|
HU Credits:
2
Degree/Cycle:
1st degree (Bachelor)
Responsible Department:
Computer Sciences
Semester:
2nd Semester
Teaching Languages:
Hebrew
Campus:
E. Safra
Course/Module Coordinator:
Prof Mïichael Werman
Coordinator Office Hours:
Coordinate in advance
Teaching Staff:
Prof
Course/Module description:
Computer vision seeks to interpret the visual world in ways that replicate the astonishing capabilities of human perception. The input/output process can be succinctly described as inferring the high-level properties of the scene such as location and identities of objects, the surfaces that make the scene, the motion of the observer and other objects and the actions of the various objects (like people, animals). The input is merely a video, i.e., a collection of 2D images of the scene. Humans can readily infer a great deal of those properties from a single image. The goal of computer vision is to be able to do the same but by a computer algorithm.
The course will present the fundamental computational models behind scene interpretation, motion understanding and object recognition. We will focus on specific problems which have witnessed remarkable success including object recognition (faces, people), 3D reconstruction, segmentation and scene categorization. The student will be exposed to tools from statistical learning and image processing while obtaining an understanding of key leading techniques for the main problems of computer vision: recognition, reconstruction and segmentation.
Course/Module aims:
Computer vision seeks to interpret the visual world in ways that replicate the astonishing capabilities of human perception. The input/output process can be succinctly described as inferring the high-level properties of the scene such as location and identities of objects, the surfaces that make the scene, the motion of the observer and other objects and the actions of the various objects (like people, animals). The input is merely a video, i.e., a collection of 2D images of the scene. Humans can readily infer a great deal of those properties from a single image. The goal of computer vision is to be able to do the same but by a computer algorithm.
Learning outcomes - On successful completion of this module, students should be able to:
Students will master the theories of reconstruction, and visual recognition. Each of the above would be subject to a programming exercise
Attendance requirements(%):
93
Teaching arrangement and method of instruction:
Mixture of Power-Point and whiteboard writing.
Course/Module Content:
1) geometry (camera + projective + multicamera)
2) color + shading
Required Reading:
NA
Additional Reading Material:
NA
Grading Scheme :
Written / Oral / Practical Exam 70 %
Submission assignments during the semester: Exercises / Essays / Audits / Reports / Forum / Simulation / others 30 %
Additional information:
Students are expected to know the material from Image Processing
The course will be mathematical/theoretical
|
close