Pointillism: Accurate 3D bounding box estimation with multi-radars
This addresses the need for reliable autonomous perception in adverse weather conditions for automotive systems, representing a novel method for a known bottleneck.
The paper tackles the problem of poor 3D bounding box estimation from radar point clouds due to specular reflections and sparsity, by introducing Pointillism, a system that combines multiple radars with optimal separation and a novel deep learning architecture, achieving a 15% improvement in accuracy over baseline methods.
Autonomous perception requires high-quality environment sensing in the form of 3D bounding boxes of dynamic objects. The primary sensors used in automotive systems are light-based cameras and LiDARs. However, they are known to fail in adverse weather conditions. Radars can potentially solve this problem as they are barely affected by adverse weather conditions. However, specular reflections of wireless signals cause poor performance of radar point clouds. We introduce Pointillism, a system that combines data from multiple spatially separated radars with an optimal separation to mitigate these problems. We introduce a novel concept of Cross Potential Point Clouds, which uses the spatial diversity induced by multiple radars and solves the problem of noise and sparsity in radar point clouds. Furthermore, we present the design of RP-net, a novel deep learning architecture, designed explicitly for radar's sparse data distribution, to enable accurate 3D bounding box estimation. The spatial techniques designed and proposed in this paper are fundamental to radars point cloud distribution and would benefit other radar sensing applications.