Francesc Serratosa
Universitat Rovira i Virgili, Universitat Politècnica de Catalunya
Papers
12
Total Citations
232
H-Index
6
About
Francesc Serratosa is a leading researcher in computer vision and robotics, whose work bridges graph-based image analysis and multi-robot perception. His seminal 2002 paper on graph-based representations for image processing (96 citations) laid foundational methods for matching visual structures, while his 2006 study on signatures versus histograms (54 citations) clarified key distance metrics for feature comparison. Serratosa has made major contributions to pose estimation, developing interactive and cooperative frameworks that integrate human guidance with autonomous systems. His work on partially supervised correspondence (2014, 26 citations) and cooperative pose estimation for robot fleets (2015, 15 citations) addresses real-world challenges in alignment and consensus among multiple agents. Notably, he pioneered the use of SIFT descriptors for graph matching in mobile robot pose recovery (2010), enhancing robustness in dynamic environments. His research on the MARCO robot (2001) demonstrated early integration of learning and perception for indoor navigation. With over 220 total citations across his top papers, Serratosa’s impact lies in advancing both theoretical graph matching and practical multi-camera, multi-robot systems, making him a key figure in interactive and cooperative computer vision.
Research Focus
Key Achievements
Top Papers
- 1
- 2Signatures versus histograms: Definitions, distances and algorithms54 citations · 2006
- 3
- 4
- 5Consensus of multiple correspondences between sets of elements10 citations · 2015
- 6
- 7Online human assisted and cooperative pose estimation of 2D cameras6 citations · 2016
- 8
- 9
- 10