the edge of the power supply line in the image, use the correlation of the left and right cameras in the binocular vision to calculate the poss...

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 discloses a binocular vision image edge detection and target tracking method, comprising the following steps: (1) collecting target images through left and right cameras; (2) performing target edge detection on the images collected by left and right cameras; (3) through The correlation of the target imaged by the left and right cameras complements the edge information of the undetected target; (4) judge whether the completed edge information is reasonable according to the physical properties of the target and the continuity in space; Edge information, to get the physical data of the target. The present invention tracks and infers the undetected target edge to obtain the target edge through the relevance of the imaging of the target in the two cameras in binocular vision, and then further judges according to the continuity of the target in physical space, effectively improving the detection efficiency. accuracy and reliability.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a binocular vision image edge detection and target tracking method. Background technique [0002] Edge detection is a basic problem in image processing and computer vision. Accurately locating the edge of the target is used to extract the features of the target, and data analysis plays an important role. At present, binocular vision is a commonly used method for target detection and tracking technology, but the current technology cannot effectively deal with discontinuous points and broken edges in the detection, and the accuracy of obtaining three-dimensional information from two-dimensional images will be inaccurate. Accuracy, data loss and other issues. The binocular vision target edge detection method proposed in the present invention uses the correlation between the images captured by the two binocular vision cameras to effectively and accurately complement the breakpoints t...

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 Patents(China)
IPC IPC(8): G06T7/13G06T7/80G06T7/70
CPCG06T7/13G06T7/85G06T7/70G06T2207/10012
Inventor 马千里张涛
Owner NANJING UNIV OF POSTS & TELECOMM