FE-Det: An Effective Traffic Object Detection Framework for Fish-Eye Cameras

Abstract

In the realm of intelligent traffic systems, fisheye cameras have emerged as a pivotal tool, distinguished by their expansive field of view which significantly enhances the surveillance of complex street networks and intersections. However, the inherent distortion characteristics of fisheye lenses, various illumination, tiny objects and confusion of vehicle classes pose significant challenges to conventional image processing and object detection techniques. To address these challenges, we propose an advanced object detection framework named FE-Det specifically designed for fisheye cameras in traffic monitoring systems. This framework integrates detection models optimized for day and night scene variability. Additionally, it incorporates innovative post-processing operations which brings detection enhancement, including a Vehicles Classifier Module for precise vehicle identification, a Static Objects Processing Module for more accurate detection of stationary objects and a Confidence Score Refinement Module to adjust confidence scores for improving the detection of peripheral objects. Experimental evidence substantiates that our framework exhibits a 1.4% improvement in distinguishing between day and night scenes compared to traditional models. Moreover, the application of the proposed post-processing method results in an additional enhancement of 4.1%.