Simple Salience-Driven Bag of Visual Words Models for Remote Sensing Scene Classification
- 10.2991/iccia-17.2017.69How to use a DOI?
- remote sensing scene classification, Itti model, GBVS, salience-driven BoVW model
In order to improve the accuracy of remote sensing scene classification, this paper proposes to integrate visual saliency into bag of words model. In this paper, the color histogram (CH), Scale Invariant Feature Transform (SIFT) and local binary pattern (LBP) methods are used to extract the features of the original remote sensing image firstly. Then, Itti model and Graph-based Visual Saliency (GBVS) algorithm are used to analyze the salient region separately. Finally, salience-driven Bag of Visual Words (BoVW) models are established by features which are both from the original images and filtered by salient regions. Experiments show that the salience-driven BoVW models can improve the accuracy of remote sensing scene classification obviously than without salience-driven.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Lipeng Ji AU - Xiaohui Hu AU - Beijia Hu AU - Mingye Wang PY - 2016/07 DA - 2016/07 TI - Simple Salience-Driven Bag of Visual Words Models for Remote Sensing Scene Classification BT - Proceedings of the 2nd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2017) PB - Atlantis Press SP - 415 EP - 421 SN - 2352-538X UR - https://doi.org/10.2991/iccia-17.2017.69 DO - 10.2991/iccia-17.2017.69 ID - Ji2016/07 ER -