Home Research Camera Networks

Camera Networks

Contact person: A. Cenedese
Related projects: FeedNetBack

Camera networks are a prototypical example of networked control systems, where the aspects of distributed control, estimation and communication assume a crucial role.



Sparse Camera Networks

This research concerns the design surveillance systems based on a network with hundreds of cameras.

In particular we are interested in developing a self-calibrating system that requires only minimal installation and maintenance costs, and that it is able to accomplish multiple tasks such as multiple target tracking, event detection and recognition, and redundant video storing. The main challenges reside in the bandwidth and computation requirements which makes unfeasible a centralized control and management architecture.
The goal of the research is to consider a network of smart cameras, i.e. cameras with computational, memory and communication resources, which can cooperate though distributed algorithms to accomplish multiple and possibly competitive tasks, and provide the end user of the surveillance system only the essential information.
Research activities include:
  • Camera distributed calibration
  • Camera network topology learning
  • Smart patrolling and camera synchronization
  • Multicamera tracking


Cooperative and coordinated patrolling and event tracking in a camera network (simulation).

Cooperative and coordinated patrolling and event tracking in a camera network (NAVLAB experiment).

Dense Camera Networks

This research area  addresses the problem of reconstructing the 3D motion of multiple objects  moving within a predefined volume from the videos of multiple cameras. In particular, the motion is captured by tracking a number of unlabeled markers placed on each target object.

Each camera placed around the arena focuses only on a small portion of the total volume to achieve high resolution, and each point of the arena can be seen from multiple cameras to avoid cluttering. The motion of the objects can be reconstructed only by combining the videos from all cameras.
Although motion marker-based motion capture is a well studied problem, the main novel challenge reside in the need of performing the 3D motion capture from hundreds of cameras in real-time. This poses severe problems due to obvious bandwidth constraints and to computational constraints.
Therefore, the goal here is to devise smart distributed tracking algorithms and adaptive cameras bundling that can take advantage of  smart cameras capable of autonomous computation and communication to reduce both computational burden and communication requirements.

Research activities include:
  • 3D distributed reconstruction
  • Characterization of the 3D reconstruction error
  • Camera affinity estimation

Centralized 3D reconstruction of a typical mocap scenario.

Distributed 3D reconstruction of a typical mocap scenario.

