Sorry, you need to enable JavaScript to visit this website.

RADAR PERCEPTION WITH SCALABLE CONNECTIVE TEMPORAL RELATIONS FOR AUTONOMOUS DRIVING

DOI:
10.60864/mwf1-rc59
Citation Author(s):
Ryoma Yataka, Pu Wang, Petros Boufounos, Ryuhei Takahashi
Submitted by:
Ryoma Yataka
Last updated:
6 June 2024 - 10:21am
Document Type:
Presentation Slides
Document Year:
2024
Event:
Presenters:
Ryoma Yataka
Paper Code:
SS-L2.3
 

Due to the noise and low spatial resolution in automotive radar data, exploring temporal relations of learnable features over consecutive 2 radar frames has shown performance gain on downstream tasks (e.g., object detection and tracking) in our previous study. In this paper, we further enhance radar perception by significantly extending the time horizon of temporal relations.
To this end, we propose a scalable connective temporal radar (SCTR) method that consists of 1) a standard temporal relation layer (TRL), 2) a connective TRL with shifted window attention, and 3) a window merging operation, to facilitate feature connectivity between radar frames over an extended time interval. Our complexity analysis and comprehensive evaluation of the Radiate dataset demonstrate that the SCTR achieves a great tradeoff between the complexity and downstream detection performance.

up
0 users have voted: