RVSA-3D: Voxel-based fully sparse attention 3D object detection for rail transit obstacle perception
Authors:
- Lirong LianLLLirong Lian
- Yong QinYQYong Qin
- Zhiwei CaoZCZhiwei Cao
- Yang GaoYGYang Gao
- Wei LiWLWei Li
- Xiaoqing ChengXCXiaoqing Cheng
- 23 August 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 171
Abstract
No abstract availableFunding Information
- Beijing Jiaotong University (RAO2025ZR001)
- Beijing Jiaotong University (RAO2023ZZ003)
- China Postdoctoral Science Foundation (GZC20251118)
This publication has 13 references indexed in Scilit:
- High performance point-Voxel feature set abstraction with mamba for 3D object detectionExpert Systems with Applications, 2025
- VoxT-GNN: A 3D object detection approach from point cloud based on voxel-level transformer and graph neural networkInformation Processing & Management, 2025
- SCNet3D: Rethinking the Feature Extraction Process of Pillar-Based 3D Object DetectionIEEE Transactions on Intelligent Transportation Systems, 2024
- Railway Intrusion Detection Based on Machine Vision: A Survey, Challenges, and PerspectivesIEEE Transactions on Intelligent Transportation Systems, 2024
- Robust Artificial Intelligence-Aided Multimodal Rail-Obstacle Detection Method by Rail Track Topology ReconstructionApplied Sciences, 2024
- Research on Railway Obstacle Detection Method Based on Developed Euclidean ClusteringElectronics, 2023
- Automatic Obstacle Detection Method for the Train Based on Deep LearningSustainability, 2023
- An effective railway intrusion detection method using dynamic intrusion region and lightweight neural networkMeasurement, 2022
- TANet: Robust 3D Object Detection from Point Clouds with Triple AttentionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018