Montse Pardàs
Biography
Montse Pardàs received the MS degree in telecommunications and the Ph. D. degree from the Polytechnic University of Catalonia, Barcelona, Spain, in July 1991 and January 1995, respectively. From September 1994 she has been teaching under-graduate and graduate courses in the area of communication systems, digital image processing and computer vision in this University, where she is currently Professor. From January 1999 to December 1999 she was a research visitor at Bell Labs, Lucent Technologies, in New Jersey, and from July 2019 to June 2020 at Toshiba’s Cambridge Research Lab (Computer Vision group). Her main research interests include image and video analysis using mathematical morphology and deep learning, with a special emphasis on segmentation and object tracking applications.
She has served as associate editor of journals such as EURASIP Journal on Advances in Signal Processing and ISRN Machine Vision, as technical co-chair for the international conference EUSIPCO 2011 and as regular reviewer for image processing and computer vision conferences.
Journal Articles top
, “Depth Estimation and Semantic Segmentation from a Single RGB Image Using a Hybrid Convolutional Neural Network”, Sensors, vol. 19, no. 8, 2019. (4.75 MB) |
|
, “Temporally Coherent 3D Point Cloud Video Segmentation in Generic Scenes”, IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 3087 - 3099, 2018. (24.37 MB) |
| , “Real-time user independent hand gesture recognition from time-of-flight camera video using static and dynamic models”, Machine vision and applications, vol. 24, no. 1, pp. 187–204, 2013. |
| , “Region Based Foreground Segmentation Combinig Color and Depth Sensors Via Logarithmic Opinion Pool Decision”, Journal of Visual Communication and Image Representation, 2013. |
| , “Enhanced foreground segmentation and tracking combining Bayesian background, shadow and foreground modeling”, Pattern Recognition Letters, vol. 33, no. 12, pp. 1558–1568, 2012. |
Book Chapters and Bookstop
| , “Foreground objects segmentation for moving camera scenarios based on SCGMM”, in Computational Intelligence for Multimedia Understanding, vol. 7252, Berlin Heidelberg: Springer, 2012, pp. 195-206. |
| , “Skeleton and shape adjustment and tracking in multicamera environments”, in Lecture notes in computer science, vol. 6169/2010, Berlin / Heidelberg: Springer, 2010, pp. 88–97. |
| , “Image and video processing tools for HCI”, in Multimodal signal processing: theory and applications for human-computer interaction, 2009, pp. 93–118. |
| , “Activity Classification”, in Computers in the Human Interaction Loop, London: Springer, 2009, pp. 107–119. |
| , “Head Orientation Estimation Using Particle Filtering in Multiview Scenarios”, in Multimodal Technologies for Perception of Humans, vol. 4625, Berlin / Heidelberg: Springer, 2008, pp. 317–327. |
Conference Papers top
| , “Refinement network for unsupervised on the scene foreground segmentation”, in EUSIPCO European Signal Processing Conference, 2020. |
|
, “One Shot Learning for Generic Instance Segmentation in RGBD Videos”, in International Conference on Computer Vision, Theory and Applications, Prague, 2019. (1.64 MB) |
|
, “HybridNet for Depth Estimation and Semantic Segmentation”, in ICASSP 2018, Calgary, Alberta, Canada, 2018. (1.14 MB) |
|
, “3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field”, in The 25th European Signal Processing Conference (EUSIPCO 2017), Kos island, Greece, 2017. (2.34 MB) |
|
, “Graph based Dynamic Segmentation of Generic Objects in 3D”, in CVPR SUNw: Scene Understanding Workshop, Las Vegas, US, 2016. (956.15 KB) |
Theses top
| , “Semantic and Generic Object Segmentation for Scene Analysis Using RGB-D Data”, Universitat Politècnica de Catalunya (UPC), download link, 2018. |
|
, “Stochastic optimization and interactive machine learning for human motion analysis”, UPC, Barcelona, 2014. (17.16 MB) |
|
, “Parametric Region-Based Foreground Segmentation in Planar and Multi-View Sequences”, Universitat Politècnica de Catalunya (UPC), 2013. (70.23 MB) |
|
, “Human Motion Capture with Scalable Body Models”, Universitat Politècnica de Catalunya (UPC), 2009. (13.45 MB) |
| , “A Unified Framework for Consistent 2D/3D Foreground Object Detection”, Universitat Politècnica de Catalunya (UPC), 2008. |
Other top
| , “Video coding method and corresponding coding and decoding systems”, U.S. Patent 9693276.5-1997. | Patent |
|
, “Segmented Picture Coding Method and System and Corresponding Decoding Method and System”, U.S. Patent 964009161-1996. (2.27 MB) |
Patent |
Projects top
 |
MALEGRA - Multimodal Signal Processing and Machine Learning on Graphs | National | Jan 2017 | Jun 2021 |
 |
BigGraph - Heterogeneous information and graph signal processing for the Big Data era. Application to high-throughput, remote sensing, multimedia and human computer interfaces. | National | Jan 2014 | Dec 2017 |
 |
SGR14 - Image and Video Processing Group | National | Jan 2014 | Apr 2017 |
 |
MuViPro - Multicamera Video Processing | National | Jan 2011 | Aug 2014 |
 |
SGR09 - Processament de Video Multicamera | National | Oct 2009 | Dec 2013 |
Demos and Resources top
 |
Temporally Coherent 3D Point Cloud Video Segmentation in Generic Scenes | Results | Aug 2017 |
 |
3D Point Cloud Segmentation using a Fully Connected Conditional Random Field | Results | Mar 2017 |
 |
Interactive registration for 3D data fusion | Demo | Jul 2016 |
 |
Graph based Dynamic Segmentation of Generic Objects in 3D | Results | May 2016 |
 |
Human manipulation dataset | Dataset | Feb 2016 |