Typically, projects will involve analytic, programming and testing components. Projects will consist of four parts, as follows. Please see the Schedule for deadlines.

• Project Idea: The student will propose a specific project idea in the form of a short paragraph, submitted via Moodle. The instructor will either accept the topic (possibly with modifications) or raise issues that the student will address in revision of the project idea. The final project selection is subject to the instructor's approval. Students are encouraged to select their own project independently, however a list of possible topics is provided below.
• Proposal: The proposal is a one-page document submitted via Moodle that includes: (i) Motivation: why is the topic interesting? (ii) Datasets: what datasets will you use to study the problem? (iii) Proposed methods: what algorithm(s) do you plan to implement? (iv) Evaluation methodology and (v) Proposed timeline for completion.
• Presentation/Demo: A brief slide presentation on the project will be made during one of the last two lecture meetings. There will also be an opportunity to demo the project during the final lab.
• Final Report: Maximum 8 pages, in CVPR 2018 format.

<!-- -->

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.

• Image formation: Since in computer vision we seek to recover information about the world from images, it is important to understand how the world information was projected into the images. Correspondingly, in lecture and in the textbook, various models of image formation have been described. For this topic, the student will further explore image formation. As a specific direction for investigation, one might study the effects of the approximations that are involved for various models of image projection (e.g., a quantitative comparison of the geometric ramifications of perspective vs. weak perspective vs. orthographic projection). Alternatively, one might embark on a quantitative exploration of optical aberrations (geometric and/or radiometric). The student also is welcome explore models of image formation that have not been covered in class (e.g., image formation using transmittance image formation, etc.). In any case, an appropriate methodology for this project would be to couple formal mathematical analysis with computer simulations of the models of concern.

• Image preprocessing: The output provided by a computer vision algorithm can be greatly improved via appropriate preprocessing of the input imagery. For example, techniques can be applied to suppress noise; alternatively, features of particular interest can be enhanced. For this topic, the student will select a computer vision algorithm that takes as its input one or more images (e.g., edge detection, optical flow estimation, etc.) and quantitatively evaluate the effects of one or more image preprocessing steps. Since the emphasis here is on how the preprocessing can help improve a computer vision algorithm of interest, it might be possible to acquire the necessary software for the algorithm whose performance you wish to improve without actually implementing it (e.g., from the web). In contrast, the preprocessing operations should be implemented by the student.

• Adaptive stereo vision: In our study of stereopsis, we will learn that a useful strategy is to begin our estimation procedures with coarse image data (e.g., imagery with low spatial resolution) and subsequently refine our solution through systematic incorporation of more refined image data (e.g., imagery with higher spatial resolution). We will refer to this paradigm as course-to-fine refinement. An interesting question that arises in this paradigm is how to decide on the level of refinement that is appropriate for a given image or even a given image region. For this project, the student will explore methods for automatically adapting the coarse-to-fine refinement of stereo estimates based on the input binocular image data and implement as well as test at least one such procedure.

• Primitive event recognition: Image sequences comprise a vast amount of data. For timely processing, it is critical that early operations begin to recognize significant patterns in this data. For example, when processing a video sequence, it might be desirable to make distinctions regarding those portions of the imagery that correspond to moving objects so that subsequent processing might attend to such regions. For this project, the student will suggest and investigate a set of simple, dynamic patterns or events that it might be advantageous to support through early processing (e.g., what is moving, what is not, what is noise, etc.). The student will develop an analysis that shows how the patterns can be distinguished on the basis of simple vision operations as well as implement and test corresponding algorithms.

• Module combination: Typically, a solitary computer vision module provides incomplete information about the world; however, taken in tandem (two or more) modules might combine forces to provide a better understanding of the impinging environment. For example, binocular stereo typically performs best in regions with well define features or texture patterns, but poorly in smoothly shaded regions; in contrast shape from shading can perform reasonably in smoothly shaded regions, but less well in highly textured regions. For this project, students will select a pair of complimentary vision modules (e.g., stereo and shading, feature-based and area-based image correspondence/matching for stereo, binocular stereo and motion, etc.) and study how they can be combined in an advantageous fashion. The student will develop an analysis that shows how the modules can be combined as well as implement and test corresponding algorithms.

• 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.