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

Stereo matching algorithm based on infrared and visible light images

A technology of stereo matching and infrared images, which is applied in the field of stereo matching algorithms based on infrared and visible light images, and can solve problems such as edge gaps and burrs

Active Publication Date: 2021-04-30
TIANJIN UNIV MARINE TECH RES INST
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most image edge detection algorithms are based on the change of the gray level of each pixel in the image within the field, and detect the edge according to the change rule of the first-order or second-order directional derivative near the edge, but this kind of detection method will Ignore the line edge and the edge information between the line edge and the step edge, causing the detected edge to have gaps or burrs, 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
  • Stereo matching algorithm based on infrared and visible light images
  • Stereo matching algorithm based on infrared and visible light images
  • Stereo matching algorithm based on infrared and visible light images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] For better stereo matching, two cameras are used to build a binocular system. In order to reduce the complexity of calculation, the cameras are kept as horizontal as possible and fixed with a tripod. The left side is a visible light camera, and the right side is an infrared camera. The focal length of the infrared camera is selected as 25mm, and the temperature measurement range is -20°C~+150°C. The focal length of the visible light camera is selected as 18mm~55mm. The overall implementation is as attached figure 1 First, the original images collected by the left and right cameras are continuously down-sampled using the Gaussian image pyramid to obtain images of multiple scales. Next, the matching cost is calculated in multiple scale spaces, and then the segmentation tree structure is used on each layer of the pyramid. Cost aggregation. After the cost of each scale space is aggregated, the cost of multiple scale images is aggregated and constrained, and merged into the...

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 stereo matching algorithm based on infrared and visible light images, and the algorithm comprises the steps: selectively introducing edge detection with stability based on phase consistency, collecting images at the same moment through employing a binocular system with an infrared camera and a visible light camera, carrying out image equalization of left and right images, and obtaining the processed left and right images; using a Gaussian pyramid to generate a multi-scale image, calculating a segmentation tree graph structure of the image in each scale space, creating a sub-tree structure in a segmentation block and a segmentation block tree structure of a whole graph, and according to a relationship aggregation matching cost of tree nodes and leaf nodes, using a WTA (Winner Takes All, winner eat) algorithm to calculate and acquire a final parallax value.

Description

technical field [0001] The invention relates to a stereo matching method, in particular to a stereo matching algorithm based on infrared and visible light images. Background technique [0002] Stereo matching is one of the important steps in computer vision systems. Stereo matching usually consists of four steps: matching cost calculation, cost aggregation, disparity calculation and disparity optimization. Various algorithms with different performance can be produced by using different methods in each step. Generally speaking, they can be divided into two algorithms: local matching and global matching. [0003] The local stereo matching algorithm combines the information of adjacent pixels in the window to calculate the similarity of a single pixel. The amount of extracted information is small, the structure is simple, and the operation efficiency is high. However, it is also sensitive to noise, weak texture, occlusion, and discontinuous disparity. The problem of high fals...

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): G06T7/55G06T7/11G06T5/00G06T5/40G06K9/62
CPCG06T7/55G06T7/11G06T5/40G06F18/22G06T5/90Y02T10/40
Inventor 徐江涛常宇慧史兴萍于子涵路凯歌
Owner TIANJIN UNIV MARINE TECH RES INST