SIRA: Scalable Inter-frame Relation and Association for Radar Perception
This work addresses radar perception for autonomous vehicles, offering incremental improvements in detection and tracking accuracy.
The paper tackles radar perception challenges like low resolution and noise by exploiting temporal feature relations and enforcing spatial motion consistency, achieving 58.11 mAP@0.5 for detection and 47.79 MOTA for tracking on the Radiate dataset, surpassing previous SOTA by +4.11 mAP@0.5 and +9.94 MOTA.
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.