Persons
prof. Ing. Jiří Matas, Ph.D.
head_person_supervisor
Supervisor specialist
Archive of PhD students
Ing. Tomáš Vojíř, Ph.D.
Short-Term Visual Object Tracking in Real-Time
Mgr. Jan Šochman, Ph.D.
Learning for Sequential Classification
Mgr. Dmytro Mishkin, Ph.D.
Learning and Crafting for the Wide Multiple Baseline Stereo
Ing. Lukáš Neumann, Ph.D.
Scene text localization and recognition in images and videos
prof. Mgr. Ondřej Chum, Ph.D.
Two-view Geometry Estimation by Random Sample and Consensus
doc. Ing. Karel Zimmermann, Ph.D.
Fast Learnable Methods for Object Tracking
Ing. Štěpán Obdržálek, Ph.D.
Object Recognition Using Local Affine Frames
Dissertation topics
Detection and recognition of text „in the wild“.
- Branch of study: Computer Science – Department of Cybernetics
- Department: Department of Cybernetics
-
Description:
The problem of text detection an recognition has many application. The open problems include: reliable detection of characters and word in any script, font and language; grouping of strokes, characters and words into a linear sequences, and modelling and detection of higher level structures such as blocks and displays. The thesis will focus on one of the open problems listed above. http://cmp.felk.cvut.cz/~matas/
Recognition of objects in images and videos
- Branch of study: Computer Science – Department of Cybernetics
- Department: Department of Cybernetics
-
Description:
Object recognition encompasses a broad range of problems ranging from two view matching of images of a given object, image retrieval and discovery of objects in collections of images and perhaps the most challenging problem of categorisation. The thesis will focus on one of the open problems listed above. http://cmp.felk.cvut.cz/~matas/
Visual tracking, motion estimation and segmentation
- Branch of study: Computer Science – Department of Cybernetics
- Department: Department of Cybernetics
-
Description:
Visual tracking is a broad area of research that deals with estimating the state of one or more a priori know or unknown objects in sequences captured by one or more cameras with overlapping on non-overlapping fields of view. The state might be as simple as a single point (estimating location), a rectangle – an approximation of the segmentation, location, scale and possibly orientation, full pixel-wise segmentation, or a per-pixel displacement field, especially in the case of articulated or deformable objects. The problem can be restricted to sequences without significant occlusion (short-term tracking); the more general setting consider cases where the object leaves the field of view or is fully occluded (long-term tracking). If the object is not known a priori (model-free tracking), the problem entails learning the model of the tracked object, typically its appearance but potentially its shape as well. There are many open problems in visual tracking; the field is highly active with hundreds of papers published at major conference and top journals.
