lec2

lec2 - Lecture 2 Course Enrollment Those on waiting list...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2008 Copyright 2008, by R. Nevatia 1 Lecture 2: Aug 25, 10 • Course Enrollment – Those on waiting list will be admitted as slots open • Must continue to attend class (provided seating is available) • Must hand in HW 0 • Decisions by next Wednesday • Grading – 30% assignments, 25% exam 1, 35% exam 2, 10% attendance and participation – Exam dates: ~Oct 13 and Dec 3 (raise objections today, if any) – Academic integrity: rules for cooperation on assignments • Today’s objective – Problems of vision – Course syllabus outline – Image formation in human visual system and in cameras
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2008 Copyright 2008, by R. Nevatia 2 Why is Vision Hard? • Last class: – Issues of representation: what is a chair? what does a pen look like? – Projection from 3-D to 2-D, occlusions – Problems of figure/ground separation – Image Segmentation – Influence of context in interpretation
Background image of page 2
USC CS574: Computer Vision, Fall 2008 Copyright 2008, by R. Nevatia 3 Video Analysis • Adds difficulties of detecting and tracking moving objects – If camera also moves, we need to distinguish between object and background motion • We want to detect not only objects but also events in the video • Make inferences about the intentions/plans of actors • This course will cover motion analysis only briefly or not at all (though is the major topic of research in the USC vision group at this time).
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
USC CS574: Computer Vision, Fall 2008 Copyright 2008, by R. Nevatia 4 How can we solve these problems? • Imitate biology – We can learn some lessons but biological vision is not well understood • Invert the imaging process – Image formation (graphics) is relatively well understood: in graphics given a scene and a camera, goal is to create a realistic image – Inverse problems are difficult, mapping is one to many; however, knowledge of image formation is essential to study of visual perception – Knowledge of the world is important in addition to image formation • Perception is a complex process, likely to proceed in stages – Evidence in biological vision (areas of human visual systems)
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 19

lec2 - Lecture 2 Course Enrollment Those on waiting list...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online