Abstract
Abstract
In the current worldwide situation, pedestrian detection has reemerged as a pivotal tool for intelligent video-based systems aiming to solve tasks such as pedestrian tracking, social distancing monitoring or pedestrian mass counting. Pedestrian detection methods, even the top performing ones, are highly sensitive to occlusions among pedestrians, which dramatically degrades their performance in crowded scenarios. The generalization of multi-camera setups permits to better confront occlusions by combining information from different viewpoints. In this paper, we present a multi-camera approach to globally combine pedestrian detections leveraging automatically extracted scene context. Contrarily to the majority of the methods of the state-of-the-art, the proposed approach is scene-agnostic, not requiring a tailored adaptation to the target scenario–e.g., via fine-tuning. This noteworthy attribute does not require ad hoc training with labeled data, expediting the deployment of the proposed method in real-world situations. Context information, obtained via semantic segmentation, is used (1) to automatically generate a common area of interest for the scene and all the cameras, avoiding the usual need of manually defining it, and (2) to obtain detections for each camera by solving a global optimization problem that maximizes coherence of detections both in each 2D image and in the 3D scene. This process yields tightly fitted bounding boxes that circumvent occlusions or miss detections. The experimental results on five publicly available datasets show that the proposed approach outperforms state-of-the-art multi-camera pedestrian detectors, even some specifically trained on the target scenario, signifying the versatility and robustness of the proposed method without requiring ad hoc annotations nor human-guided configuration.
Funder
Universidad Autónoma de Madrid
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Hardware and Architecture,Human-Computer Interaction,Information Systems,Software
Reference44 articles.
1. Alahi A, Jacques L, Boursier Y, Vandergheynst P (2011) Sparsity driven people localization with a heterogeneous network of cameras. J Math Imaging Vision 41(1):39–58
2. Aliakbarpour H, Prasath VBS, Palaniappan K, Seetharaman G, Dias J (2016) Heterogeneous multi-view information fusion: review of 3D reconstruction methods and a new registration with uncertainty modeling. Science 4:8264–8285
3. Baqué P, Fleuret F, Fua P (2017) Deep occlusion reasoning for multi-camera multi-target detection. In: IEEE international conference on computer vision (ICCV), pp 271–279
4. Chavdarova T, Baqué P, Bouquet S, Maksai A, Jose C, Bagautdinov T, Lettry L, Fua P, Van Gool L, Fleuret F (2018) Wildtrack dataset. https://cvlab.epfl.ch/data/wildtrack
5. Chavdarova T, Baqué P, Bouquet S, Maksai A, Jose C, Bagautdinov T, Lettry L, Fua P, Van Gool L, Fleuret F (2018) WILDTRACK: a multi-camera HD dataset for dense unscripted pedestrian detection
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献