DepthCN: Vehicle detection using 3D-LIDAR and ConvNet

This paper addresses the problem of vehicle detection using Deep Convolutional Neural Network (ConvNet) and 3D-LIDAR data with application in advanced driver assistance systems and autonomous driving. A vehicle detection system based on the Hypothesis Generation (HG) and Verification (HV) paradigms is proposed. The data inputted to the system is a point cloud obtained from a 3D-LIDAR mounted on board an instrumented vehicle, which is transformed to a Dense-depth Map (DM). The proposed solution starts by removing ground points followed by point cloud segmentation. Then, segmented obstacles (object hypotheses) are projected onto the DM. Bounding boxes are fitted to the segmented objects as vehicle hypotheses (the HG step). Finally, the bounding boxes are used as inputs to a ConvNet to classify/verify the hypotheses of belonging to the category `vehicle' (the HV step). In this paper, we present an evaluation of ConvNet using LIDAR-based DMs and also the impact of domain-specific data augmentation on vehicle detection performance. To train and to evaluate the proposed vehicle detection system, the KITTI Benchmark Suite was used.