Y
Yan Lu
Researcher at University UCINF
Publications - 7
Citations - 144
Yan Lu is an academic researcher from University UCINF. The author has contributed to research in topics: Active appearance model & Tree (data structure). The author has an hindex of 6, co-authored 7 publications receiving 132 citations. Previous affiliations of Yan Lu include University of Delaware.
Papers
More filters
Proceedings ArticleDOI
Simplified markov random fields for efficient semantic labeling of 3D point clouds
Yan Lu,Christopher Rasmussen +1 more
TL;DR: This paper proposes to use simplified Markov networks to model the contextual relations between points, where the node potentials are calculated from point-wise classification results using off-the-shelf classifiers, and the edge possibles are set by physical distance between points.
Proceedings ArticleDOI
Appearance contrast for fast, robust trail-following
TL;DR: This shape-based visual trail tracker assumes that the approaching trail region is approximately triangular under perspective, and generates region hypotheses from a learned distribution of expected trail width and curvature variation, and scores them using a robust measure of color and brightness contrast with flanking regions.
Book ChapterDOI
A Trail-Following Robot Which Uses Appearance and Structural Cues
TL;DR: A wheeled robotic system which navigates along outdoor “trails” intended for hikers and bikers through a combination of appearance and structural cues derived from stereo omnidirectional color cameras and a tiltable laser range-finder, which is able to detect and track rough paths despite widely varying tread material, border vegetation, and illumination conditions.
Proceedings ArticleDOI
Tree trunk detection using contrast templates
Yan Lu,Christopher Rasmussen +1 more
TL;DR: A bank of bar filters parametrized from camera intrinsics combined with trunk location and diameter limits are applied, and results vertically are integrated vertically, and non-maximum suppression is applied to candidates in the resulting trunk likelihood image.
Proceedings ArticleDOI
Trail following with omnidirectional vision
TL;DR: A system which follows “trails” for autonomous outdoor robot navigation through a combination of visual cues provided by stereo omnidirectional color cameras and ladar-based structural information is described, able to detect and track rough paths despite widely varying tread material, border vegetation, and illumination conditions.