The team championed the Road Object Detection in Fish-Eye Cameras category, which witnessed the participation of 403 out of the 726 teams competing in the contest.
The entrants were requested to process image data from an ultra-wide-angle traffic camera lens, including 180-degree and 360-degree observations.
They were challenged to identify objects such as buses, motorbikes, cars, pedestrians, and trucks in these images.
The AI City Challenge was hosted at Conference on Computer Vision and Pattern Recognition (CVPR) 2024, which was held in the US in late June.
The contest focused on harnessing AI to enhance operational efficiency in physical settings such as retail and warehouse environments, and Intelligent Traffic Systems (ITS). It aims to utilise AI for actionable insights from sensor data, such as camera feeds, to improve traffic safety and transportation outcomes.
This year, the challenge highlighted two key areas with significant potential: retail business and ITS. Key areas of interest include multi-camera people tracking, traffic safety analysis, naturalistic driving action recognition, fish-eye camera road object detection, and motorcycle helmet rule violation detection.