Publications     [ all BibTeX ]
L. Varotto, M. Fabris, G. Michieletto, A. Cenedese. Visual sensor network stimulation model identification via Gaussian mixture model and deep embedded features. Engineering Applications of Artificial Intelligence, vol. 114pp. 105096, 2022    [ abstract ] [url] [BibTeX]  
J. Giordano, M. Lazzaretto, G. Michieletto, A. Cenedese. Visual Sensor Networks for Indoor Real-time Surveillance and Tracking of Multiple Targets. Sensors, vol. 22(7), pp. 1--28, 2022    [ abstract ] [url] [BibTeX]  
A. Cenedese, L. Varotto. A Distributed Approach to 3D Reconstruction in Marker Motion Capture Systems. International Conference on Distributed Smart Cameras (ICDSC 2019), 2019    [ abstract ] [url] [BibTeX]  
L. Varotto, M. Fabris, G. Michieletto, A. Cenedese. Distributed Dual Quaternion Based Localization of Visual Sensor Networks. European Control Conference (ECC 2019), 2019    [ abstract ] [url] [BibTeX]  
G. Michieletto, S. Milani, A. Cenedese, G. Baggio. Improving Consensus-based Distributed Camera Calibration via Edge Pruning and Graph Traversal Initialization. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3166--3170, 2018    [ abstract ] [url] [BibTeX]  
N. Bof, R. Carli, A. Cenedese, L. Schenato. Asynchronous Distributed Camera Network Patrolling under Unreliable Communication. IEEE Transactions on Automatic Control, vol. 62(11)pp. 5982-5989, 2017    [ abstract ] [url] [pdf] [BibTeX]  
G. Belgioioso, A. Cenedese, G. Michieletto. Distributed partitioning strategies with visual optimization for camera network perimeter patrolling. 55th Conference on Decision and Control (CDC16), pp. 5912-5917, 2016    [ abstract ] [url] [BibTeX]  
A. Masiero, A. Cenedese. Affinity-based Distributed Algorithm for 3D Reconstruction in Large Scale Visual Sensor Networks. Proceedings of the American Control Conference (ACC2014), pp. 4671--4676, 2014    [ abstract ] [url] [pdf] [BibTeX]  
R. Lucchese, A. Cenedese, R. Carli. An Hidden Markov Model based transitional description of camera networks. Proceedings of the 19th IFAC World Congress, pp. 7394-7399, 2014    [ abstract ] [url] [BibTeX]  
A. Masiero, A. Cenedese. Structure-based approach for optimizing distributed reconstruction in Motion Capture systems. Proceedings of the 19th IFAC World Congress, pp. 10914-10919, 2014    [ abstract ] [url] [BibTeX]  
A. Masiero, A. Cenedese. A Kalman filter approach for the synchronization of motion capture systems. Proc. of the IEEE Conference on Decision and Control (CDC 2012), 2012    [ abstract ] [url] [BibTeX]  
G. Gennari, G. Raccanelli, R. Frezza, A. Cenedese, F. D'Alessi. EP2160883 - METHOD FOR COORDINATING A PLURALITY OF SENSORS. B1 Patent specification (17.10.2012), 2012    [url] [BibTeX]  
G. Gennari, G. Raccanelli, R. Frezza, A. Cenedese, F. D'Alessi. EP2163094 - METHOD AND SYSTEM FOR MONITORING AN ENVIRONMENT. B1 Patent specification (07.11.2012), 2012    [url] [BibTeX]  
R. Alberton, R. Carli, A. Cenedese, L. Schenato. Multi-agent perimeter patrolling subject to mobility constraints. Proceedings of American Control Conference ACC2012, 2012    [ abstract ] [url] [pdf] [BibTeX]  
A. Masiero, A. Cenedese. On triangulation algorithms in large scale camera network systems. American Control Conference (ACC2012), pp. 4096–-4101, 2012    [ abstract ] [pdf] [BibTeX]  
R. Carli, A. Cenedese, L. Schenato. Distributed Partitioning Strategies for Perimeter patrolling. Proceedings of the American Control Conference (ACC11), 2011    [ abstract ] [pdf] [BibTeX]  
M. Munaro, A. Cenedese. Scene specific people detection by simple human interaction. Proceedings of the HICV Workshop in the ICCV 2011, 2011    [ abstract ] [pdf] [BibTeX]  
T. Ko, S. Soatto, D. Estrin, A. Cenedese. Cataloging Birds in Their Natural Habitat. Workshop on Visual Observation and Analysis of Animal and Insect Behavior (VAIB2010), International Conference on Pattern Recognition (ICPR2010), 2010   [pdf] [BibTeX]  
A. Cenedese, F. Cerruti, M. Fabbro, C. Masiero, L. Schenato. Decentralized Task Assignment in Camera Networks. Conference on Decision and Control (CDC10), pp. --, 2010   [pdf] [BibTeX]  
M. Baseggio, A. Cenedese, P. Merlo, M. Pozzi, L. Schenato. Distributed perimeter patrolling and tracking for camera networks. Conference on Decision and Control (CDC10), pp. --, 2010   [pdf] [BibTeX]  
G. Gennari, G. Raccanelli, R. Frezza, E. Campana, A. Cenedese. EP1908016 - EVENT DETECTION METHOD AND VIDEO SURVEILLANCE SYSTEM USING SAID METHOD. B1 Patent specification (23.06.2010), 2010    [url] [BibTeX]  
A. Cenedese, R. Ghirardello, R. Guiotto, F. Paggiaro, L. Schenato. On the Graph Building Problem in Camera Networks. IFAC Workshop on Distributed Estimation and Control in Networked Systems (Necsys'10), pp. 299--304, 2010   [pdf] [BibTeX]  
A. Cenedese, R. Marcon. Methodologies for the Adaptive Compression of Video Sequences. Proceedings of the Joint 48th IEEE Conference on Decision and Control and 28th Chinese Control Conference, pp. 794--799, 2009   [pdf] [BibTeX]  
A. Cenedese, R. Frezza, E. Campana, G. Gennari, G. Raccanelli. Building a Normality Space of Events - A PCA Approach to Event Detection. Proc. of the 3rd International Conference on Computer Vision Theory and Applications (VISAPP2008), pp. 551--554, 2008   [pdf] [BibTeX]