HOME / PUBLICATIONS /

A Comparative Study of State-of-the-Art methods for vision-based Obstacle Detection

Citation:

Menacer A, GUEZOULI L, Guezouli L. A Comparative Study of State-of-the-Art methods for vision-based Obstacle Detection, in International Conference on Advances in Communication Technology,Computing and Engineering (ICACTCE) - 2021. ; Forthcoming.

Date Presented:

24 March 2021

Abstract:

Research into vision-based obstacle detection systems plays a fundamental role in developing autonomous vehicles and intelligent transportation systems. In fact, an intelligent vehicle should be ready to discover vehicles and possible obstacles along its route. This paper presents a comparative study of existing state-of-the-art methods for obstacle detection. However, there have been a large number of studies that thoroughly explored various types of state-of-the-art methods for obstacle detection. Here, this paper compares three methods in obstacle detection, namely the “Robust obstacle detection for ADAS using distortions of IPM of a monocular camera”, “Robust Obstacle Detection and Recognition for DAS”, and “Real-time Obstacle Detection Over Rails Using Deep CNN” and analyzes the obtained results. 

Last updated on 02/25/2021