Citation

Satzoda RK, Trivedi MM. IEEE Trans. Intel. Transp. Syst. 2019; 20(12): 4297-4307.

Copyright

(Copyright © 2019, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2016.2614545

PMID

unavailable

Abstract

Existing nighttime vehicle detection methods use color as the primary cue for detecting vehicles. However, complex road and ambient lighting conditions, and camera configurations can influence the effectiveness of such explicit rule and threshold-based methods. In this paper, there are three main contributions. First, we present a novel method to detect vehicles during nighttime involving both learned classifiers and explicit rules, which can operate in the presence of varying ambient lighting conditions. The proposed method that is titled as Vehicle Detection using Active-learning during Nighttime (VeDANt) employs a modified form of active learning for training Adaboost classifiers with Haar-like features using gray-level input images. The hypothesis windows are then further verified using the proposed techniques involving perspective geometries and color information of the taillights. Second, VeDANt is extended to analyze the dynamics of the vehicles during nighttime by detecting three taillight activities-braking, turning left, and turning right. Third, we release three new and fully annotated Laboratory for Intelligent and Safe Automobiles-Night data sets with over 5000 frames for evaluation and benchmarking, which capture a variety of complex traffic and lighting conditions. Such comprehensively annotated and complex public data sets are a first in the area of nighttime vehicle detection. We show that VeDANt is able to detect vehicles during nighttime with over 98% accuracy and less than 1% false detections.

Language: en

Keywords

active safety; adaboost classifiers; automobiles; camera configurations; cameras; Cameras; feature extraction; Feature extraction; gray-level input images; Haar transforms; Haar-like features; image classification; Image color analysis; image segmentation; learning (artificial intelligence); Lighting; lighting conditions; machine learning; machine vision; nighttime vehicle detection methods; object detection; rear lights; road safety; Taillight activity analysis; traffic engineering computing; Training; VeDANt; vehicle behavior; vehicle detection using active-learning during nighttime; Vehicle dynamics; Vehicles