SIRA: Scalable Inter-frame Relation and Association for Radar Perception

TL;DR

This paper introduces SIRA, a scalable method leveraging extended temporal relations and motion consistency for improved radar perception, achieving state-of-the-art results in object detection and tracking.

Contribution

SIRA innovatively extends temporal relation modeling and enforces motion consistency, enhancing radar perception beyond existing methods.

Findings

Achieves 58.11 mAP@0.5 in object detection

Attains 47.79 MOTA in multi-object tracking

Surpasses previous state-of-the-art by significant margins

Abstract

Conventional radar feature extraction faces limitations due to low spatial resolution, noise, multipath reflection, the presence of ghost targets, and motion blur. Such limitations can be exacerbated by nonlinear object motion, particularly from an ego-centric viewpoint. It becomes evident that to address these challenges, the key lies in exploiting temporal feature relation over an extended horizon and enforcing spatial motion consistency for effective association. To this end, this paper proposes SIRA (Scalable Inter-frame Relation and Association) with two designs. First, inspired by Swin Transformer, we introduce extended temporal relation, generalizing the existing temporal relation layer from two consecutive frames to multiple inter-frames with temporally regrouped window attention for scalability. Second, we propose motion consistency track with the concept of a pseudo-tracklet generated from observational data for better trajectory prediction and subsequent object association. Our approach achieves 58.11 mAP@0.5 for oriented object detection and 47.79 MOTA for multiple object tracking on the Radiate dataset, surpassing previous state-of-the-art by a margin of +4.11 mAP@0.5 and +9.94 MOTA, respectively.