Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis
This work addresses the need for fine-scale risk factor identification in cycling safety using panoramic video, offering practical improvements for researchers and safety analysts, though it is incremental as it builds on existing computer vision models.
The research tackled the problem of detecting and tracking multiple objects in panoramic videos for cycling safety analysis by proposing a novel three-step framework, resulting in a 10.0% decrease in identification switches, a 2.7% improvement in identification precision, and an F-score of 0.82 for overtaking detection.
Cyclists face a disproportionate risk of injury, yet conventional crash records are too sparse to identify risk factors at fine spatial and temporal scales. Recently, naturalistic studies have used video data to capture the complex behavioural and infrastructural risk factors. A promising format is panoramic video, which can record 360$^\circ$ views around a rider. However, its use is limited by distortions, large numbers of small objects, and boundary continuity, which cannot be handled using existing computer vision models. This research proposes a novel three-step framework: (1) enhancing object detection accuracy on panoramic imagery by segmenting and projecting the original 360$^\circ$ images into sub-images; (2) modifying multi-object tracking models to incorporate boundary continuity and object category information; and (3) validating through a real-world application of vehicle overtaking detection. The methodology is evaluated using panoramic videos recorded by cyclists on London's roadways under diverse conditions. Experimental results demonstrate improvements over baselines, achieving higher average precision across varying image resolutions. Moreover, the enhanced tracking approach yields a 10.0% decrease in identification switches and a 2.7% improvement in identification precision. The overtaking detection task achieves a high F-score of 0.82, illustrating the practical effectiveness of the proposed method in real-world cycling safety scenarios.