Parking space detection method

A detection method and technology for parking spaces, applied in instruments, biological neural network models, computing, etc., can solve problems such as incomplete automation, and achieve the effect of adapting to scene changes and making the algorithm stable and efficient.

Inactive Publication Date: 2019-10-18
TONGJI UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main disadvantage of these methods is that they are not fully automated

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
  • Parking space detection method
  • Parking space detection method
  • Parking space detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] The solution of the present invention is:

[0043] (1) Obtain the input; the input is the bird's-eye view video stream obtained in any form, and the bird's-eye view of the present invention is formed by splicing the fisheye camera video streams around the front, rear, left and right sides of the vehicle through de-distortion and inverse perspective transformation to imitate the top view The non-perspective and distortion-free image can clearly display the surroundings of the vehicle without dead angles, so it is also called the surround view image, hereinafter referred to as the surround view;

[0044] (2) Mark point detection; the input of the present invention is a look around, and mark point detection is performed on the look around image. First divide the look-around image into S*S grids, and then use CNN to extract the features of each grid...

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 parking space detection method. The method comprises the following steps: (1) acquiring information around a vehicle as input; (2) using DMPR-PS to carry out direction mark point detection on the input acquired in the step (1);and (3) realizing parking space inference through the direction marking points obtained in the step (2). Experiments prove that the direction marking points proposed by the algorithm effectively improve the precision and accuracy of parking space judgment, and meet the real-time performance of parking space image analysis in practical application. The method is used as a key step in an automatic parking scene in the field of automatic driving, and an accurate position and a parking entrance of a parking space in a vehicle coordinate system are provided. On the basis of no additional infrastructure, the position of the parking space can be detected by the camera of the vehicle.

Description

technical field [0001] The invention belongs to the field of auxiliary parking for intelligent driving, and relates to a parking space detection method, in particular to a parking space detection method based on visual machine learning. Background technique [0002] The automatic parking system is the last step of autonomous driving and an important part of the unmanned driving system, which has attracted the interest of many researchers. In the process of developing such a system, how to correctly detect and locate parking spaces using in-vehicle sensors is one of the key design issues. Methods to solve this problem fall into two categories: spatial-based free methods and vision-based methods. [0003] Free-space-based methods designate target parking locations by identifying sufficient spaces between adjacent vehicles. Various ranging sensors are used in these methods, such as ultrasonic sensors, laser scanners, short-range radars, etc. However, free-space methods have ...

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): G06K9/00G06N3/04G06K9/62
CPCG06V20/41G06V20/52G06N3/045G06F18/214
Inventor 张林黄君豪
Owner TONGJI UNIV
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