This course is devoted to computer vision problems: Finding of correspondences between images using image features and their robust invariant descriptors, features matching, picture stitching, object and segment recognition in pictures or video, image retrieval and object tracking in the video sequences.
The computer vision methods course expects programming skills in MATLAB computing environment. The programing assignments solving various computer vision methods are a substantial part of the labs. The attendee is expected to know basics of digital image processing as convolution, filtration, intensity transformations, image function interpolations and basic geometric transformations of the image (see the first lab). The attended is also expected to govern basics of linear algebra and probability theory.
Lecturers: JM Jiří Matas, JC Jan Čech, OD Ondřej Drbohlav
|1||19.2.||JC||Correspondence I-III |
|Interest point and distinguished regions detection: Harris operator (corner detection), Laplace operator and its approximation by difference of Gaussians, affine covariant version, Maximally Stable Extremal Regions (MSER).|
|2||26.2.||JM|| Correspondence I-III |
|Descriptors of measurement regions: SIFT (scale invariant feature transform), shape context. Local affine frames for geometric and photometric invariance of description.|
|3||5.3.||JM|| Correspondence I-III |
|SIFT variants, LBP (local binary patterns), Finding correspondences and object recognition using local invariant description.|
|RANSAC. Image Retrieval for large image collections: image description, indexing, geometric consistency.|
|5||19.3.||JC||Deep learning||A shallow introduction into the deep machine learning.|
|6||26.3.||JC||Deep learning II||Deep learning for object detection. Further insights into the deep nets.|
|8||9.4.||JM||Tracking I-III||Tracking I. Introduction. KLT tracker, Flock of Trackers.|
|9||16.4.||JM||Tracking I-III mean shift||Tracking II. Means Shift. Tracking by Detection.|
|10||23.4.||JC||Tracking I-III, KCF Tracking||Tracking III. TLD: Tracking-Learning-Detection, KCF Kernel Correlation Filter.|
|11||30.4.||JM||Viola-Jones face detector, Waldboost||Object detection by sliding window and sequential decision making (Method of Viola and Jones, Waldboost)|
|12||7.5.||JM||Hough Transform||Detection of geometric primitives (lines, circles, elipses, etc.). Hough transform and its comparison with RANSAC(Random Sample Consensus).|
Work during the semester 50%, written part of the exam 40%, oral part of the exam 10%
Examples of exam questions. There will be 4-5 similar questions at the written part of the exam. The oral part of the questions takes place after the written part and will focused on discussion of your answers.
Further informations are available in next sections of this page, we would appreciate your feedback on content and organization on the discussion forum of the course.
Good luck to all participants of the course.