Obstacle detection method, device and storage medium

An obstacle detection and obstacle technology, applied in the field of obstacle detection, can solve the problem of low application deployment efficiency, achieve the effect of improving application deployment efficiency and avoiding the training of deep learning models

Active Publication Date: 2021-07-23
知行汽车科技(苏州)股份有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides an obstacle detection method, device and storage medium, which can solve the problem of low application deployment efficiency

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 detection method, device and storage medium
  • Obstacle detection method, device and storage medium
  • Obstacle detection method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following examples are intended to illustrate the present application, but not to limit the scope of the present application.

[0047] figure 1 It is a schematic structural diagram of the obstacle detecting device 100 provided by one embodiment of the present application, such as figure 1 As shown, the apparatus includes at least a control assembly 110 and a laser detecting assembly 120 that is coupled to the control assembly 110.

[0048] The laser detecting assembly 120 is mounted on a moving carrier. The moving carrier refers to a carrier moving on a moving plane in a certain speed. Alternatively, the moving carrier can be a vehicle or a cleaning robot, and the present embodiment does not limit the implementation of the moving carrier.

[0049] Alternatively, the laser detecting assembly 120 can be a laser radar, a stereo camera or a crossing time camera, etc., the present embodiment does not limit the type of device...

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 present application relates to an obstacle detection method, device and storage medium, belonging to the field of computer technology. The method includes: acquiring point cloud data collected by a laser detection component during the movement of a mobile carrier on a moving plane; the point cloud data includes The three-dimensional coordinates and reflection signal strength of the sampling point; take the height direction perpendicular to the moving plane as the projection direction, project the sampling point to the two-dimensional plane according to the three-dimensional coordinates, and obtain a bird's-eye view; determine each pixel in the bird's-eye view according to the point cloud data The pixel information of the point, the pixel information of each pixel point includes the first pixel value, the second pixel value and the third pixel value; according to the pixel information in the bird's-eye view, obstacles within the collection range are detected; it can solve the problem of application deployment efficiency Low problem; by processing huge point cloud data into two-dimensional image data, there is no need to collect a large amount of point cloud data for deep learning model training, improving the efficiency of application deployment.

Description

Technical field [0001] The present application relates to an obstacle detection method, a device, and a storage medium belonging to the technical field of computer. Background technique [0002] With the rapid development of automatic driving technology, the automatic driving system needs to obtain the surrounding obstacle information to achieve safe driving on the road. [0003] The existing obstacle detection method passes the point cloud information of the surrounding environment through the laser radar, and training the key points and characteristics of the extraction point cloud to obtain training samples; learning or depth learning or depth by BP neural network, SVM Methods The model of identifying the obstacle is identified by the model to identify the type of obstacle around the vehicle. [0004] However, machine learning or depth learning models need to consume a large number of computing resources during use, while a large amount of data training is required, and the tr...

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): G06K9/00G01S17/931G01S17/89
CPCG01S17/931G01S17/89G06V20/58
Inventor 王泽荔顾晨益王文爽陈伟
Owner 知行汽车科技(苏州)股份有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap