mlsanityData to 7 Oct 2026

LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation

arXiv 2111.04875 ↗First posted 8 Nov 2021cs.CV cs.ROcited by 15

Not on the map. Why?

Abstract (arXiv)

Moving object detection and segmentation is an essential task in the Autonomous Driving pipeline. Detecting and isolating static and moving components of a vehicle's surroundings are particularly crucial in path planning and localization tasks. This paper proposes a novel real-time architecture for motion segmentation of Light Detection and Ranging (LiDAR) data. We use three successive scans of LiDAR data in 2D Bird's Eye View (BEV) representation to perform pixel-wise classification as static or moving. Furthermore, we propose a novel data augmentation technique to reduce the significant class imbalance between static and moving objects. We achieve this by artificially synthesizing moving objects by cutting and pasting static vehicles. We demonstrate a low latency of 8 ms on a commonly used automotive embedded platform, namely Nvidia Jetson Xavier. To the best of our knowledge, this is the first work directly performing motion segmentation in LiDAR BEV space. We provide quantitative results on the challenging SemanticKITTI dataset, and qualitative results are provided in https://youtu.be/2aJ-cL8b0LI.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 32 of its 51 references that are in the map. First posted on arXiv 8 Nov 2021.

Builds on

32 of 51 references.

References · 32

  1. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  2. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  3. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  4. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  5. 2021Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Datacited by 64
  6. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  7. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  8. 2020SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Drivingcited by 48
  9. 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 41
  10. 2020Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platformcited by 40
  11. 2019RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Drivingcited by 39
  12. 2019FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Drivingcited by 36
20 more
  1. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  2. 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
  3. 2019FuseMODNet: Real-Time Camera and LiDAR based Moving Object Detection for robust low-light Autonomous Drivingcited by 26
  4. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  5. 2017Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environmentscited by 22
  6. 2021Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learningcited by 20
  7. 2018Monocular Fisheye Camera Depth Estimation Using Sparse LiDAR Supervisioncited by 19
  8. 2020BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye Viewcited by 19
  9. 2019FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Drivingcited by 18
  10. 2020TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metriccited by 17
  11. 2021BEVDetNet: Bird's Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Drivingcited by 17
  12. 2021Adversarial Attacks on Multi-task Visual Perception for Autonomous Drivingcited by 14
  13. 2019DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scanscited by 13
  14. 2021An Online Learning System for Wireless Charging Alignment using Surround-view Fisheye Camerascited by 9
  15. 2021A Hybrid Sparse-Dense Monocular SLAM System for Autonomous Drivingcited by 8
  16. 2016Robust Moving Objects Detection in Lidar Data Exploiting Visual Cuescited by 7
  17. 2018Mapless Online Detection of Dynamic Objects in 3D Lidarcited by 7
  18. 2017Deep Semantic Classification for 3D LiDAR Datacited by 5
  19. 2019LU-Net: An Efficient Network for 3D LiDAR Point Cloud Semantic Segmentation Based on End-to-End-Learned 3D Features and U-Netcited by 5
  20. 2018Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarioscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 4; 2025: 2; 2026: 1.

15 papers.

Sort:

  1. 2022Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutionscited by 35
  2. 2022Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentationcited by 29
  3. 2023InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Datacited by 18
  4. 2024MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Modelcited by 12
  5. 2023MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Featurescited by 10
  6. 2023Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Cloudscited by 9
  7. 2022Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Seriescited by 8
  8. 2024SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloudcited by 5
  9. 2024StreamMOS: Streaming Moving Object Segmentation with Multi-View Perception and Dual-Span Memorycited by 3
  10. 2023LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Drivingcited by 2
  11. 2023Multi-camera Bird's Eye View Perception for Autonomous Drivingcited by 2
  12. 2024CV-MOS: A Cross-View Model for Motion Segmentationcited by 1
3 more
  1. 2025BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentationcited by 0
  2. 2025KDMOS:Knowledge Distillation for Motion Segmentationcited by 0
  3. 2026Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networkscited by 0