Unlock instant, AI-driven research and patent intelligence for your innovation.

A parking space scene recognition method based on multi-sensor fusion

A multi-sensor fusion and scene recognition technology, applied in the field of parking space scene recognition based on multi-sensor, can solve the problems of waste of parking space resources and difficulty of accurate identification of parking spaces, and achieve the effect of improving the utilization rate

Active Publication Date: 2019-03-15
JIANGSU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the mainstream of the market is to use a single ultrasonic radar sensor to detect the storage space. In real life, people park more casually and often park their cars crookedly, which brings difficulties to the accurate identification of parking spaces. Misjudgment that the parking space does not meet the parking requirements, resulting in a waste of parking space resources

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
  • A parking space scene recognition method based on multi-sensor fusion
  • A parking space scene recognition method based on multi-sensor fusion
  • A parking space scene recognition method based on multi-sensor fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention is further described below in conjunction with accompanying drawing and implementation example, in the present embodiment, controller adopts Infineon 32-bit TC series single-chip microcomputer, laser radar adopts LMS series, and camera adopts TMS320 series.

[0028] figure 1 Shown is a multi-sensor based parking space scene recognition method flow chart, the method includes the following steps:

[0029] 1) The car enters the mode of looking for vertical parking spaces, starts the right lidar to detect the edge of the parking space, and starts the camera to capture the entire parking space image, wherein the detection direction of the laser radar is perpendicular to the side of the car, and the camera is installed on the top of the car;

[0030] 2) detecting the edge point of the parking space, wherein, the method for detecting the edge point of the parking space comprises the following steps:

[0031] 2.1) When the car is moving forward, every tim...

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 method for identifying a parking lot scene based on multiple-sensor fusion. The method, directed at defects of prior art, comprises the following steps: detecting edge points of a parking lot by using a laser radar, extracting a contour of a parking lot edge by using a parking lot scene photo photographed by a camera, conducting fusion between garage length detected by the laser radar and the contour of the parking lot edge extracted from the photo, determining whether the parking lot meets requirements. According to the invention, the method can further identify the parking lot in more complex scene and increase usage of the parking lot resource.

Description

technical field [0001] The invention belongs to the field of automotive electronics, and in particular relates to a multi-sensor-based parking space scene recognition method. Background technique [0002] With the continuous increase of urban car ownership, parking space resources are becoming more and more tense. At present, the mainstream of the market is to use a single ultrasonic radar sensor to detect the storage space. In real life, people park more casually and often park their cars crookedly, which brings difficulties to the accurate identification of parking spaces. Misjudgment of parking spaces means that the parking requirements are not met, resulting in a waste of parking space resources. Contents of the invention [0003] In order to overcome the shortcomings of the existing technology, the present invention proposes a parking space scene recognition method based on multi-sensor fusion, through the fusion of cameras and lidar multi-sensors, more complex verti...

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): G08G1/14
CPCG08G1/141
Inventor 沈峥楠江浩斌马世典李臣旭
Owner JIANGSU UNIV