Proyecto
TEC2017-88169-R (MobiNetVideo): Análisis de vídeo para implementación práctica de redes de cámaras móviles cooperativas (2018-2020)The main objective of this project is to achieve advances in the state-of-the-art for video analysis
systems employing mobile imaging devices, as a response to the growing social and industry demand
for potential visual-based applications supported by the boom of mobile devices featuring high
imaging and computing capabilities. This project will focus on networked systems composed of fixed,
pan-tilt-zoom and mobile cameras (i.e., heterogeneous camera networks) and it will address key
challenges that nowadays limit their widespread adoption: autonomous and coordinated operation,
performance of visual analysis tools and practical deployment issues. The outcomes of this project
will underpin emerging applications in many areas where camera mobility plays a key role, such as
unmanned aerial vehicles exploration for search and rescue missions and disaster management, smart
traffic and people surveillance, in-home pervasive networks for monitoring the elderly, real-time
health supervision and life-logging cameras integrated with wearable body sensors, etc.
Funded by: Ministerio de Economía, Industria y Competitividad
Participants: Universidad Autónoma de Madrid
Main researcher: Martinez Sanchez, Jose María
Researchers: Bescós Cano, Jesús, Carballeira Lopez, Pablo, Escudero Viñolo, Marcos, García, Miguel Angel, García, Alvaro, SanMiguel Avedillo, Juan Carlos
Web link: TEC2017-88169-R (MobiNetVideo)
External Publications:
Journals
- Diego Ortego, Juan C. SanMiguel, Jose M. Martinez : "Hierarchical improvement of foreground segmentation masks in background subtraction", IEEE Transactions on Circuits and Systems for Video Technology
- Alejandro Lopez, Marcos Escudero, Jesús Bescós, Alvaro Garcia-Martin : "Semantic-Aware Scene Recognition", Pattern Recognition
- Elena Luna, Juan C. SanMiguel, Jose M. Martinez, Marcos Escudero : "Online clustering-based multi-camera vehicle tracking in scenarios with overlapping FOVs", Multimedia Tools and Applications
- Elena Luna, Juan C. SanMiguel, Jose M. Martinez, Pablo Carballeira : "Graph Neural Networks for Cross-Camera Data Association", IEEE Transactions on Circuits and Systems for Video Technology (En prensa)
- Paula Moral, Alvaro Garcia-Martin, Jose M. Martinez, Jesús Bescós : "Enhancing Vehicle Re-Identification Via Synthetic Training Datasets and Re-ranking Based on Video-Clips Information", Multimedia Tools and Applications
- Alejandro Lopez, Marcos Escudero, Jesús Bescós, Juan C. SanMiguel : "Attention-based Knowledge Distillation in Scene Recognition: the Impact of a DCT-driven Loss", IEEE Transactions on Circuits and Systems for Video Technology (En prensa)
Conferences
- Elena Luna, Paula Moral, Juan C. SanMiguel, Alvaro Garcia-Martin, Jose M. Martinez : "VPULab participation at AI City Challenge 2019", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
- Elena Luna, Diego Ortego, Juan C. SanMiguel, Jose M. Martinez : "Multi-target Tracking from Unmanned Aerial Vehicles", 23rd Iberoamerican Congress on Pattern Recognition
- Elena Luna, Diego Ortego, Juan C. SanMiguel, Jose M. Martinez, et al. : "VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results", European Conference on Computer Vision Workshops
- Alejandro Peña : "People-background segmentation based on DeepPyramid Deformable Part Models", Iberoamerican Congress on Pattern Recognition
- Alejandro Lopez, Marcos Escudero : "Visualizing the Effect of Semantic Categories in the Attribution of Scene Recognition Models", International Conference on Pattern Recognition
- Paula Moral : "Vehicle Re-Identification in Multi-Camera scenarios based on Ensembling Deep Learning Features", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
- Paula Moral, Alvaro Garcia-Martin, Jose M. Martinez : "Vehicle Re-Identification in Multi-Camera scenarios based on Ensembling Deep Learning Features", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop 2020
- Marta Fernandez, Paula Moral, Alvaro Garcia-Martin, Jose M. Martinez : "Vehicle Re-Identification based on Ensembling Deep Learning Features including a Synthetic Training Dataset, Orientation and Background Features, and Camera Verification", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop 2021
- Alvaro Garcia-Martin, Matej Kristan, Jesús Bescós : "The sixth Visual Object Tracking VOT2020 challenge results", 16TH EUROPEAN CONFERENCE ON COMPUTER VISION
Internal Publications:
Tesis
- Quality-Driven video analysis for the improvement of foreground segmentation, Ortego Hernandez, Diego, June 2018, (Tutor: Martinez Sanchez, Jose María) , (Ponente: SanMiguel Avedillo, Juan Carlos)
- Detección y asociación de objetos en escenarios multivista, Moral de Eusebio, Paula, (Tutor: Garcia-Martin, Alvaro) , (Ponente: Martinez Sanchez, Jose María)
Master Thesis
- People detection in omnidirectional cameras: development of a deep learning architecture based on a spatial grid of classifiers, Sepulveda Jorcano, Enrique, July 2020, (Tutor: Carballeira Lopez, Pablo)
Degree Project
- Adaptación de un sistema de detección de personas en cámaras omnidireccionales a descriptores deep learning, Garcia Crespo, Nicolas, July 2019, (Tutor: Carballeira Lopez, Pablo) , (Ponente: Bescós Cano, Jesús)