Signal and Image Processing

Figure : Multiview people detection (ISPGroup)

ICTEAM researchers use and develop signal processing techniques to solve a problems ranging from physical layer problems, localisation or channel coding to image processing and recognition and networked media.

Principal Investigators :

Pierre-Antoine Absil, Christophe De Vleeschouwer, Laurent Jacques, Sébastien Jodogne, Jérôme Louveaux, Benoit Macq, Luc Vandendorpe

Research Labs :

Image and Signal Processing Group (ISPGroup), INMA

Research Areas :

The research focuses on estimation and detection techniques for wired and wireless environments. Transmitters and receivers are designed and optimized for OFDM (multicarrier) transmission schemes, filter-bank based multicarrier modulation schemes, OFDMA systems, multiuser multiantenna systems (MIMO) and multicell/interference limited systems.
Particular attention is paid to iterative/soft information/turbo receivers both for detection and estimation (carrier phase, carrier frequency, channel state information) or synchronization. Optimization of modulation, coding and resource allocation are also investigated.

This research focuses on security achieved at the PHY layer. Particular attention is paid to scenarios where a transmitter wants to communicate to a legitimate receiver over parallel channels (for instance OFDM over frequency selective channels). An eavesdropper is able to capture information from some of the links. Along the work of cooperative techniques (relays) emphasis is put on transmission schemes helped by a relay. The objectives are to obtain bounds on secure transmission rates, investigate situations where non perfect CSI is available, and to design coding schemes to exploit the potential for secure communications.

This researches focuses on ultra wide band (UWB) based localisation or positioning. Methods considered are time of arrival (TOA), time difference of arrival (TDOA) and angle of arrival (AOA). Bounds have been derived to assess the potential of UWB, understand the impact of multipath propagation and investigate the ambiguities. Practical estimators are proposed and their performance is investigated. A practical testbed has been developed and is being upgraded. An accuracy of a few millimeters has been achieved for indoor positioning over distances of about ten meters and with obstacles.

Source coding and channel coding (or decoding) and transmission are often designed independently. This research track investigates scenarios where there is advantage or potential in jointly designing the encoders or decoders. The research focuses on bounds for some techniques, and practical schemes applying this philosophy, in particular for sensor networks.

Compression & streaming

Image and video compression algorithms are investigated, including for stereo and multi-view contents. Visually pleasant and fluent video streaming or image browsing are implemented by adapting compression and forwarding mechanisms to network and terminal resources. This implies the rate-distortion optimization of image/video packet schedules, but also adaptive switching between multiple versions of the content. For low bandwidth wireless accesses, interactive streaming architectures are investigated to allow the end-user to control the trade-offs involved when reducing the spatial and temporal resolution of the streamed content.

Content-based retrieval

Coarse-to-fine JPEG2000 image classification, active learning for surveillance scene retrieval.


Fingerprinting of mono and stereo images for Digital Cinema; 3D meshes watermarking.

Object & people detection and tracking algorithms are developed to understand behaviors in natural scenes. Application domains include autonomous production of visual reports (e.g. for team sport events), but also video-surveillance. Resource constrained allocation solutions are also proposed to build automatically personalized summaries of edited video feeds.

Another field of research is the solving of inverse problems from generalized sparsity prior (with applications in optics and X-ray CT), Compressed Sensing (theory and application), theoretical questions linked to the design of new sensors (for computer vision), applied mathematics for astronomical and biomedical signal processing questions, and representation of data on strange spaces (e.g., sphere, manifolds, or graphs).

This project aims at detecting segments or contours of objects in a given picture by means of graph-based techniques that unfold the community structures in a large graph. The communities found are also hierarchical, allowing to find subregions inside an object.

The research develops image & signal processing tools for the use in various biomedical contexts, including protein docking, radiotherapy, proton therapy, brachytherapy, surgery, EEG analysis, kinematic assessment through accelerometers, etc. 

  • Shape analysis for protein docking including 3D mesh processing and the analysis of protein surface properties; 
  • Radio/proton therapy: rigid and non-rigid image registrations methods for 2D-3D and 3D-3D images both for single and multiple modalities as well as for surfaces; 
  • Segmentation techniques either using prior knowledge (atlas-based) or allowing user interaction (graph cuts); 
  • EEG reconstruction, transcranial magnetic stimulation, as well as on the use of functional imaging for measuring motion disorders;
  • Accelerometers are used for kinematic analysis, e.g.  to quantify the motor disturbances due to Parkinson's disease or to measure objectively the effects of the rehabilitation process following a stroke;
  • Human-computer interactions to create intuitive user interfaces for the clinical world.

Most recent publications

Below are listed the 10 most recent journal articles and conference papers produced in this research area. You also can access all publications by following this link : see all publications.

Journal Articles

1. Dirksen, Sjoerd; Genzel, Martin; Stollenwerk, Alexander; Jacques, Laurent. The Separation Capacity of Random Neural Networks. In: Journal of Machine Learning Research, Vol. 23, no.209, p. 1--47 (2022). (Accepté/Sous presse).

2. Schellekens, Vincent; Jacques, Laurent. Asymmetric Compressive Learning Guarantees With Applications to Quantized Sketches. In: IEEE Transactions on Signal Processing, Vol. 70, no.1, p. 1348-1360 (2022). doi:10.1109/tsp.2022.3157486.

