GPU-based Video Feature Tracking And Matching

By Sudipta N. Sinha, Jan-Michael Frahm, Marc Pollefeys, Yakup Genç. 2006

384 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7f3f22fa33da96c08615abb156a03723dfa01a1e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Subspace video stabilization (2011, methodology): “The KLT tracker we used achieves 7 fps when it is tuned to track roughly 500 feature points per frame on the input videos, which are resized to 640 ×360; note that others have developed GPU-accelerated real-time versions [Sinha et al. 2006].”
ORB: An efficient alternative to SIFT or SURF (2011, background): “The efficiency is tested on several real-world applications, including object detection and patch-tracking on a smart phone.”
Visual simultaneous localization and mapping: a survey (2012, methodology): “2010) and GPU-SIFT, an implementation of SIFT on a GPU (Graphics Processing Unit) in order to make processing in parallel and in real time (Sinha et al. 2006).”
Activity recognition using the velocity histories of tracked keypoints (2009, background): “Recent GPU-based implementations of this algorithm can run in real time [21].”
Robotic Hand Pose Estimation Based on Stereo Vision and GPU-enabled Internal Graphical Simulation (2016, background): “Some authors state that it is possible to achieve a speed-up of almost 10 times [40] in high-level computer vision algorithms, when more conservative ones, and in a wider perspective, claim for 2.5 times on average [24].”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, background): “But this performance is veriﬁed only when there is no substantial scale change between the images and if the images contain highly contrasted objects.”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, unknown): “GPU [123] so that it can be used in AR applications.”