CAP 5415 Computer Vision General n n n

CAP 5415 Computer Vision

General n n n Instructor: Dr. Alper Yilmaz Email: yilmaz@cs. ucf. edu Office: CSB 250

Course n Office hours n n n Grading n n n Midterms (2) 20% Final 30% Assignments (bi-weekly) %20 Projects (2) %30 Class notes n n Monday 3. 00 pm-4. 30 pm Wednesday 3. 00 pm-4. 30 pm “Fundamentals of computer vision”, Dr. Mubarak Shah available on web page (http: //www. cs. ucf. edu/courses/cap 6411/book. pdf) Text book n “Introductory Techniques for 3 D Computer Vision” Trucco and Verri, Prentice Hall.

Topics We’ll Cover n n n n n Imaging Geometry Camera Modeling and Calibration Filtering and Enhancing Images Region Segmentation Color and Texture Line and Curve Detection Shape Analysis Stereo We may change order Motion and Optical Flow Structure from X

Computer Vision n Image Analysis n n n Single frame Image Understanding Video Analysis n n Multiple frames, temporal information Video Understanding

Generating an Image n 3 D Scene n n Surface reflectance Surface structure (shape) Light source Camera

Perspective Projection 3 D world (X, Y, Z) f Pin hole camera Image plane y Z

Orthographic Projection 3 D world (X, Y, Z) y Image plane Z

Discrete Domain Image n Set of integer values in two dimensions n n Gray level image (1 matrix n n 0: Black 255: White Color image (3 matrices) n n 0 -255 Red, Green, Blue Resolution n Number of rows, number of columns

Video n Sequence of image n n n Frames per second Gray level video Color video

Digitization n Analog camera n n n Analog to Digital converter Frame grabber Digital camera n n Already digitized MPEG or JPEG

Image Formats n n n n TIFF JPEG PGM, PPM PNM BMP MPEG Quick Time…

Computer Vision n Shape From “X” n n Shading (single image) Texture (single image) Stereo (two images) Motion (multiple images)

Stereo

http: //www. vision 3 D. com/stereo. html

Example

Stereo Pair

Stereo Fun candy dinosaur shark

Shape from Shading

Lambertian Surface Model surface normal light source

Sphere Example

Vase Image (1, 0, 1) (-1, 1, 1) (-1, 1)

Object Motion Video Sequence of images

An Image from Hamburg Taxi Sequence

Video Mosaics

Vision Lab. Sequence

Beach Volley Sequence

Sprite

Tracking in Multiple Cameras n n n Find field of view (FOV) lines Detect objects Associate objects

Story Segmentation

Explosion/fire Detection