Techniques for automated analysis of images and videos. Image formation, detecting features in images, segmenting or grouping image regions and image features, multiple view geometry, object instance and category recognition in images, and video processing
Why take this course?
Computers increasingly require the ability to "see" their surroundings in order to interact with humans and with the three-dimensional world. This course introduces theory and techniques for analyzing the content of images. Applications of computer vision include robotics, autonomous vehicle navigation, industrial automation, content-based search in image databases, face and gesture recognition, and aids for the seeing-impaired.
3574 and (STAT 4705 or STAT 4714)
The course is senior level as it draws knowledge from the listed prerequisite courses which are taught in the junior year. The listed prerequisite courses cover relevant material which includes basic concepts of probability and statistics (random variables, expectation, conditional distributions, Bayes rule, likelihood, maximum likelihood).
Major Measurable Learning Objectives
contrast common image formation models
extract various features from images
segment an image into meaningful regions
derive the theory behind multi-view geometry
implement various approaches to recognizing objects and scenes in images
process video sequences
Percentage of Course
1. Features and filters: Image formation, low-level vision including linear filters, extracting edges and contours from images, binary image analysis, analyzing texture in images
2. Grouping and fitting: Mid-level vision including image segmentation and clustering algorithms, approaches to fit models to image features
3. Multi-view geometry and motion: Vision from multiple views and motion including local invariant image feature detection and description, image transformations and alignment, planar homography, epipolar geometry and stereo
4. Recognition: High-level vision including recognition of objects (instances and categories) and scenes, face detection and recognition
5. Video processing: Processing temporal sequences of images (frames) including optical flow, motion descriptors, tracking and activity recognition