Obstacle pose determination method and device, equipment and medium

A technology of obstacle and pose, which is applied in the field of determination of obstacle pose, can solve problems such as inaccurate estimation of point cloud obstacle pose, influence on pose estimation, and inability to accurately determine obstacle pose information, etc., to achieve The effect of simplifying the determination process, improving accuracy, and avoiding the problem of inaccurate pose estimation

Active Publication Date: 2019-11-05
DEEPBLUE TECH (SHANGHAI) CO LTD
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing lidar obstacle pose estimation algorithm is either integrated in the obstacle detection algorithm, or based on 3D point cloud pose estimation. The former will affect the pose estimation when the obstacle detection is inaccurate, and the latter Or the obstacle pose estimation is inaccurate due to the sparsity of the point cloud
[0004] In summary, none of the existing lidar obstacle pose estimation algorithms can accurately determine the pose information of obstacles

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 pose determination method and device, equipment and medium
  • Obstacle pose determination method and device, equipment and medium
  • Obstacle pose determination method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific implementations of the method, device, equipment and medium for determining the obstacle pose provided by the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0044] Such as figure 1 As shown, the embodiment of the present invention provides a method for determining the pose of an obstacle, including the following steps:

[0045] S101. Acquire a picture containing an obstacle point cloud.

[0046] During the specific implementation, the 3D point cloud data containing obstacles is collected by lidar, and the point cloud data of the road surface is filtered out from the 3D point cloud data, and the obstacle point cloud data is filtered out, and then the obstacle point cloud data is mapped on the bird's-eye view. In the coordinate system of the figure, two-dimensional point cloud data containing obstacles is generated, and based on the two-dimensional point cloud data, a picture containing p...

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 embodiment of the invention discloses an obstacle pose determination method and device, equipment and a medium, which are used for improving the accuracy of the determined obstacle pose. The obstacle pose determination method comprises the steps of obtaining a picture containing obstacle point cloud, inputting the picture into a pre-trained obstacle pose recognition model to obtain an output result, and determining the pose of an obstacle contained in the picture based on the output result of the obstacle pose recognition model.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device, equipment and medium for determining the pose of an obstacle. Background technique [0002] In the vehicle automatic driving scenario, by determining the position and orientation of obstacles on the vehicle's driving road, it can help the vehicle plan a suitable driving route to avoid potential collision risks between the vehicle and the obstacles when driving on the driving road. [0003] However, the existing lidar obstacle pose estimation algorithm is either integrated in the obstacle detection algorithm, or based on 3D point cloud pose estimation. The former will affect the pose estimation when the obstacle detection is inaccurate, and the latter Or the obstacle pose estimation is inaccurate due to the sparsity of the point cloud. [0004] To sum up, none of the existing lidar obstacle pose estimation algorithms can accurately determ...

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): G06K9/00G06K9/62G08G1/16
CPCG08G1/16G06V20/58G06F18/214
Inventor 陈海波
Owner DEEPBLUE TECH (SHANGHAI) CO 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