Only released in EOL distros:
Package Summary
The SiftGPU library is an implementation of SIFT for GPU.
- Author: Changchang Wu (library), Bence Magyar (ROS wrapper)
- License: non-profit license from University of North Carolina
- Source: git https://github.com/pal-robotics/perception_blort.git (branch: electric)
Package Summary
The SiftGPU library is an implementation of SIFT for GPU.
- Author: Changchang Wu (library), Bence Magyar (ROS wrapper)
- License: non-profit license from University of North Carolina
- Source: git https://github.com/pal-robotics/perception_blort.git (branch: fuerte)
Package Summary
The SiftGPU library is an implementation of SIFT for GPU.
- Maintainer: Bence Magyar <bence.magyar AT pal-robotics DOT com>
- Author: Changchang Wu <ccwu AT cs.unc DOT edu>
- License: non-profit license from University of North Carolina
- External website: http://cs.unc.edu/~ccwu/siftgpu/
- Source: git https://github.com/pal-robotics/perception_blort.git (branch: hydro-devel)
Contents
Overview
[0] Changchang Wu SiftGPU: A GPU Implementation of Scale Invariant Feature Transform (SIFT), 2007
For more details go to the SiftGPU homepage
SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors.
SiftGPU is inspired by Andrea Vedaldi's sift++[2] and Sudipta N Sinha et al's GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified.
SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and finds the closest feature matches on GPU. Both GLSL and CUDA implementations are provided.
[1] D. G. Lowe. Distinctive image features from scale-invariant keypoints . International Journal of Computer Vision, November 2004.
[2] A. Vedaldi. sift++, http://www.vlfeat.org/~vedaldi/code/siftpp.html.
[3] G. Ziegler, et al. GPU point list generation through histogram pyramids. In Technical Report, June 2006.
[4] Sudipta N Sinha, Jan-Michael Frahm, Marc Pollefeys and Yakup Genc, "GPU-Based Video Feature Tracking and Matching ", EDGE 2006, workshop on Edge Computing Using New Commodity Architectures, Chapel Hill, May 2006
