RETR: Multi-View Radar Detection Transformer for Indoor Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yataka, Ryoma, Cardace, Adriano, Wang, Pu Perry, Boufounos, Petros, Takahashi, Ryuhei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912192975077376
author Yataka, Ryoma
Cardace, Adriano
Wang, Pu Perry
Boufounos, Petros
Takahashi, Ryuhei
author_facet Yataka, Ryoma
Cardace, Adriano
Wang, Pu Perry
Boufounos, Petros
Takahashi, Ryuhei
contents Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and smoke). However, existing radar perception pipelines fail to account for distinctive characteristics of the multi-view radar setting. In this paper, we propose Radar dEtection TRansformer (RETR), an extension of the popular DETR architecture, tailored for multi-view radar perception. RETR inherits the advantages of DETR, eliminating the need for hand-crafted components for object detection and segmentation in the image plane. More importantly, RETR incorporates carefully designed modifications such as 1) depth-prioritized feature similarity via a tunable positional encoding (TPE); 2) a tri-plane loss from both radar and camera coordinates; and 3) a learnable radar-to-camera transformation via reparameterization, to account for the unique multi-view radar setting. Evaluated on two indoor radar perception datasets, our approach outperforms existing state-of-the-art methods by a margin of 15.38+ AP for object detection and 11.91+ IoU for instance segmentation, respectively. Our implementation is available at https://github.com/merlresearch/radar-detection-transformer.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10293
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RETR: Multi-View Radar Detection Transformer for Indoor Perception
Yataka, Ryoma
Cardace, Adriano
Wang, Pu Perry
Boufounos, Petros
Takahashi, Ryuhei
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Differential Geometry
Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and smoke). However, existing radar perception pipelines fail to account for distinctive characteristics of the multi-view radar setting. In this paper, we propose Radar dEtection TRansformer (RETR), an extension of the popular DETR architecture, tailored for multi-view radar perception. RETR inherits the advantages of DETR, eliminating the need for hand-crafted components for object detection and segmentation in the image plane. More importantly, RETR incorporates carefully designed modifications such as 1) depth-prioritized feature similarity via a tunable positional encoding (TPE); 2) a tri-plane loss from both radar and camera coordinates; and 3) a learnable radar-to-camera transformation via reparameterization, to account for the unique multi-view radar setting. Evaluated on two indoor radar perception datasets, our approach outperforms existing state-of-the-art methods by a margin of 15.38+ AP for object detection and 11.91+ IoU for instance segmentation, respectively. Our implementation is available at https://github.com/merlresearch/radar-detection-transformer.
title RETR: Multi-View Radar Detection Transformer for Indoor Perception
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Differential Geometry
url https://arxiv.org/abs/2411.10293