Pointillism: Accurate 3D Bounding Box Estimation with Multi-Radars

Sensys 2020

Authors: Kshitiz Bansal, Keshav Rungta, Siyuan Zhu and Dinesh Bharadia

[Paper] [Video] [Code] [Dataset]


Jul 2022: Open source code for RP-net released. Check it out at github!
Oct 2021: Multi-radar dataset has been released. Check it out at github!


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.

Pointillism data collection platform.

(Top Left) 16- channel Ouster LiDAR, RealSense Depth Camera for ground truth labels. (Top Right) our radars. (Bottom) Our System: Two radars, LiDAR, Depth camera combined synchronously to common clock.


Cite the paper

Kshitiz Bansal, Keshav Rungta, Siyuan Zhu and Dinesh Bharadia†. 2020. Pointillism: Accurate 3D Bounding Box Estimation with Multi-Radars. In The 18th ACM Conference on Embedded Networked Sensor Systems (SenSys ’20), November 16–19, 2020, Virtual Event, Japan. ACM, New York, NY, USA, 14 pages. https://doi.org/10.1145/3384419.3430783

Press cover:

11/20/2020: 10News.com: UC San Diego researchers find ways to make self-driving cars safer

11/17/2020: ScienceDaily and UCSD News: Upgraded radar can enable self-driving cars to see clearly no matter the weather.