Visual query compression with locality preserving projection on Grassmann manifold

For a variety of visual search and visual key points based navigation applications, compression of visual key point features like SIFT is an important part of the overall system that can directly affect the efficiency and latency. In this work, we examine a new approach in visual key points compress...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Image Processing (ICIP) pp. 3026 - 3030
Main Authors Zhang, Zhaobin, Li, Li, Li, Zhu, Li, Houqiang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2017
Subjects
Binary trees
Bit rate
Compression
Grassmann manifold
Indexing
LPP
Manifolds
Principal component analysis
Transforms
Visual identification
Visual query
Visualization
Online AccessGet full text
ISSN2381-8549
DOI10.1109/ICIP.2017.8296838

Cover

More Information
Summary:For a variety of visual search and visual key points based navigation applications, compression of visual key point features like SIFT is an important part of the overall system that can directly affect the efficiency and latency. In this work, we examine a new approach in visual key points compression, that utilizes subspaces that optimized for preserving key point feature matching properties than the reconstruction performance, and allows for a set of optimal subspaces on Grassmann manifold that can better adapt to the local manifold geometry. The simulation demonstrates that such scheme has very low overhead in signaling subspaces, and has very much improved performance on the repeatability of the keypoint matching subject to bit rate constraints.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296838