Obstacle identification method applied to automatic parking

An obstacle recognition and automatic parking technology, applied in the field of automatic driving, can solve problems such as tight resource allocation, affecting parking safety and parking success rate, complex calculation examples, etc., to improve functional experience and avoid low recognition rate , Expand the effect of application scenarios

Pending Publication Date: 2021-08-17
ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The existing automatic parking parking obstacle recognition on the market mainly relies on ultrasonic radar for detection. The problem is that low obstacles cannot be detected, and it is easy to give wrong judgments on parking spaces, which affects parking safety and parking success rate.
Although the existing schemes also try to use machine learning or 2D panorama to identify parking spaces, due to the complexity of the existing deep learning examples, resource allocation will inevitably lead to tension problems; and the existing schemes based on 2D surround view recognition of parking spaces have a low detection rate. and higher false positive rate

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 identification method applied to automatic parking
  • Obstacle identification method applied to automatic parking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0026] The present invention proposes an embodiment of an obstacle recognition method applied to automatic parking, specifically, as figure 1 As shown, the following steps may be included:

[0027] Step S1. Acquiring pictures collected by the four fisheye cameras in real time, and using a distortion algorithm to generate a de-distorted picture.

[0028] In practice, these four pictures can be stored in an array for subsequent feature extraction algorithms. And because the present invention integrates the training and testing...

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 an obstacle recognition method applied to automatic parking. The conception of the method is that multi-dimensional image features are extracted from pictures shot by a fisheye camera, and a plurality of established obstacle types are recognized in combination with a classification algorithm in a machine learning mechanism. According to the method, the problem that the recognition rate of obstacle detection in an existing scheme is low is effectively avoided, the application scene of automatic parking is widened to a certain extent, and the function experience of automatic parking is improved.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to an obstacle recognition method applied to automatic parking. Background technique [0002] The existing automatic parking parking obstacle recognition on the market mainly relies on ultrasonic radar for detection. The problem is that low obstacles cannot be detected, and it is easy to give wrong judgments on parking spaces, which affects parking safety and parking success rate. Although the existing schemes also try to use machine learning or 2D panorama to identify parking spaces, due to the complexity of the existing deep learning examples, resource allocation will inevitably lead to tension problems; and the existing schemes based on 2D surround view recognition of parking spaces have a low detection rate. And the false detection rate is also higher. Contents of the invention [0003] In view of the above, the present invention aims to provide an obstacle recognition method...

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): B60W30/06B60W30/09B60W30/095
CPCB60W30/06B60W30/09B60W30/0956
Inventor 徐瑞雪吴琼李卫兵丁钊李涛
Owner ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD
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