The objective of this course is to give students a hands-on introduction to the fundamentals of computer vision. Topics include: image formation, image processing, feature detection and matching, segmentation, feature-based alignment, structure from motion dense motion estimation, image stitching, stereo correspondence, 3D shape reconstruction, and object recognition. Upon completion of this course, students should be prepared to read current papers in computer vision and to undertake research in this area. Prerequisites: Programming experience in C/C++ in a UNIX environment, some background in digital image processing or computer graphics.
"Computer Vision: Algorithms and Applications" by Richard Szeliski, which is available in PDF format at http://szeliski.org/Book. We will also use the open source computer vision library OpenCV at http://opencv.willowgarage.com.
Final grades in this class will be determined by a weighted average of programming project scores and exam scores as follows:
We use the following scale to assign final grades:
Programming Projects: There will be 6-8 relatively large programming projects that will integrate material taught in the course. The project requirements and due dates will be posted on the class website. The programming projects will be graded according to the following scale:
Programming projects must be submitted electronically by midnight of the due date specified in the project description. Projects which are submitted within 24 hours of the due date will lose 50% of their grade. Projects will NOT be accepted beyond this 24 hour period. Partial credit will be given for programs which compile but which are not complete. Starting early on programming projects is strongly encouraged.
Exams: There will be two exams in this class. One midterm exam and a comprehensive final exam. All exams will be closed book, but each student will be allowed to bring in a single 8.5 by 11 sheet of notes. Calculators will not be needed or allowed. Make up exams will only be allowed under exceptional circumstances (e.g., a note from your doctor).
As a core part of its mission, the University of Arkansas provides students with the opportunity to further their educational goals through programs of study and research in an environment that promotes freedom of inquiry and academic responsibility. Accomplishing this mission is only possible when intellectual honesty and individual integrity prevail.
Each University of Arkansas student is required to be familiar with and abide by the University's 'Academic Integrity Policy' which may be found at http://provost.uark.edu/245.php. Students with questions about how these policies apply to a particular course or assignment should immediately contact their instructor.
The following policies will apply to this class:
Violations of these policies will be punished according to the 'Academic Integrity Sanction Rubric' http://provost.uark.edu/246.php. Depending on the violation level, this may result in a grade of ZERO on an exam or project, a grade of F in the class, or suspension from the University of Arkansas.