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

Method and device for sparse scene flow detection in mobile environment

A mobile environment and scene flow technology, applied in the field of sparse scene flow detection in a mobile environment, can solve the problems of reduced detection accuracy, inability to process data in real time, and difficulty in obtaining scene flow in low-texture areas, so as to improve detection speed and accuracy The effect of efficiency and effectiveness

Active Publication Date: 2019-11-15
ZHEJIANG DAHUA TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present invention provides a sparse scene flow detection method and device in a mobile environment, which is used to solve the problem that the detection process takes a long time and cannot be real-time when detecting a moving target by obtaining a dense scene flow in the prior art. When processing data and performing detection by obtaining sparse scene flow, it is difficult to obtain scene flow in low-texture areas, which will lead to technical problems of reduced detection accuracy

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
  • Method and device for sparse scene flow detection in mobile environment
  • Method and device for sparse scene flow detection in mobile environment
  • Method and device for sparse scene flow detection in mobile environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] In order to solve the above technical problems, the general idea of ​​the technical solution in the embodiment of the present invention is as follows:

[0079] A sparse scene flow detection method and device in a mobile environment. Specifically, a binocular camera is used to collect images in a mobile environment, and the first image and the second image of the current frame and the third image and the third image of the previous frame of the current frame are obtained. A fourth image; based on the first image, the second image, the third image and the fourth image, obtain a first matching point pair set, wherein the first matching point pair set is the same as the first matching point pair set Sparse scene flow correspondence; expanding the first matching point pair set to obtain a second matching point pair set; dividing the second matching point pair set to obtain interior point matching in the second matching point pair set A point pair set and an outer point match...

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 method and device for detecting a sparse scene flow under a mobile environment. The method specifically comprises the steps of acquiring images in the mobile environment through a binocular camera, acquiring a left image and a right image of the current frame and a left image and a right image of the previous frame; acquiring a first matching point pair set correspondingto a first sparse scene flow based on the four images; expanding first matching point pair set, and acquiring a second matching point pair set corresponding to a second sparse scene flow; and acquiring a self-motion scene flow of the binocular camera and a moving target scene flow in the second sparse scene flow. According to the self-motion scene flow of the binocular camera, the pose state and avisual odometer of the binocular camera can be acquired; and according to the moving target scene flow, the moving trajectory of a moving target can be acquired and / or the moving state of the movingtarget can be predicted.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, in particular to a sparse scene flow detection method and device in a mobile environment. Background technique [0002] With the continuous improvement of the performance of software and hardware equipment and the gradual development of artificial intelligence technology, the analysis of static scenes in the traditional fixed state is gradually moving towards the analysis of moving scenes in the mobile state. more and more attention. [0003] Scene flow refers to the three-dimensional scene motion vector of the inherent target in the actual scene, while optical flow refers to the two-dimensional surface motion vector of the projected image of the actual scene, where the optical flow is essentially the projection of the scene flow on the two-dimensional image plane, so the scene flow It can better reflect the essential motion state of the actual target. The introduction of sc...

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): G06T7/80
CPCG06T7/285G06T7/85G06T2200/04
Inventor 陈平张凯卢维潘石柱
Owner ZHEJIANG DAHUA TECH CO LTD