eprintid: 3449
rev_number: 10
eprint_status: archive
userid: 392
dir: disk0/00/00/34/49
datestamp: 2019-06-03 04:07:26
lastmod: 2019-06-03 04:07:26
status_changed: 2019-06-03 04:07:26
type: article
metadata_visibility: show
creators_name: Luu, Viet Hung
creators_name: Dinh, Van Kiet
creators_name: Luong, Nguyen Hoang Hoa
creators_name: Bui, Quang Hung
creators_name: Nguyen, Thi Nhat Thanh
creators_id: hunglv@fimo.edu.vn
creators_id: hungbq@vnu.edu.vn
creators_id: thanhntn@vnu.edu.vn
title: Improving the Bag-of-Words model with Spatial Pyramid matching using data augmentation for fine-grained arbitrary-oriented ship classification
ispublished: pub
subjects: IT
subjects: Scopus
subjects: isi
divisions: FIMO
divisions: fac_fit
abstract: In this letter, we investigate fine-grained classification of arbitrary-oriented ships in very high resolution optical imagery using Bag of Word model with Spatial Pyramid (SP-BoW). Given that based on ‘spatial pyramid’ of the histogram of local features, the final feature vectors not only count the multiplicity of ‘words’ but also represent their spatial topology. We attempt to improve the performance of this model by introducing augmented data for training phase. Our aim is to make the dataset big enough to be able to capture holistic variation of ship orientation. Three data augmentation operations are used including random rotate by an angle of modulo 90°, random flip-left-right, and random flip-top-bottom. Through this procedure, our trained SP-BoW model is able to get better generalization. The proposed approach is validated on the High-Resolution Ship Collections 2016 (HRSC2016) ship dataset. The results indicate that training on augmented data can significantly improve the performance of SP-BoW. Beside, compared to other state-of-the-art convolutional neural network-based approaches, the approach proposed in this research has yielded competitive results and could make it a good baseline for evaluating more sophisticated CNN architecture in the future.
date: 2019
date_type: published
publisher: Taylor & Francis
full_text_status: none
publication: Remote Sensing Letters
volume: 10
number: 9
pagerange: 826-834
refereed: TRUE
issn: 2150-704X
citation:   Luu, Viet Hung and Dinh, Van Kiet and Luong, Nguyen Hoang Hoa and Bui, Quang Hung and Nguyen, Thi Nhat Thanh  (2019) Improving the Bag-of-Words model with Spatial Pyramid matching using data augmentation for fine-grained arbitrary-oriented ship classification.  Remote Sensing Letters, 10  (9).   pp. 826-834.  ISSN 2150-704X