Pattern-Aware Data Augmentation for LiDAR 3D Object Detection
This addresses a specific data imbalance issue in autonomous driving datasets, offering an incremental improvement for detecting distant objects.
The paper tackles the problem of performance degradation in LiDAR 3D object detection for distant objects due to data imbalance, and the result is a data augmentation technique that improves PV-RCNN's performance by over 0.7% on the KITTI validation split for cars beyond 25 meters.
Autonomous driving datasets are often skewed and in particular, lack training data for objects at farther distances from the ego vehicle. The imbalance of data causes a performance degradation as the distance of the detected objects increases. In this paper, we propose pattern-aware ground truth sampling, a data augmentation technique that downsamples an object's point cloud based on the LiDAR's characteristics. Specifically, we mimic the natural diverging point pattern variation that occurs for objects at depth to simulate samples at farther distances. Thus, the network has more diverse training examples and can generalize to detecting farther objects more effectively. We evaluate against existing data augmentation techniques that use point removal or perturbation methods and find that our method outperforms all of them. Additionally, we propose using equal element AP bins to evaluate the performance of 3D object detectors across distance. We improve the performance of PV-RCNN on the car class by more than 0.7 percent on the KITTI validation split at distances greater than 25 m.