Reversing obstacle automatic detection and early warning method based on binocular vision

An automatic detection and binocular vision technology, which is applied to vehicle parts, instruments, characters and pattern recognition, etc., can solve the problem of mismatching of the area on the left side of the left-eye map, the calculation accuracy of obstacle distance is not high, and the area where the texture of the disparity map is not rich, etc. problems, to achieve the effect of improving accuracy, meeting real-time requirements, and improving accuracy

Inactive Publication Date: 2014-09-03
XIAN UNIV OF TECH
View PDF3 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a method for automatic detection and early warning of reversing obstacles based on binocular vision, which solves the problems of the reversing equipment based on binocular vision in the prior art, the disparity map is susceptible to areas with insufficient texture, and the left side of the left-eye image. Due to the influence of area mismatch, the calculation accuracy of obstacle distance is not high, and the matching speed of binocular disparity map is slow

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
  • Reversing obstacle automatic detection and early warning method based on binocular vision
  • Reversing obstacle automatic detection and early warning method based on binocular vision
  • Reversing obstacle automatic detection and early warning method based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] The automatic detection and early warning method for reversing obstacles based on binocular vision of the present invention is specifically implemented according to the following steps:

[0024] Step 1: Calibrate the binocular camera installed at the rear of the vehicle

[0025] For the binocular camera installed at a certain height in the middle of the rear of the vehicle, measure the physical length of its blind area, denoted as Z min , let the physical height of the lowest obstacle be H min , height less than H min The object is not considered as an obstacle, and the number of inner corners of the checkerboard for calibration is P Q , remember the physical height of the checkerboard is HQ, HQ≤H min ;Measure the physical distance between the binocular camera and the lowest obstacle when the binocular camera just captures the lowe...

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 relates to a reversing obstacle automatic detection and early warning method based on binocular vision. The method comprises steps that: 1), a binocular camera is calibrated; 2), a pavement area without abundant textures is removed from a binocular video frame image pair; 3), the contour at the right eye image is extracted, and cutting amount of a left eye image is determined; 4), a disparity image based on the left eye image is acquired according to the cut left eye image and the complete right eye image; 5), a splicing position of the right eye image is determined according to the disparity image of the left eye image, and the left and right eye images are spliced; 6), a suspected barrier contour and an external rectangle are extracted from the spliced image of the left and right eye images; and 7), pixel height of the suspected obstacle is calculated, the obstacle is screened, a distance to the obstacle is calculated, obstacle and distance marks are made on the spliced image, and grading early warning is realized. The reversing obstacle automatic detection and early warning method has advantages of simple and practical performance and high accuracy.

Description

technical field [0001] The invention belongs to the technical field of automobile intelligent assisted safe driving, and relates to an automatic detection and early warning method for reversing obstacles based on binocular vision. Background technique [0002] Cars are one of the most important means of transportation in the world today. With the increase in the number of cars, people are paying more and more attention to the safety driving assistance technology of vehicles. Reversing is a very important item in car driving. Due to the range of human perspective, There are blind spots in the rearview mirror, misuse by the driver, unskilled novice and other reasons, which can easily lead to the occurrence of reversing accidents. Installing a reversing auxiliary device can effectively reduce the probability of reversing accidents. There are two main types of commonly used reversing auxiliary devices at present: the reversing probe and the reversing image. [0003] The reversi...

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): G06K9/46G06K9/62B60R1/00
Inventor 胡涛贺鹏艳范彩霞景翠宁
Owner XIAN UNIV OF TECH
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