Attention-Aware Multi-View Pedestrian Tracking

• URL: http://arxiv.org/abs/2504.03047v1
• Date: Thu, 03 Apr 2025 21:53:08 GMT
• Title: Attention-Aware Multi-View Pedestrian Tracking
• Authors: Reef Alturki, Adrian Hilton, Jean-Yves Guillemaut,
• Abstract summary: Recent multi-view pedestrian detection models have highlighted the potential of an early-fusion strategy.<n>This strategy has been shown to improve both detection and tracking performance.<n>We propose a novel model that incorporates attention mechanisms in a multi-view pedestrian tracking scenario.
• Score: 21.393389135740712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In spite of the recent advancements in multi-object tracking, occlusion poses a significant challenge. Multi-camera setups have been used to address this challenge by providing a comprehensive coverage of the scene. Recent multi-view pedestrian detection models have highlighted the potential of an early-fusion strategy, projecting feature maps of all views to a common ground plane or the Bird's Eye View (BEV), and then performing detection. This strategy has been shown to improve both detection and tracking performance. However, the perspective transformation results in significant distortion on the ground plane, affecting the robustness of the appearance features of the pedestrians. To tackle this limitation, we propose a novel model that incorporates attention mechanisms in a multi-view pedestrian tracking scenario. Our model utilizes an early-fusion strategy for detection, and a cross-attention mechanism to establish robust associations between pedestrians in different frames, while efficiently propagating pedestrian features across frames, resulting in a more robust feature representation for each pedestrian. Extensive experiments demonstrate that our model outperforms state-of-the-art models, with an IDF1 score of $96.1\%$ on Wildtrack dataset, and $85.7\%$ on MultiviewX dataset.

Related papers

• Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume [21.393389135740712]
  Occlusion poses a significant challenge in pedestrian detection from a single view.<n>Recent advances in multi-view detection utilized an early-fusion strategy that strategically projects the features onto the ground plane.<n>We introduce a novel model that efficiently leverages traditional 3D reconstruction techniques to enhance deep multi-view pedestrian detection.
  arXiv  Detail & Related papers  (2025-03-14T01:05:44Z)
• MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection [4.506083131558207]
  We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing.<n>We propose an unsupervised domain adaptation (UDA) method that adapts the model to new rigs without requiring additional labeled data.
  arXiv  Detail & Related papers  (2024-12-05T12:36:12Z)
• DVPE: Divided View Position Embedding for Multi-View 3D Object Detection [7.791229698270439]
  Current research faces challenges in balancing between receptive fields and reducing interference when aggregating multi-view features. This paper proposes a divided view method, in which features are modeled globally via the visibility crossattention mechanism, but interact only with partial features in a divided local virtual space. Our framework, named DVPE, achieves state-of-the-art performance (57.2% mAP and 64.5% NDS) on the nuScenes test set.
  arXiv  Detail & Related papers  (2024-07-24T02:44:41Z)
• Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval [85.73149096516543]
  We address the choice of viewpoint during sketch creation in Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) A pilot study highlights the system's struggle when query-sketches differ in viewpoint from target instances. To reconcile this, we advocate for a view-aware system, seamlessly accommodating both view-agnostic and view-specific tasks.
  arXiv  Detail & Related papers  (2024-07-01T21:20:44Z)
• Lifting Multi-View Detection and Tracking to the Bird's Eye View [5.679775668038154]
  Recent advancements in multi-view detection and 3D object recognition have significantly improved performance. We compare modern lifting methods, both parameter-free and parameterized, to multi-view aggregation. We present an architecture that aggregates the features of multiple times steps to learn robust detection.
  arXiv  Detail & Related papers  (2024-03-19T09:33:07Z)
• Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking [55.13878429987136]
  We propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets. Our method has achieved significant improvements on MOT17 and MOT20 datasets while reaching state-of-the-art performance on DanceTrack dataset.
  arXiv  Detail & Related papers  (2023-11-17T08:17:49Z)
• EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View [6.093524345727119]
  We show that early-fusion in the Bird's Eye View achieves high accuracy for both detection and tracking. EarlyBird outperforms the state-of-the-art methods and improves the current state-of-the-art on Wildtrack by +4.6 MOTA and +5.6 IDF1.
  arXiv  Detail & Related papers  (2023-10-20T08:27:21Z)
• Rethinking Range View Representation for LiDAR Segmentation [66.73116059734788]
  "Many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer, a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-03-09T16:13:27Z)
• DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes [74.64897845999677]
  We introduce a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT.
  arXiv  Detail & Related papers  (2023-02-15T14:10:42Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.