A Lightweight Attention Fusion Module for Multi-sensor 3-D Object Detection

Abstract

With the rapid development of autonomous vehicles, three-dimensional (3D) object detection has become more important, whose purpose is to perceive the size and accurate location of objects in the real world. Many kinds of LiDAR-camera-based 3D object detectors have been developed with two heavy neural networks to extract view-specific features, while a LiDAR-camera-based 3D detector runs very slow about 10 frames per second (FPS). To tackle this issue, this paper first presents an accuracy and efficiency multiple-sensor framework with an early-fusion method to exploit both LiDAR and camera data for fast 3D object detection. Moreover, we also present a lightweight attention fusion module to further improve the performance of our proposed framework. Massive experiments evaluated on the KITTI benchmark suite show that the proposed approach outperforms state-of-the-art LiDAR-camera-based methods on the three classes in 3D performance. Additionally, the proposed model runs at 23 frames per second (FPS), which is almost 2× faster than state-of-the-art fusion methods for LiDAR and camera.