CS-ORION

“Compressed Sensing for Remote Imaging in Aerial and Terrestrial Surveillance”, 09/2010 – 08/2014.

Funded by: European Commission, FP7, Marie Curie IAPP.

Partners: FORTH-ICS (Coordinator:  P. Tsakalides), CEA/Saclay (France, PI: JL Starck), SAGEM (France), VTrip (Greece).

Funding: €1.280.000 (FORTH-ICS: €520.783)
.

SPL Contact Person:  Prof. Panagiotis Tsakalides.

Summary: Remote sensing platforms such as distributed camera networks, Unmanned Aerial Vehicles (UAVs), and sensor networks can provide a wealth of information and offer critical insights about the environment and its condition. However, the limited resources of these platforms, including low-end processing unit, batteries, and short-range radio prohibit their proliferation in civilian applications.

The technical objectives of CS-ORION are to employ, implement, and validate the concepts of Compressed Sensing in the acquisition, coding, transmission, and reconstruction of image and video from power constrained remote surveillance systems. To that end, CS-ORION investigated methods that can support: I) fast, simple and efficient compression/coding, ii) fully linear compression that allows efficient data fusion, iii) full decoupling between the compression/coding stage and the decompression/reconstruction stage, iv) robustness to bit losses due to adverse operating remote sensing environments, and v) encryption without the additional computational cost of a separate protocol.

The role of SPL:

  • Design of a novel Compressed Video Sensing and Learning paradigm for video encoding and classification on resource-limited platforms.

  • Design of image enhancement (low light and high dynamic range) methods based on the concepts of sparsity.

Related Publications:

Tsagkatakis, Grigorios; Woiselle, Arnaud; Tzagkarakis, George; Bousquet, Marc; Starck, Jean-Luck; Tsakalides, Panagiotis, Multireturn compressed gated range imaging. Optical Engineering, 54(3), 031106-031106, 2015.

Tzagkarakis, Grigorios; Tsakalides, Panagiotis; Starck, Jean-Luck, Compressive Video Sensing with Adaptive Measurement Allocation for Improving MPEGx Performance, in Proc. 10th International Conference on Computer Vision Theory and Applications (VISAPP ‘15), Berlin, Germany, March 11-14, 2015.

Fotiadou, Konstantina; Tsagkatakis, Grigorios; Tsakalides, Panagiotis, Low Light Image Enhancement via Sparse Representations, in Proc. International Conference on Image Analysis and Recognition (ICIAR ‘14), Vilamoura, Algarve, Portugal, October 22-24, 2014.

 Achievements:

  • Development of an innovative, highly efficient Time-of-Flight camera based on the concept of Compressed Sensing.

  • Development of a Compressed Sensing-based localization platform for mobile devices and sensor networks.