Laboratory for Pattern Recognition and Biometric Security Systems

Biography

Siniša Šegvić is an Associate Professor at the University of Zagreb, Faculty of Electrical Engineering and Computing, where he (co-)teaches one postgraduate and several undergraduate courses. He completed two one-year postdoc fellowships at IRISA Rennes, France, and TU Graz, Austria. He was a leader of a three-year project jointly funded by Croatian Science Foundation and industrial partners, co-leader of a two-year bilateral Croatian-Austrian research project, as well as a leader of two shorter research projects funded by the University of Zagreb and national ministry of science. He has participated at one FP7 REGPOT project, one FP6 MC IIF mobility project, one French research project, and several Croatian research projects. He speaks English and Italian very well, and has basic communication skills in French. He is a member of IEEE.

His research interests are in computer vision and machine learning with emphasis on applications of object detection, image motion analysis and multiple view geometry. His recent research activities in collaboration with industry and international research institutions include computer vision solutions for road safety inspection, airborne traffic surveillance and autonomous navigation.

Publications

Proceedings articles:

• Brkić, Karla; Pinz, Axel; Šegvić, Siniša; Kalafatić, Zoran. Histogram-Based Description of Local State-Time Appearance. // Proceedings of the Scandinavian Conference on Image Analysis; 206-217.
• Bonači, Igor; Kusalić, Ivan, Kovaček, Ivan; Kalafatić, Zoran; Šegvić, Siniša. Addressing false alarms and localization inaccuracy in traffic sign detection and recognition // Proceedings of the Computer Vision Winter Workshop. 1-8.
• Šegvić, Siniša; Brkić, Karla; Kalafatić, Zoran; Stanisavljević, Vladimir; Ševrović, Marko; Budimir, Damir; Dadić, Ivan. A computer vision assisted geoinformation inventory for traffic infrastructure // Proceedings of the IEEE Conference on Intelligent Transportation Systems. 66-73.
• Schweighofer, Gerald; Šegvić, Siniša; Pinz, Axel. Online/Realtime Structure and Motion for General Camera Models // Proceedings of Workshop on Applications of Computer Vision. 1-6.
• Šegvić, Siniša; Schweighofer, gerald; Pinz, Axel. Influence of the numerical conditioning to the accuracy of relative orientation // Computer Vision and Pattern Recognition, 2007. 1-8.
• Šegvić, Siniša; Schweighofer, Gerald; Pinz, Axel. Performance evaluation of the five-point relative pose with emphasis on planar scenes // Conference Proceedings of the 31st AAPR/OAGM Workshop. 33-40.
• Šegvić, Siniša; Remazeilles, Anthony; Chaumette, François. Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support. // Proceedings of the European Conference on Computer Vision. 3952 (2006) ; 112-124.

Journal articles:

• Šegvić, Siniša; Brkić, Karla; Kalafatić, Zoran; Pinz, Axel. Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle. // Machine Vision and Applications. Accepted for publication.
• Diosi, Albert; Šegvić, Siniša; Remazeilles, Anthony; Chaumette, François. Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing. // Ieee transactions on intelligent transportation systems. 12 (2011) , 3; 870-883.
• Šegvić, Siniša; Remazeilles, Anthony; Diosi, Albert; Chaumette, François. A mapping and localization framework for scalable appearance-based navigation. // Computer Vision and Image Understanding. 113 (2009) , 2; 172-187.
• Šegvić, Siniša; Ribarić, Slobodan. Determining the Absolute Orientation in a Corridor Using Projective Geometry and Active Vision. // IEEE Transactions on Industrial Electronics. 48 (2001) , 3; 696-710 (journal article).

Please note that a complete publication list with full-text pdf articles and video demonstrations is available from the personal web pages of the author.