Deep Hierarchical Rear‐Lamp Tracking at Nighttime

Abstract

Rear‐lamp tracking at night is a research topic in night vision that is essential for Advanced Driver Assistance Systems (ADAS). Most current computer vision‐based methods address this problem using color features because rear lamps are lit during night driving. However, such methods are sufficiently robust in complex environments owing to the lack of feature diversity. On the other hand, as there is no off‐the‐shelf dataset, the application of deep learning to nighttime rear‐lamp tracking has been sparsely explored. To tackle the above issues, in this paper, we propose hierarchical rear‐lamp tracking at nighttime (H‐RTN) and create a novel dataset for rear‐lamp tracking. Specifically, the H‐RTN consists of a rough detection hierarchy (R‐hierarchy), an accurate detection hierarchy (A‐hierarchy), and an optimization hierarchy (O‐hierarchy). The R‐hierarchy determines the region of interest (ROI) containing the target rear lamps, the A‐hierarchy samples the rear‐lamp candidates in the ROI, and the O‐hierarchy selects the best pair of candidates as the final location of the target rear lamps. The experimental results show that H‐RTN outperforms the alternative existing methods. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.