Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Hanfang, Yang, Yizhuo, Hu, Jinming, Yang, Jianfei, Liu, Fen, Yuan, Shenghai
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909460113391616
author Liang, Hanfang
Yang, Yizhuo
Hu, Jinming
Yang, Jianfei
Liu, Fen
Yuan, Shenghai
author_facet Liang, Hanfang
Yang, Yizhuo
Hu, Jinming
Yang, Jianfei
Liu, Fen
Yuan, Shenghai
contents Compact UAV systems, while advancing delivery and surveillance, pose significant security challenges due to their small size, which hinders detection by traditional methods. This paper presents a cost-effective, unsupervised UAV detection method using spatial-temporal sequence processing to fuse multiple LiDAR scans for accurate UAV tracking in real-world scenarios. Our approach segments point clouds into foreground and background, analyzes spatial-temporal data, and employs a scoring mechanism to enhance detection accuracy. Tested on a public dataset, our solution placed 4th in the CVPR 2024 UG2+ Challenge, demonstrating its practical effectiveness. We plan to open-source all designs, code, and sample data for the research community github.com/lianghanfang/UnLiDAR-UAV-Est.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12716
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds
Liang, Hanfang
Yang, Yizhuo
Hu, Jinming
Yang, Jianfei
Liu, Fen
Yuan, Shenghai
Computer Vision and Pattern Recognition
Robotics
Compact UAV systems, while advancing delivery and surveillance, pose significant security challenges due to their small size, which hinders detection by traditional methods. This paper presents a cost-effective, unsupervised UAV detection method using spatial-temporal sequence processing to fuse multiple LiDAR scans for accurate UAV tracking in real-world scenarios. Our approach segments point clouds into foreground and background, analyzes spatial-temporal data, and employs a scoring mechanism to enhance detection accuracy. Tested on a public dataset, our solution placed 4th in the CVPR 2024 UG2+ Challenge, demonstrating its practical effectiveness. We plan to open-source all designs, code, and sample data for the research community github.com/lianghanfang/UnLiDAR-UAV-Est.
title Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2412.12716