Real-time overtaking vehicle detection based on optical flow and convolutional neural network

2Citations
Citations of this article
8Readers
Mendeley users who have this article in their library.
Get full text

Abstract

For the development of driver assistance systems, overtaking detection plays an important role in commercial vehicle applications. In this paper, we present a real-time overtaking vehicle detection system using a monocular camera mounted in the rear of a vehicle. It aims to assist the drivers or self-driving cars to perform safe lane change operations. In the proposed method, the possible overtaking vehicles are first located based on motion cues. The candidates are then identified using Convolutional Neural Network (CNN) and tracked for behavior analysis in a short period of time. We present an algorithm to solve the issue of repetitive patterns which is commonly appeared in highway driving. A series of experiments are carried out with real scene video sequences recorded by a dashcam. The objective is to detect other vehicles passing by so as to alert the driver and avoid the potential traffic accidents. The performance evaluation has demonstrated the effectiveness of the proposed technique.

Cite

CITATION STYLE

APA

Wu, L. T., Tran, V. L., & Lin, H. Y. (2019). Real-time overtaking vehicle detection based on optical flow and convolutional neural network. In Communications in Computer and Information Science (Vol. 992, pp. 227–243). Springer Verlag. https://doi.org/10.1007/978-3-030-26633-2_11

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free