Differences

This shows you the differences between two versions of the page.

--- project [2013/09/18 21:52] – wildes
+++ project [2017/09/18 15:01] (current) – wildes
@@ Line 5: / Line 5: @@
 Students will be required to complete a computer vision project as a part of this course. This project will allow students to gain "hands on" experience with a computer vision research topic. Typically, projects will involve analytic, programming and testing components. Projects will consist of four parts, as follows.
-    * White Paper: Each student will select a particular topic for study and inform the instructor of their choice via a short (1-2 sentence) written description. The final topic selection is subject to the instructor's approval. A list of suggested topics is provided below. Topics other than those listed may be acceptable; however, it a good idea to check with the instructor as early as possible for such cases. Due date: 4 October 2013.
+    * White Paper: Each student will select a particular topic for study and inform the instructor of their choice via a short (1-2 sentence) written description. The final topic selection is subject to the instructor's approval. A list of suggested topics is provided below. Topics other than those listed may be acceptable; however, it a good idea to check with the instructor as early as possible for such cases. Due date: 4 October 2017.
-    * Proposal: Each student will submit to the instructor a brief (1 page) proposal for their project. This will extend on the topic selection by (i) motivating the area of investigation (explaining why it is interesting), (ii) describing an approach (providing a plan of attack), including what problem analyses, implementations and testing you intend to perform and (iii) suggesting possible outcomes. Due date: 21 October 2013.
+    * Proposal: Each student will submit to the instructor a brief (1 page) proposal for their project. This will extend on the topic selection by (i) motivating the area of investigation (explaining why it is interesting), (ii) describing an approach (providing a plan of attack), including what problem analyses, implementations and testing you intend to perform and (iii) suggesting possible outcomes. Due date: 25 October 2017.
-    * Site Visit: Each student will make a brief verbal report of their progress; students are encouraged to provide preliminary demonstrations of any software that is being developed at this time. Due Date: Presentations will be made in the lab (1006B LAS), 18 November 2013.
+    * Site Visit: Each student will make a brief verbal report of their progress; students are encouraged to provide preliminary demonstrations of any software that is being developed at this time. Due Date: Presentations will be made in the lab session during week 10.
-    * Final Demo: A final written report (approximately 5 pages) that documents the results of the student's investigations will be will be delivered to the instructor. Further, each student will provide a demonstration/discussion of their project results in front of the class. The software program that results as part of the project must be callable from the command line with argument of pgm image(s), as appropriate to the particular problem considered: This will allow the instructor to test the program during the final demo. For students enrolled in CSE 5323 only, the final written report also will be required to have an appendix (beyond the 5 page main body of the report), which is comprised of an annotated bibliography of references to the primary literature that is related to the project. Due Date: Written reports due at start of class 29 November 2013; in lab demonstrations will be conducted during the last several lecture periods beginning the same day.
+    * Final Demo: A final written report (approximately 5 pages) that documents the results of the student's investigations will be will be delivered to the instructor. Further, each student will provide a demonstration/discussion of their project results in front of the class. The software program that results as part of the project must be callable from the command line with argument of pgm image(s), as appropriate to the particular problem considered: This will allow the instructor to test the program during the final demo. For students enrolled in EECS 5323 only, the final written report also will be required to have an appendix (beyond the 5 page main body of the report), which is comprised of an annotated bibliography of references to the primary literature that is related to the project. Due Date: Written reports due at start of class 27 November 2017; in lab demonstrations will be conducted during the final lab session as well as the last several lecture periods.
 ==== Laboratory Facilities ====
-Computer Science and Engineering Department laboratory facilites will be available for support of projects. Details TBA.
+Electrical Engineering and Computer Science Department laboratory facilites will be available for support of projects. Documentation of the lab is available under the Syllabus link on the sidebar to this page.
 ==== Suggested Topics ====
+<html>
+<!--
+-->
+</html>
 Following is a list of suggested topics for this course as well as brief descriptions. If further discussion of any of these topics is desired, then see the instructor.
@@ Line 29: / Line 34: @@
   * Algorithm comparisons: For any given research or application topic in computer vision there is more than one possible approach. For example, many different approaches to optical flow estimation have been developed. For this project, students will consider a particular topic (e.g., binocular stereo correspondence, optical flow estimation, shape from shading, etc.) and select at least two algorithms that have been developed for this topic. The student will compare the selected algorithms both analytically (to develop a theoretical understanding of their relationships) and empirically (to develop a practical understanding of their relationships. Since for this project the student will be comparing extant algorithms, it might be possible to acquire the necessary software without actually implementing the algorithms per se (e.g., from the web); however, probably more will be learned if the student implements their own versions. A restriction on this topic is that comparison of algorithms for edge detection is not an allowable topic; there has been a great deal of research on this topic, which will make it too difficult for students to make a novel contribution.