Brian Fulkerson

Learn More
VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and students. It includes rigorous implementations of common building blocks such as feature detectors, feature extractors, (hierarchical) k-means clustering, randomized kd-tree matching, and(More)
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by(More)
The paper presents an exact GPU implementation of the quick shift image segmentation algorithm. Variants of the implementation which use global memory and texture caching are presented, and the paper shows that a method backed by texture caching can produce a 1050X speedup for practical images, making computation of super-pixels possible at 5-10Hz on modest(More)
Over the last decade, embedded sensing systems have been successfully deployed in a range of application areas, from education and science to military and industry. These systems are becoming more robust, capable, and widely adopted. Yet today, most sensor networks function in isolated patches, each with different mechanisms to deliver data to their users,(More)
Inside the mammalian nose lies a labyrinth of bony plates covered in epithelium collectively known as turbinates. Respiratory turbinates lie anteriorly and aid in heat and water conservation, while more posterior olfactory turbinates function in olfaction. Previous observations on a few carnivorans revealed that aquatic species have relatively large,(More)
tal exchange among the lithosphere, biosphere, and atmosphere. Understanding the rates of these exchanges, and the sequestration of elements within any pool, is becoming increasingly crucial to understanding soil processes and to sustainable management of local processes that are linked to the global climate. Indeed, scaling may be the single most difficult(More)
This paper presents the Golem Group/University of California at Los Angeles entry to the 2005 DARPA Grand Challenge competition. We describe the main design principles behind the development of Golem 2, the race vehicle. The subsystems devoted to obstacle detection, avoidance, and state estimation are discussed in more detail. An overview of vehicle(More)