An Optimized Multi-sensor Fused Object Detection Method for Intelligent Vehicles

Abstract

An accurate and efficient environment perception system is crucial for intelligent vehicles. This study proposes an optimized 2D object detection method utilizing multi-sensor fusion to improve the performance of the environment perception system. In the sensor fusion module, a depth completion network is used to predict dense depth map, so both dense and sparse RGB-D images can be obtained. Then, an efficient object detection baseline is optimized for intelligent vehicles. This method is verified by KITTI 2D object detection dataset. The experimental results show that the proposed method can be more accurate than many latest methods on KITTI leaderboard. Meanwhile, this method consumes less inference time and shows its high efficiency.