Litcius/Paper detail

ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking

Tara Sadjadpour, Jie Li, Rareş Ambruş, Jeannette Bohg

2023IEEE Robotics and Automation Letters29 citationsDOI

Abstract

Multi-object tracking (MOT) is a cornerstone capability of any robotic system. Tracking quality is largely dependent on the quality of input detections. In many applications, such as autonomous driving, it is preferable to over-detect objects to avoid catastrophic outcomes due to missed detections. As a result, current state-of-the-art 3D detectors produce high rates of false-positives to ensure a low number of false-negatives. This can negatively affect tracking by making data association and track lifecycle management more challenging. Additionally, occasional false-negative detections due to difficult scenarios like occlusions can harm tracking performance. To address these issues in a unified framework, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ShaSTA</i> which learns shape and spatio-temporal affinities between tracks and detections in consecutive frames. The affinity is a probabilistic matching that leads to robust data association, track lifecycle management, false-positive elimination, false-negative propagation, and sequential track confidence refinement. We offer the first self-contained framework that addresses all aspects of the 3D MOT problem. We quantitatively evaluate ShaSTA on the nuScenes tracking benchmark with 5 metrics, including the most common tracking accuracy metric called AMOTA, to demonstrate how ShaSTA may impact the ultimate goal of an autonomous mobile agent. ShaSTA achieves 1st place amongst LiDAR-only trackers that use CenterPoint detections. The open-source code for reproducing and extending our work can be found <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/tsadja/ShaSTA</uri> .

Topics & Concepts

False positive paradoxComputer scienceMetric (unit)Tracking (education)Benchmark (surveying)BitTorrent trackerArtificial intelligenceTracking systemObject (grammar)Data miningComputer visionEye trackingFilter (signal processing)EngineeringOperations managementGeodesyPsychologyGeographyPedagogyVideo Surveillance and Tracking MethodsAutonomous Vehicle Technology and SafetyImpact of Light on Environment and Health
ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking | Litcius