Evolutionary Rear-Lamp Tracking at Nighttime

Haitian Sun,Chao Zhang,Naidan Zhang,Takumi Nakane

doi:10.1109/access.2021.3087238

Haitian Sun, Chao Zhang + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3087238

Copy DOI

Abstract

Rear-lamp tracking at nighttime plays a momentous role in the advanced driver assistance system (ADAS), involving collision mitigation, automatic cruise control, automatic headlamp dimming, etc. Most of the existing tracking methods based on monocular camera leverage on color features. However, such tracking methods can be easily influenced by background clutter, illumination change, distance variation, and occlusion. In this paper, we propose an evolutionary adaptive rear-lamp tracking method at nighttime, in which a novel genetic algorithm powered by the probabilistic bitwise operation (PBO) is utilized. Also, to improve the robustness against various environments, a balanced fitness function is proposed by taking color information, symmetry, spatial relationship, and rigidity into account. Especially, a series of adaptive thresholds based on rear data in HSV color space is proposed to exploit color information reasonably with respect to our task. A strategy to deal with occlusion is also proposed, which relies on color information and rigidity. Moreover, to our knowledge, there is no publicly available dataset for rear-lamp tracking at nighttime. To fill the gap between the real-world application and the theoretical research, we create a novel dataset, which contains diverse traffic conditions at nighttime. The experimental results indicate that our method outperforms comparative online tracking methods in terms of success rate and center location error.

Highlights

More than half of all traffic deaths occur after dark and a large percentage of road injuries are attributed to lack of clarity of vision at nighttime [1], [2]
We aim to design a rear-lamp tracking system that depends on a single monocular camera, which can be a part of the driving recorder
We propose a novel robust evolutionary rearlamp tracking method at nighttime, which is based on refined genetic algorithm (GA) with a balanced fitness function

Summary

Introduction

More than half of all traffic deaths occur after dark and a large percentage of road injuries are attributed to lack of clarity of vision at nighttime [1], [2]. We propose to automatically track the rear-lamps of the preceding vehicle at nighttime, in order to make contributions to the advanced driving assistance system (ADAS). Our proposed rear-lamp tracking method can be useful for the traffic status understanding (e.g., the status of the brake light or the turn signal light), collision mitigation, automatic cruise control, automatic headlamp dimming, etc. Most existing researches on vehicle tracking or detection have been focused on the daytime environment (e.g., [3]). Tracking or detection at nighttime can be more challenging because of the low-light environment and complex light sources. The scale of rear-lamp regions changes and a variety of light sources appear to include street lamps, traffic lights, the headlight of opposite vehicles, reflection from the ground, etc., which makes the tracking task challenging

Objectives

Methods

Findings

Conclusion