This paper develops and investigates a new approach for evaluating feature based object hypotheses in a direct way. The idea is to compute a feature likelihood map (FLM), which is ...
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single c...
Wei Zhang, Akshat Surve, Xiaoli Fern, Thomas G. Di...
We present an object detection and tracking algorithm that addresses the problem of multiple simultaneous targets tracking in realworld surveillance scenarios. The algorithm is bas...
: Several species of animals use whiskers to accurately navigate and explore objects in the absence of vision. We have developed inexpensive arrays of artificial whiskers based on ...
Aimee Schultz, Joseph Solomon, Michael A. Peshkin,...