P
Peter Henry
Researcher at University of Washington
Publications - 23
Citations - 5587
Peter Henry is an academic researcher from University of Washington. The author has contributed to research in topics: Cyberstalking & Law enforcement. The author has an hindex of 15, co-authored 21 publications receiving 4915 citations. Previous affiliations of Peter Henry include University of Texas Southwestern Medical Center & Florida State University.
Papers
More filters
Journal ArticleDOI
RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments
TL;DR: This paper presents RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment to achieve globally consistent maps.
Proceedings ArticleDOI
End-to-End Learning of Geometry and Context for Deep Stereo Regression
TL;DR: A novel deep learning architecture for regressing disparity from a rectified pair of stereo images is proposed, leveraging knowledge of the problem’s geometry to form a cost volume using deep feature representations and incorporating contextual information using 3-D convolutions over this volume.
Book ChapterDOI
RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments
TL;DR: This paper presents RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment to achieve globally consistent maps.
Book ChapterDOI
Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera
Albert S. Huang,Abraham Bachrach,Peter Henry,Michael Krainin,Daniel Maturana,Dieter Fox,Nicholas Roy +6 more
TL;DR: A system for visual odometry and mapping using an RGB-D camera, and its application to autonomous flight, which enables 3D flight in cluttered environments using only onboard sensor data.
Posted Content
End-to-End Learning of Geometry and Context for Deep Stereo Regression
Alex Kendall,Hayk Martirosyan,Saumitro Dasgupta,Peter Henry,Ryan Kennedy,Abraham Bachrach,Adam Bry +6 more
TL;DR: In this paper, the authors propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images, which leverages knowledge of the problem's geometry to form a cost volume using deep feature representations.