UAM_Biblioteca | Unified search engine | Scientific Production Portal | UAM Research Data Repository
Universidad Autónoma de Madrid
Biblos-e Archivo
We are onFacebookCanal BiblosYouTubeTwitterPinterestWhatsappInstagram
    • español
    • English
  • English 
    • español
    • English
  • Log in
JavaScript is disabled for your browser. Some features of this site may not work without it.

Search Biblos-e Archivo

Advanced Search

Browse

All of Biblos-e ArchivoCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsFacultiesThis CollectionBy Issue DateAuthorsTitlesSubjectsFaculties

My Account

Log inRegister

Statistics

View Usage Statistics

Help

Information about Biblos-e ArchivoI want to submit my workI want to submit my doctoral thesisFrequently Asked QuestionsCopyrightsFinancial Agencies and OA policy

UAM_Biblioteca

View Item 
  •   Biblos-e Archivo
  • 1 - Producción científica en acceso abierto de la UAM
  • Producción científica en acceso abierto de la UAM
  • View Item
  •   Biblos-e Archivo
  • 1 - Producción científica en acceso abierto de la UAM
  • Producción científica en acceso abierto de la UAM
  • View Item

Semantic-driven multi-camera pedestrian detection

Author
López Cifuentes, Alejandrountranslated; Escudero Viñolo, Marcosuntranslated; Bescos Cano, Jesúsuntranslated; Carballeira López, Pablountranslated
Entity
UAM. Departamento de Tecnología Electrónica y de las Comunicaciones
Publisher
Springer Nature
Date
2022-05-01
Citation
10.1007/s10115-022-01673-w
Knowledge and Information Systems 64.5 (2022): 1211-1237
 
 
 
ISSN
0219-1377 (print); 0219-3116 (online)
DOI
10.1007/s10115-022-01673-w
Funded by
This study has been partially supported by the Spanish Government through its TEC2017- 88169-R MobiNetVideo project
Project
Gobierno de España. TEC2017- 88169-R
Editor's Version
https://doi.org/10.1007/s10115-022-01673-w
Subjects
Multi-camera systems; Pedestrian detection; Semantic segmentation; Video surveillance; Telecomunicaciones
URI
http://hdl.handle.net/10486/702408
Rights
© The author(s)

Licencia Creative Commons
Esta obra está bajo una Licencia Creative Commons Atribución 4.0 Internacional.

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
Show full item record

Files in this item

Thumbnail
Name
semantic_lopez-cifuentes_Knowl Inf Syst_2022.pdf
Size
3.145Mb
Format
PDF

Refworks Export

Delicious Save this on Delicious

Google™ Scholar:López Cifuentes, Alejandro - Escudero Viñolo, Marcos - Bescos Cano, Jesús - Carballeira López, Pablo

This item appears in the following Collection(s)

  • Producción científica en acceso abierto de la UAM [15086]

Related items

Showing items related by title, author, creator and subject.

  • Semantic-driven multi-camera pedestrian detection 

    López Cifuentes, AlejandroAutoridad UAM; Escudero Viñolo, MarcosAutoridad UAM; Bescos Cano, JesúsAutoridad UAM; Carballeira López, PabloAutoridad UAM
    2022-04-09
  • Automatic semantic parsing of the ground-plane in scenarios recorded with multiple moving cameras 

    López Cifuentes, AlejandroAutoridad UAM; Escudero Viñolo, MarcosAutoridad UAM; Bescos Cano, JesúsAutoridad UAM
    2018-08-17
  • Online clustering-based multi-camera vehicle tracking in scenarios with overlapping FOVs 

    Luna García, ElenaAutoridad UAM; San Miguel Avedillo, Juan CarlosAutoridad UAM; Martínez Sánchez, José MaríaAutoridad UAM; Escudero Viñolo, MarcosAutoridad UAM
    2022-02
All the documents from Biblos-e Archivo are protected by copyrights. Some rights reserved.
Universidad Autónoma de Madrid. Biblioteca
Contact Us | Send Feedback
We are onFacebookCanal BiblosYouTubeTwitterPinterestWhatsappInstagram
 

 

All the documents from Biblos-e Archivo are protected by copyrights. Some rights reserved.
Universidad Autónoma de Madrid. Biblioteca
Contact Us | Send Feedback
We are onFacebookCanal BiblosYouTubeTwitterPinterestWhatsappInstagram