Looking at Vehicles in the Night: Detection and Dynamics of Rear Lights

Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

“…A lot of work for nighttime object detection/recognition has focused on human detection, by using FIR cameras [31], [10] or visible light cameras [18], or a combination of both [5] road traffic objects such as cars [19] and their rear lights [29]. Another group of work is to develop methods robust to illumination changes for robust road area detection [2] and semantic labeling [25].…”

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

“…Several works pertain to human detection at nighttime, using FIR cameras [10,37], visible light cameras [15], or a combination of both [4]. In driving scenarios, a few methods have been proposed to detect cars [17] and vehicles' 1 https://trace.ethz.ch/projects/adverse/GCMA_UIoU rear lights [30]. Contrary to these domain-specific methods, previous work also includes both methods designed for robustness to illumination changes, by employing domaininvariant representations [1,25] or fusing information from complementary modalities and spectra [33], and datasets with adverse illumination [21,29] for localization benchmarking.…”

Infrastructure-free NLoS Obstacle Detection for Autonomous Cars

“…Taillight Detection at Nights. Even though it is statistically more dangerous to drive at night, a survey of the literature suggests that vision based ADAS for night-time driving is less focused on [22], [3]. Instead vision based vehicle detection at day time is covered more broadly [24], [23], [21].…”

“…Instead vision based vehicle detection at day time is covered more broadly [24], [23], [21]. Some taillight detection approaches for vehicles at nights are rule-based [2] and others are learning-based [22]. But both require direct sight of the other vehicle to detect it based on the taillight.…”