TSBOW: Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions

TL;DR

TSBOW addresses the gap in traffic surveillance benchmarks by providing a large-scale, multi-weather, occlusion-focused dataset derived from CCTV footage. It employs a semi-automatic annotation pipeline and establishes baseline detectors (YOLOv8x, YOLOv11x, YOLOv12x, RT-DETR-x) to evaluate performance across four weather conditions, three road-scale categories, and eight object classes. The work demonstrates that TSBOW’s diversity in weather, occlusion, and viewpoint improves generalization over existing datasets, with YOLOv12x offering robust performance while disasters and heavy snow markedly challenge detection. Beyond object detection, TSBOW supports downstream tasks like counting, speed estimation, and tracking, promising practical impact for intelligent transportation systems and urban traffic management under climate-induced extreme weather.

Abstract

Global warming has intensified the frequency and severity of extreme weather events, which degrade CCTV signal and video quality while disrupting traffic flow, thereby increasing traffic accident rates. Existing datasets, often limited to light haze, rain, and snow, fail to capture extreme weather conditions. To address this gap, this study introduces the Traffic Surveillance Benchmark for Occluded vehicles under various Weather conditions (TSBOW), a comprehensive dataset designed to enhance occluded vehicle detection across diverse annual weather scenarios. Comprising over 32 hours of real-world traffic data from densely populated urban areas, TSBOW includes more than 48,000 manually annotated and 3.2 million semi-labeled frames; bounding boxes spanning eight traffic participant classes from large vehicles to micromobility devices and pedestrians. We establish an object detection benchmark for TSBOW, highlighting challenges posed by occlusions and adverse weather. With its varied road types, scales, and viewpoints, TSBOW serves as a critical resource for advancing Intelligent Transportation Systems. Our findings underscore the potential of CCTV-based traffic monitoring, pave the way for new research and applications. The TSBOW dataset is publicly available at: https://github.com/SKKUAutoLab/TSBOW.

Figures (15)

• Figure 1: Scenes from the TSBOW dataset, comprising 198 videos recorded across four distinct scenarios spanning all seasons (sunny/cloudy, haze/fog, rain, snow) over a year. The dataset emphasizes adverse weather conditions and densely populated urban areas with heavy traffic, addressing significant challenges in image degradation and vehicle occlusion.
• Figure 1: Comparison with other datasets about weather conditions and scales
• Figure 2: Detailed overview of the data collection and annotation pipeline. The process commences with the recording and categorization of videos during the data collection phase. Subsequently, the videos are preprocessed and allocated to a team of annotators for manual labeling. Next, a state-of-the-art model is fine-tuned to automatically annotate the remaining frames. The resulting annotations are then verified against predefined labeling criteria. Finally, the annotated instances are aggregated and undergo post-processing to finalize the dataset.
• Figure 2: Comparison weather conditions and disaster
• Figure 3: Suwon recording locations in TSBOW dataset.