Computer Vision and Image Processing

At the end of this course, the students should be able to: 1. explain the basic algorithms, tools and systems for the management, processing and analysis of digital images; 2. identify basic concepts, terminology, theories, models and methods in the field of computer vision; 3. describe basic methods of computer vision related to multi-scale representation, edge detection and detection of other primitives, stereo, motion and object recognition; 4. assess which methods to use for solving a given problem, and analyse the accuracy of the methods; 5. develop and apply computer vision techniques for solving practical problems; 6. choose appropriate image processing methods for image filtering, image restoration, image reconstruction, segmentation, classification and representation;l 7. acquire good and practical skills in computer vision; and 8. design and develop simple systems oriented to real-world computer vision applications such as those requiring segmentation and classification of objects in digital images.

Computer vision and image processing are important and fast evolving areas of Mechatronics and Robotics. Student will get familiar with both established and emergent methods, algorithms and architectures. The course will enable students to apply computer vision and image processing techniques to solving various real-world mechatronics and robotics problems, and develop skills for research in the fields. Image formation, image filtering, edge detection and segmentation, morphological processing, registration, object recognition, object detection and tracking 3D vision. The topics may include but are not limited to: 1. Image formation and perception, image representation. 2. Image filtering: space- and frequency- domain filtering, linear and non-linear filters. 3. Morphological image processing. 4. Image geometric transformations, image registration. 5. Edge detection, image segmentation, active contours, and level set methods. 6. Object recognition, template matching, and classification. 7. Object detection and tracking: background modeling, kernel-based tracking, particle filters. 8. Camera models, stereo vision.