WiSAR3D - Aerial LiDAR dataset for 3D object detection

Oren Shrout, Ori Nizan, Yizhak Ben-Shabat, Ayellet Tal
Technion, Israel Institute of Technology
Paper arXiv Code Data

The WiSAR3D dataset includes LiDAR point clouds captured by an aerial drone, specifically designed for Wilderness Search And Rescue (WiSAR) scenarios. It features annotations for 3D object detection across a range of categories and sizes.

Abstract

Wilderness Search and Rescue (WiSAR) operations aim to locate and rescue individuals in remote, rugged environments. We introduce WiSAR3D, the first aerial LiDAR 3D dataset specifically tailored for 3D object detection in rural scenes. WiSAR3D comprises 2633 strips—contiguous point clouds collected along the flight path, all fully annotated with 67.5K 3D bounding boxes for 22 categories. As the data is captured with multiple returns (echoes), it enables detection under foliage, which is impossible with RGB cameras. Additionally, as this is the first-of-its-kind dataset, we provide benchmark evaluations for state-of-the-art methods developed for autonomous cars on our aerial dataset. The results suggest that specialized models are needed in this domain, as finding individuals remains challenging for current 3D detectors.

Tents under foliage

This animation shows tents under foliage, colored by intensity on the left and by the return number on the right. Use the slider to move between the videos.