3. Guérit, Stéphanie; Sivankutty, Siddharth; Lee, John Aldo; Rigneault, Hervé; Jacques, Laurent. Compressive Imaging Through Optical Fiber with Partial Speckle Scanning. In: SIAM Journal on Imaging Sciences, Vol. 15, no.2, p. 387-423 (2022). doi:10.1137/21m1407586.

4. Benjilali, Wissam; Guicquero, William; Jacques, Laurent; Sicard, Gilles. Hardware-Compliant Compressive Image Sensor Architecture Based on Random Modulations and Permutations for Embedded Inference. In: IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 67, no.4, p. 1218-1231 (2020). doi:10.1109/tcsi.2020.2971565.

5. Moshtaghpour, Amirafshar; Bioucas-Dias, Jose M.; Jacques, Laurent. Close Encounters of the Binary Kind: Signal Reconstruction Guarantees for Compressive Hadamard Sampling with Haar Wavelet Basis. In: IEEE Transactions on Information Theory, Vol. 66, no. 11, p. 7253 - 7273 (2020). doi:10.1109/tit.2020.2992852 (Accepté/Sous presse).

6. Vandaele, Rémy; Aceto, Jessica; Muller, Marc; Péronnet, Frédérique; Debat, Vincent; Wang, Ching-Wei; Huang, Cheng-Ta; Jodogne, Sébastien; Martinive, Philippe; Geurts, Pierre; Marée, Raphaël. Landmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach. In: Scientific Reports, Vol. 8, no.1, p. 13 (2018). doi:10.1038/s41598-017-18993-5.

7. Jodogne, Sébastien. The Orthanc Ecosystem for Medical Imaging. In: Journal of Digital Imaging, Vol. 31, no.3, p. 341-352 (2018). doi:10.1007/s10278-018-0082-y.

8. Kirkove, Murielle; Guérit, Stéphanie; Jacques, Laurent; Loffet, Christophe; Languy, Fabian; Vandenrijt, Jean-François; Georges, Marc. Determination of vibration amplitudes from binary phase patterns obtained by phase-shifting time-averaged speckle shearing interferometry. In: Applied Optics, Vol. 57, no.27, p. 8065 (2018). doi:10.1364/ao.57.008065.

9. Bergmann, Ronny; Gousenbourger, Pierre-Yves. A Variational Model for Data Fitting on Manifolds by Minimizing the Acceleration of a Bézier Curve. In: Frontiers in Applied Mathematics and Statistics, Vol. 4, no.59, p. 1--16 (2018). doi:10.3389/fams.2018.00059.

10. Gousenbourger, Pierre-Yves; Massart, Estelle; Absil, Pierre-Antoine. Data Fitting on Manifolds with Composite Bézier-Like Curves and Blended Cubic Splines. In: Journal of Mathematical Imaging and Vision, Vol. 61, no. 5, p. 645-671 (2018). doi:10.1007/s10851-018-0865-2.

Conference Papers

1. Jodogne, Sébastien. Client-Side Application of Deep Learning Models Through Teleradiology. In: Studies in Health Technology and Informatics. Vol. 302, no.1, p. 997-1001 (2023). Maria Hägglund et al. 2023 xxx. doi:10.3233/shti230325.

2. Delogne, Rémi; Schellekens, Vincent; Jacques, Laurent. ROP inception: signal estimation with quadratic random sketching. 2022 xxx.

3. Leblanc, Olivier; Hofer, Matthias; Sivankutty, Siddharth; Rigneault, Hervé; Jacques, Laurent. An Interferometric view of Speckle Imaging. 2022 xxx.

4. Jodogne, Sébastien. Rendering Medical Images using WebAssembly. In: Proc. of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (Volume 2), 2022, 978-989-758-552-4, 43-51 xxx. doi:10.5220/0000156300003123.

5. Sjoerd, Dirksen; Genzel, Martin; Jacques, Laurent; Stollenwerk, Alexander. The Separation Capacity of Random Neural Networks. 2021 xxx.

6. Jodogne, Sébastien. Automatically publishing medical images from a filesystem as a DICOM server. In: Insights into Imaging. Vol. 13, no. S2, p. 7. SpringerOpen, 2021 xxx. doi:10.1186/s13244-022-01168-w.

7. Jodogne, Sébastien. Importing and serving open-data medical images to support Artificial Intelligence research. In: Insights into Imaging. Vol. 13, no. S1, p. 6. SpringerOpen, 2021 xxx. doi:10.1186/s13244-022-01168-w.

8. Monnoyer de Galland de Carnières, Gilles; Feuillen, Thomas; Jacques, Laurent; Vandendorpe, Luc. Sparse Factorization-based Detection of Off-the-Grid Moving targets using FMCW radars. In: Proceedings of ICASSP 2021, Toronto, Ontario, Canada, 6-11 June 2021, 2021, 9781509066322 xxx.

9. Schellekens, Vincent; Jacques, Laurent. Compressive Learning of Generative Networks. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). Vol. 28, no./, p. / (2020). 2020 xxx.

10. Moshtaghpour, Amirafshar; Bioucas-Dias, José; Jacques, Laurent. Performance of Compressive Sensing for Hadamard-Haar Systems. In: Proceedings of SPARS'19. Vol. 1, no.1, p. 1 (2019). 2019 xxx.