Obstacle dodging technical method based on binocular vision

A binocular vision and obstacle avoidance technology, applied in the field of binocular vision obstacle avoidance technology

Pending Publication Date: 2018-07-10
SHANGHAI AWARE INFORMATION TECH +1
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Vision can not only replace a lot of manual work, improve the level of production automation, improve monitoring accuracy, but also an effective solution when many conventional measurement methods cannot be realized

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
  • Obstacle dodging technical method based on binocular vision
  • Obstacle dodging technical method based on binocular vision
  • Obstacle dodging technical method based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039]The present invention utilizes a binocular camera to reconstruct the 3D point cloud of the scene in the forward direction of the tire-type gantry crane on the site in real time, classifies obstacles and noise point clouds through histogram statistical clustering and non-maximum value transplantation, and further separates ground points through ground relocation Cloud and obstacle point cloud, using the least square method to improve the accuracy and robustness of the height and width measurement of the target point cloud, to ensure the accurate detection of long-distance small obstacles; by learning the camera installation attitude and real-time monitoring of the ground point cloud , to achieve real-time monitoring of binocular camera abnormalities and obstacle detection system abnormalities, and improve the reliability of the obstacle avoidance system.

[0040] The present invention will be further described below in conjunction with drawings and embodiments.

[0041] A...

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

According to the invention, real-time three-dimensional point cloud reconstruction of a scene in an advancing direction of a field tyre-type gantry crane is realized by means of a binocular camera. Through performing projection statistics and non-maximum value suppression on the point cloud data in different dimensions, accurate dividing of noise point cloud, ground point cloud and obstacle pointcloud is realized. Through ground repositioning, effect of vibration of the field tyre-type gantry crane in operation to detecting precision and robustness is effectively suppressed, and detecting precision of the obstacle and an obstacle detecting distance are effectively improved. Through leaning a camera gesture and detecting the number and heights of the point cloud, real-time monitoring to abnormity of the obstacle dodging system is realized, and an important meaning is realized for improving harbor automation and harbor safe production.

Description

technical field [0001] The invention relates to a binocular vision real-time field obstacle avoidance technology, in particular to the binocular vision obstacle avoidance technology that can be used for field tire type gantry crane (RTG) obstacle avoidance. Background technique [0002] With the rapid development of economic globalization, the demand for port automation has become more and more urgent, and the rapid collection and distribution of containers is directly related to the throughput of the port. In highly automated port operations, vision technology has played an increasingly important role in the field of port automation in recent years due to its advantages of fast speed, high precision, non-contact, and high degree of automation. Vision can not only replace a lot of manual work, improve the level of production automation, improve monitoring accuracy, but also an effective solution when many conventional measurement methods cannot be realized. [0003] Compare...

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
IPC IPC(8): G06T7/70G06T7/32
CPCG06T2207/20228Y02T90/00
Inventor 孟伟范柘
Owner SHANGHAI AWARE INFORMATION 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