R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection
This work addresses the problem of LiDAR sensor resolution dependency in 3D object detection for autonomous driving and robotics, offering a solution that maintains performance across different LiDAR sensors.
This paper proposes R-AGNO-RPN, a deep network that fuses LiDAR point clouds and RGB images for 3D object detection, designed to be robust to varying LiDAR point cloud resolutions. The method focuses on object localization rather than refined box estimation, achieving relevant proposal localization even when point cloud data is reduced by 80% of its original points.
Current neural networks-based object detection approaches processing LiDAR point clouds are generally trained from one kind of LiDAR sensors. However, their performances decrease when they are tested with data coming from a different LiDAR sensor than the one used for training, i.e., with a different point cloud resolution. In this paper, R-AGNO-RPN, a region proposal network built on fusion of 3D point clouds and RGB images is proposed for 3D object detection regardless of point cloud resolution. As our approach is designed to be also applied on low point cloud resolutions, the proposed method focuses on object localization instead of estimating refined boxes on reduced data. The resilience to low-resolution point cloud is obtained through image features accurately mapped to Bird's Eye View and a specific data augmentation procedure that improves the contribution of the RGB images. To show the proposed network's ability to deal with different point clouds resolutions, experiments are conducted on both data coming from the KITTI 3D Object Detection and the nuScenes datasets. In addition, to assess its performances, our method is compared to PointPillars, a well-known 3D detection network. Experimental results show that even on point cloud data reduced by $80\%$ of its original points, our method is still able to deliver relevant proposals localization.