mlsanityData to 7 Oct 2026

Valeo Near-Field: a novel dataset for pedestrian intent detection

arXiv 2510.15673 ↗First posted 17 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel dataset aimed at detecting pedestrians' intentions as they approach an ego-vehicle. The dataset comprises synchronized multi-modal data, including fisheye camera feeds, lidar laser scans, ultrasonic sensor readings, and motion capture-based 3D body poses, collected across diverse real-world scenarios. Key contributions include detailed annotations of 3D body joint positions synchronized with fisheye camera images, as well as accurate 3D pedestrian positions extracted from lidar data, facilitating robust benchmarking for perception algorithms. We release a portion of the dataset along with a comprehensive benchmark suite, featuring evaluation metrics for accuracy, efficiency, and scalability on embedded systems. By addressing real-world challenges such as sensor occlusions, dynamic environments, and hardware constraints, this dataset offers a unique resource for developing and evaluating state-of-the-art algorithms in pedestrian detection, 3D pose estimation and 4D trajectory and intention prediction. Additionally, we provide baseline performance metrics using custom neural network architectures and suggest future research directions to encourage the adoption and enhancement of the dataset. This work aims to serve as a foundation for researchers seeking to advance the capabilities of intelligent vehicles in near-field scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

21 of 28 references.

References · 21

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  3. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  4. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  5. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  6. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  7. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  8. 2018Learning to Detect and Track Visible and Occluded Body Joints in a Virtual Worldcited by 81
  9. 2020Multiview Detection with Feature Perspective Transformationcited by 70
  10. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  11. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  12. 2019MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimationcited by 39
9 more
  1. 2023Social-Transmotion: Promptable Human Trajectory Predictioncited by 33
  2. 2024Multi-Transmotion: Pre-trained Model for Human Motion Predictioncited by 21
  3. 2021Generalizable Multi-Camera 3D Pedestrian Detectioncited by 14
  4. 2019JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environmentscited by 12
  5. 2020Detecting 32 Pedestrian Attributes for Autonomous Vehiclescited by 10
  6. 2023DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusioncited by 9
  7. 2020VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Userscited by 7
  8. 2024Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformerscited by 4
  9. 2020Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 1

Built on by

Not cited yet.