Problem
Research questions and friction points this paper is trying to address.
FMCW LiDAR
long-range perception
Doppler velocity
dataset and benchmark
3D object detection
AevaScenes: An FMCW LiDAR Dataset and Benchmark for Long-Range Perception
🤖 AI Summary
This study addresses the underutilization of Doppler velocity signals from FMCW LiDAR in long-range perception. To this end, we construct the first large-scale FMCW LiDAR benchmark dataset comprising 57,000 frames and 8 million annotations, systematically defining tasks for 3D object detection, scene flow estimation, and semantic segmentation. Through multi-sensor fusion, we thoroughly investigate the mechanisms by which Doppler information enhances long-range perception, revealing its significant advantages in low-latency, single-frame scenarios. Experimental results demonstrate that the proposed approach improves the average precision (AP) of long-range vehicle and pedestrian detection by up to twofold, while also achieving substantial gains in full-range scene flow accuracy.
📝 Abstract
FMCW LiDAR measures per-point radial Doppler velocity alongside range, providing a motion cue unavailable in conventional time-of-flight sensors. Exploiting this signal at long range remains understudied. We present an FMCW LiDAR dataset of 575 sequences (57.5K frames) with over 8 million annotated 3D boxes across 16 detection classes and per-point labels across 24 semantic classes, captured by six commercial FMCW LiDAR sensors and six paired 4K cameras across eight Bay Area cities, including 237 nighttime sequences, with annotations extending to 400m. We define a benchmark with three tasks: 3D object detection, scene flow estimation, and semantic segmentation. Detection and scene flow are evaluated across three range bins to 400m, with a public evaluation server. We explore the impact of Doppler measurements on flagship recognition tasks, and find significant improvements up to 2X in detection AP of far-away vehicles and pedestrians, particularly in low-latency single-frame settings. We similarly find scene flow accuracy is significantly improved with Doppler measurements across all ranges. Our dataset and benchmark have been publicly released at https://scenes.aeva.com.
Innovation
Methods, ideas, or system contributions that make the work stand out.
FMCW LiDAR
Doppler velocity
Long-range perception
3D object detection
Scene flow estimation
🔎 Similar Papers
No similar papers found.
