mlsanityData to 7 Oct 2026

Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle

arXiv 2309.06313 ↗First posted 12 Sep 2023cs.CV cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large forward motion of the vehicle. Even object detection and human sensing models perform significantly worse on onboard videos when compared to standard benchmarks because objects often appear far away from the camera compared to the standard object detection benchmarks, image quality is often decreased by motion blur and occlusions occur often. This has led to the popularisation of traffic data-specific benchmarks. Recently Light Detection And Ranging (LiDAR) sensors have become popular to directly estimate depths without the need to perform 3D reconstructions. However, LiDAR-based methods still lack in articulated human detection at a distance when compared to image-based methods. We hypothesize that benchmarks targeted at articulated human sensing from LiDAR data could bring about increased research in human sensing and prediction in traffic and could lead to improved traffic safety for pedestrians.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 183 of its 271 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

183 of 271 references.

References · 183

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  12. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
38 more
  1. 2018Path Aggregation Network for Instance Segmentationcited by 796
  2. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  3. 2023Segment Everything Everywhere All at Oncecited by 546
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  6. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  7. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  8. 2016Convolutional Pose Machinescited by 325
  9. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  10. 2022Generalized Decoding for Pixel, Image, and Languagecited by 292
  11. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  12. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  13. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  14. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  15. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  16. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  17. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 197
  18. 2020Long-term Human Motion Prediction with Scene Contextcited by 191
  19. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  20. 2020Transformer Networks for Trajectory Forecastingcited by 180
  21. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  22. 2019Multiple Futures Predictioncited by 178
  23. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  24. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  25. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  26. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  27. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  28. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  29. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 150
  30. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 143
  31. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  32. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  33. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  34. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  35. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  36. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  37. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  38. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122

50 most cited of 183 All 183 (JSON)

Built on by

Not cited yet.