Jayan Eledath, Program Director at SRI International, presents the "Tools for 'Democratizing' Computer Vision" tutorial within the "Algorithm Development Techniques and Tools" technical session at the October 2013 Embedded Vision Summit East.
Computer vision has matured to a point where it is beginning to be widely deployed in several real-world applications. This has led to significant growth in the number of vision algorithm and application developers and their communities. However, this growth has resulted in a vast and cluttered landscape of algorithms, many of which have limited capabilities. What is needed, is an efficient means of assessing the performance of these algorithms across imaging domains, and of identifying the best algorithms for specific applications.
Under the DARPA Visual Media Reasoning program, SRI has developed automated performance characterization (APC) tools for just this purpose. This talk describes our framework and system for answering the following questions for detection algorithms:
- How well will an algorithm perform for a given image at a chosen parameter setting; and
- What parameters should be used for a particular algorithm and image.
Eledath also describes how detection probabilities can be modeled as a function of both algorithm parameters and image characteristics. Finally, he shows a live demonstration of the APC tool.