With the rapid growth of the Internet and pervasive computing activities, the migration of back-end legacy systems to network centric environments has become a focal point for res...
In this paper we propose an approach to vehicle classification under a mid-field surveillance framework. We develop a repeatable and discriminative feature based on edge points an...
We derive a new class of photometric invariants that can be used for a variety of vision tasks including lighting invariant material segmentation, change detection and tracking, a...
Srinivasa G. Narasimhan, Visvanathan Ramesh, Shree...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...