Lehigh CSE398/498

.
CSE398-011/498-010
Real-time Image Processing for Autonomous Robot Systems
TR 1:10-2:25 PM, Fall 2004

Announcements

24 Aug 04: First day of classes. Welcome!
02 Sep 04: No laboratory session today. Please come to lecture.
07 Sep 04: No laboratory session today. Please come to lecture.
14 Sep 04: Laboratory session today! Meet at PL322.
16 Sep 04: Laboratory session today! Meet at PL322.
21 Sep 04: Laboratory session today! Meet at PL322.
22 Sep 04: Lab report 1 due 23 Sep, Lab 2 due 24 Sep, Lab 3 due 29 Sep!
23 Sep 04: Laboratory session today! Meet at PL322.
28 Sep 04: Lectures have returned.
01 Oct 04: Lab 3 due by close of business (COB) the CSE office.
01 Oct 04: Lab 4 due by COB the CSE office.
14 Oct 04: For those new to Matlab, the this file might prove useful.
18 Oct 04: Assignment 1 is posted. Due date is 28 Oct 04.
31 Oct 04: Happy Halloween! Assignment 2 is posted Due date is 09 Nov 04.
08 Nov 04: Graduate student presentations begin on 18 Nov 04. Undergraduate attendance (and participation) is REQUIRED. If you miss these without notice, your class participation grade will be negatively affected.
09 Nov 04: Due to the additional session, the report for Lab 6 & Lab 7 is due 16 Nov 04.
15 Nov 04: The warping lecture is posted, along with a couple of links to relevant publications on pyramids.

Course Description

The Mars Exploration Rover (MER) employs no less than 8 cameras for sensing its environment. Cameras are a popular choice for robot sensing as they are compact, passive, require little power, and are a natural medium for human/robot interaction. This course will explore fundamental image processing and computer vision algorithms for autonomous robot operations, with additional applications to autonomous surveillance. In addition to lectures, classroom time will include laboratory sessions where algorithms will be implemented on camera and/or robot vision systems.

Topics will include (among others):

Image formation
Filtering Operations
Point operations
Feature Detection (colors, edges, corners, etc.)
Geometric Transformations
Pyramids
Image warping and alignment
Motion Dectection/Estimation
Target tracking

Prerequisites

Math 23 Analytic Geometry and Calculus III or equivalent
Math 205 Linear Methods or equivalent or equivalent
CSE 109 Systems Programming or equivalent programming experience in C/C++

Instructor
John Spletzer
Office Hours: TR 4:00-5:00 and by appointment

Course Location
Lectures: PL208
Laboratory Sessions: PL322

Course Materials
We will rely primarily on the class lecture notes, augmented by the following online materials. There is no required text for this course.

HyperMedia Image Processing Reference
CVOnline
Computer Vision Home Page
OpenCV - Intel's Open Source Computer Vision Library
Random Sample Consensus (RANSAC)

A one page summary from CVOnline
The original paper (15 pages - you can only access this from the Lehigh server)

The University of Leeds Vision Group Calibration Page. This covers Tsai's method, and includes a link to a related paper by Horn.
Caltech's Matlab Calibration Toolbox
An INRIA paper on real-time correlation based stereo by Faugeras et al
The Middlebury Stereo Vision Research Page has resources for regarding steropsis.
Pyramids:

Grading
This course is intended to be applied. As such, class lectures will be supplemented by laboratory sessions where students will implement relevant algorithms. Grading will be based primarily on laboratory assignment participation and reports. The latter are to be submitted at the following lecture.

There will be an additional paper presentation to satisfy the 400-level requirement.

There will be no exams for this course.

The breakout of course grading is as follows:

Laboratory assignments/reports: 80%
Lecture attendance/participation - particularly for the paper presentations (undergrad): 20%
Paper presentation (graduate credit): 20%

ALL ASSIGNMENTS MUST BE SUBMITTED IN ORDER TO RECEIVE A PASSING GRADE IN THIS CLASS.

Grades will be assigned acording to the following distribution:
.

A	92-100	C	72-76
A-	90-91	C-	70-71
B+	87-89	D+	67-69
B	82-86	D	62-66
B-	80-81	D-	60-61
C+	77-79	F	00-59

Late Policy: Assignments are due PRIOR to class on the due date. Late assignments will not be accepted UNLESS you have made arrangements with the instructor prior to the due date.

University Policy on Disabilities: If you have a disability for which you are or may be requesting accommodations, please contact your professor and the Office of Academic Services, Room 212, University Center or call (610-758-4152) as early as possible in the semester. University policy states that you must notify your professor seven (7) days prior to the exam.

Tentative Schedule
.

DATE	TOPICS	NOTES	ASSIGNMENT
24 Aug 04	Course overview	23Aug04_Overview.htm
26 Aug 04	Image Formation	26 Aug 04
31 Aug 04	Image Convolution and Filtering	31 Aug 04
02 Sep 04	Feature Detection: Edges	02 Sep 04
07 Sep 04	Feature Detection 2: Lines and Corners	07 Sep 04
14-16 Sep 04	Vision Labs: Remote Surveillance and Monitoring Real-time Edge Detection		Lab 1 Lab 2
09 Sep 04	Feature Detection 3: Color in Images	09 Sep 04
21 Sep 04	Vision Lab: Real-time Color Segmentation		Lab 3
23 Sep 04	Vision Lab: OpenCV		Lab 4
28 Sep 04	Camera Models & Coordinate Transformations	28 Sep 04
30 Sep 04	Class cancelled
05 Oct 04	Image Transformations and Camera Calibration	05 Oct 04
07 Oct 04	Pacing Break (No Class)
12 Oct 04	Calibration	12 Oct 04
15 Oct 04	Vision Lab: Camera Calibration		Lab 5
19 Oct - 21 Oct 04	Stereopsis	19 Oct 04 21 Oct 03	Homework 1 Left Image Right Image
26 Oct 04	Image Processing in the Frequency Domain	26 Oct 04	Homework 2 Test Image
28 Oct 04	Pyramids	28 Oct 04
02 Nov - 09 Nov 04	Vision Labs		Lab 6 Lab 7
11 Nov 04	Image Warping	11 Nov 04
16 Nov 04	Vision Lab 8		Lab 8
18 Nov 04	Graduate Student Presentations (Spencer & Thorne)
20 Nov 04	Graduate Student Presentations (Chen & Derenick)
25 Nov 04	Thanksgiving (no class)
30 Nov 04	Graduate Student Presentations (Grabowski & Moll)
02 Dec 04	Graduate Student Presentations (Erekson & Mansley)