Fast Obstacle Detection Using 3D-to-2D LiDAR Point Cloud Segmentation for Collision-free Path Planning

Whereas many existing computer vision algorithms based on color images work well in robot navigation, most of them are sensitive to illumination and the reflectance of objects. Furthermore, according to the Oren–Nayar reflectance model, the reflectance depends on the material and surface of objects....

Full description

Saved in:
Bibliographic Details
Published in:Sensors and materials 2020-07, Vol.32 (7), p.2365
Main Authors: Lin, Chien-Chou, Mao, Wei-Lung, Chang, Teng-Wen, Chang, Chuan-Yu, Abdullah, Salah Sohaib Saleh
Format: Article
Language:English
Subjects:
Algorithms
Cameras
Cloud computing
Clustering
Collision avoidance
Color imagery
Computer vision
Global positioning systems
GPS
Gyroscopes
Image segmentation
Lidar
Object recognition
Obstacle avoidance
Path planning
Reflectance
Remote monitoring
Robots
Sensors
Three dimensional models
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Whereas many existing computer vision algorithms based on color images work well in robot navigation, most of them are sensitive to illumination and the reflectance of objects. Furthermore, according to the Oren–Nayar reflectance model, the reflectance depends on the material and surface of objects. Therefore, different sensors, passive sensors and active sensors, are used simultaneously to scan objects of different materials. In this paper, an integrated sensor system, including light detection and ranging (LiDAR), global positioning system (GPS), gyroscopes (Gyro), and a camera, is proposed for an autonomous vehicle. The GPS and Gyros are used for locating the robot position and identifying its orientation, which are used for global path planning to move toward a goal. The camera is used for remote video monitoring. LiDAR is used to capture the point clouds of the current environment for use in planning the local path. In this paper, a fast segmentation method is proposed for obstacle detection. The proposed method includes ground point removal, region of interest (ROI) detection, 3D-to-2D projection, and clustering by grids. The purpose of ROI detection is to determine whether the points are candidate obstacle points. The experimental results show that the proposed segmentation method can reduce the size of the point cloud and computation complexity significantly. The integrated multisensor system is expected to be practically used in the field.
ISSN:0914-4935
DOI:10.18494/SAM.2020.2810