V
Vincent Rabaud
Researcher at University of California, San Diego
Publications - 13
Citations - 12414
Vincent Rabaud is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Structure from motion & Nonlinear dimensionality reduction. The author has an hindex of 10, co-authored 13 publications receiving 10217 citations. Previous affiliations of Vincent Rabaud include Willow Garage.
Papers
More filters
Proceedings ArticleDOI
ORB: An efficient alternative to SIFT or SURF
TL;DR: This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.
Proceedings ArticleDOI
Behavior recognition via sparse spatio-temporal features
TL;DR: It is shown that the direct 3D counterparts to commonly used 2D interest point detectors are inadequate, and an alternative is proposed, and a recognition algorithm based on spatio-temporally windowed data is devised.
Proceedings ArticleDOI
Counting Crowded Moving Objects
Vincent Rabaud,Serge Belongie +1 more
TL;DR: This work bases its approach on a highly parallelized version of the KLT tracker in order to process the video into a set of feature trajectories and proposes a simple means of spatially and temporally conditioning the trajectories.
Proceedings ArticleDOI
Keyframe-based Visual-Inertial SLAM using Nonlinear Optimization
TL;DR: A novel approach to tightly integrate visual measurements with readings from an Inertial Measurement Unit (IMU) in SLAM using the powerful concept of ‘keyframes’ to maintain a bounded-sized optimization window, ensuring real-time operation.
Proceedings ArticleDOI
Re-thinking non-rigid structure from motion
Vincent Rabaud,Serge Belongie +1 more
TL;DR: This work presents a novel approach to non-rigid structure from motion (NRSFM) from an orthographic video sequence, based on a new interpretation of the problem, which only assumes that small neighborhoods of shapes are well-modeled with a linear subspace.