Bidirectional feedback of optimized gaussian mixture model and kernel correlation filter for enhancing simple detection of small pixel vehicles

High-precision detection of vehicle position and contour from unmanned aerial vehicles (UAV) provides critical information for vehicle behavior and traffic flow studies. Vehicles in UAV videos present unique features of small target pixels, which pose challenges in accurate detection. In addition, shaking of UAV camera, shadow of vehicle, and ground sign/marking also lead to difficulties in precise vehicle contour detection. The study proposes a novel approach that designs a bidirectional feedback framework (GKB) between optimized Gaussian mixture model and Kernel correlation filter to enhance vehicle detection. The framework predicts vehicle position based on information of continuous and correlated previous frames to achieve improved performance. We also improve the detection of closely spaced and dark vehicles with morphological algorithms and data processing. The approach is tested on two UAV videos with different shooting heights, illumination conditions, and traffic states. The results show that the proposed method significantly improves vehicle detection. The total accuracy of our model is 98%, which is a 11% improvement over the traditional single detect model and a 4% improvement over the track-after-detect method. Our model’s detection rate of closely spaced and dark vehicles is improved by 15–25% compared to previous methods. Our model’s vehicle contour detection accuracy is over 94%, which is about a 15% improvement over previous methods.