Real-time detection, tracking, and classification of moving and stationary objects using multiple fisheye images - Robotics Institute Carnegie Mellon University

Real-time detection, tracking, and classification of moving and stationary objects using multiple fisheye images

Iljoo Baek, Albert Davies, Geng Yan, and Ragunathan Raj Rajkumar
Conference Paper, Proceedings of IEEE Intelligent Vehicles Symposium (IV '18), pp. 447 - 452, June, 2018

Abstract

The ability to detect pedestrians and other moving objects is crucial for an autonomous vehicle. This must be done in real-time with minimum system overhead. This paper discusses the implementation of a surround view system to identify moving as well as static objects that are close to the ego vehicle. The algorithm works on 4 views captured by fisheye cameras which are merged into a single frame. The moving object detection and tracking solution uses minimal system overhead to isolate regions of interest (ROIs) containing moving objects. These ROIs are then analyzed using a deep neural network (DNN) to categorize the moving object. With deployment and testing on a real car in urban environments, we have demonstrated the practical feasibility of the solution.

BibTeX

@conference{Baek-2018-126190,
author = {Iljoo Baek and Albert Davies and Geng Yan and Ragunathan Raj Rajkumar},
title = {Real-time detection, tracking, and classification of moving and stationary objects using multiple fisheye images},
booktitle = {Proceedings of IEEE Intelligent Vehicles Symposium (IV '18)},
year = {2018},
month = {June},
pages = {447 - 452},
}