S
S.J. Krotosky
Researcher at University of California, San Diego
Publications - 9
Citations - 342
S.J. Krotosky is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Object detection & Image registration. The author has an hindex of 8, co-authored 9 publications receiving 332 citations. Previous affiliations of S.J. Krotosky include University of California.
Papers
More filters
Journal ArticleDOI
On Color-, Infrared-, and Multimodal-Stereo Approaches to Pedestrian Detection
S.J. Krotosky,Mohan M. Trivedi +1 more
TL;DR: This paper designs a four-camera experimental testbed consisting of two color and two infrared cameras for capturing and analyzing various configuration permutations for pedestrian detection and proposes a multimodal trifocal framework consisting of a stereo pair of color cameras coupled with an infrared camera.
Journal ArticleDOI
Mutual information based registration of multimodal stereo videos for person tracking
S.J. Krotosky,Mohan M. Trivedi +1 more
TL;DR: Ground truth experiments demonstrate the utility of the disparity voting techniques for multimodal registration by yielding qualitative and quantitative results that outperform approaches that do not consider occlusions.
Proceedings ArticleDOI
A Comparison of Color and Infrared Stereo Approaches to Pedestrian Detection
S.J. Krotosky,Mohan M. Trivedi +1 more
TL;DR: This paper designs a four camera experimental testbed consisting of two color and two infrared cameras that allows for synchronous capture and direct frame-by-frame comparison of pedestrian detection approaches, and conducts comparative experiments of stereo-based approaches to obstacle detection using color and infrared imagery.
Proceedings ArticleDOI
Face detection and head tracking using stereo and thermal infrared cameras for "smart" airbags: a comparative analysis
TL;DR: This paper reviews both a stereo-based and long wave infrared-based system for "smart" airbag deployment and shows the feasibility of each video based occupant position analysis system.
Proceedings ArticleDOI
Multimodal Stereo Image Registration for Pedestrian Detection
S.J. Krotosky,Mohan M. Trivedi +1 more
TL;DR: A robust method using disparity voting for determining the registration of each object in the scene is developed and a statistically based measure is provided for evaluating the match confidence.