PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking (Accepted as an extended abstract in JRDB-ACT Workshop at CVPR21)

TL;DR

This paper introduces PC-DAN, a deep learning approach utilizing PointNet for 3D multi-object tracking using LIDAR point cloud data, aiming to enhance autonomous vehicle perception.

Contribution

It presents a novel PointNet-based deep affinity network specifically designed for 3D multi-object tracking in LIDAR point clouds.

Findings

Demonstrates improved tracking accuracy over existing methods

Effectively preserves 3D structural information in tracking

Shows robustness in complex real-world scenes

Abstract

In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation information into reliable 3D point cloud data, potentially revolutionizing the autonomous vehicles and assistive robotic industry. A point cloud is a dense compilation of spatial data in 3D coordinates. It plays a vital role in modeling complex real-world scenes since it preserves structural information and avoids perspective distortion, unlike image data, which is the projection of a 3D structure on a 2D plane. In order to leverage the intrinsic capabilities of the LIDAR data, we propose a PointNet-based approach for 3D Multi-Object Tracking (MOT).