Loading [MathJax]/extensions/tex2jax.js
Intelligent Drivable Area Detection System using Camera and Lidar Sensor for Autonomous Vehicle | IEEE Conference Publication | IEEE Xplore

Intelligent Drivable Area Detection System using Camera and Lidar Sensor for Autonomous Vehicle


Abstract:

Road detection is the most primary and important task for any autonomous vehicles. Nowadays, most of the cars available in the market have camera sensors which assist the...Show More

Abstract:

Road detection is the most primary and important task for any autonomous vehicles. Nowadays, most of the cars available in the market have camera sensors which assist the drivers for safe driving. Therefore, we propose a sensor fusion method by utilizing LiDAR and Camera sensor together to develop a robust drivable road detection system. In this paper, the edge detection and color based segmentation techniques has been used to generate the binary image of lanes from camera sensor images. Then the line models is fitted on the generated binary image using RANSAC algorithm to find the lane marking. But there are many roads in urban area where only one side lane marks are present and sometimes no lane marking at all. In such places, the drivable road detection system wouldn't be able to perform well and doesn't know its boundary for the vehicle to drive. The sensor fused method proposed in this paper utilizes the LiDAR sensor information along with camera images to know its trajectory for safe travel. The algorithm works very well in different road scenarios in an urban area where the road has two lane marks, one side lane with other side curb and finally on both side curbs. The proposed method is tested with two different datasets. The overall results show that the proposed algorithm performs robustly well and the system is able to identify its drivable region accurately.
Date of Conference: 31 July 2020 - 01 August 2020
Date Added to IEEE Xplore: 29 September 2020
ISBN Information:

ISSN Information:

Conference Location: Chicago, IL, USA

I. Introduction

Development of autonomous vehicle is increasing rapidly. Road detection is the most primary and important task for any autonomous vehicles. For a decade, most of the automotive companies has done research in Camera and Radar sensors for tasks such as road detection, object detection, corner detection and so on. Nowadays, most of the cars available in the market have camera sensors and assist the drivers for safe driving. In recent times, many famous car manufacturing companies like GM, Ford, Google, etc. are using LiDAR sensors in their cars and conducting various researches to make use of the sensor. It is because the LiDAR sensor provides a 360° Field Of View (FOV) and provides clear information during low light/night time.

References

References is not available for this document.