A 2-D wavelet decomposition-based bag-of-visual-words model for land-use scene classification

By Lijun Zhao, Ping Tang, L. Huo. 2014

71 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Remote Sensing

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Liangpei Zhang
2. Gui-Song Xia
3. Yanfei Zhong
4. Xiaoqiang Lu
5. Xiang Bai
6. Junwei Han
7. Jingwen Hu
8. Gong Cheng

In Media Technology

1. Liangpei Zhang
2. Yanfei Zhong
3. Gui-Song Xia
4. Xiaoqiang Lu
5. Wei Li
6. Jingwen Hu
7. Lijun Zhao
8. Ping Tang

In Remote Sensing

1. Liangpei Zhang
2. Gui-Song Xia
3. Jingwen Hu
4. Fan Hu
5. Yanfei Zhong
6. Wei Li
7. Hongjun Su
8. Baochang Zhang

Citations in the corpus

• AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “al [22] proposed another way to incorporate the spatial information, where wavelet decomposition was utilized in the BoVW model to combine not only the spatial information but also the texture information.”
• Land-use scene classification using multi-scale completed local binary patterns (2016, methodology): “In [4], a 2D wavelet decompositionbased BOVW model was proposed to exploit the texture structures in land-use images.”
• Strathprints Institutional Repository Shuhui and Ren, Jinchang (2015) Effective and Efficient Midlevel Visual Elements-oriented Land-use Classification Using Vhr Remote Sensing Images. Ieee Transactions on Geoscience and Remote Sensing, 53 (8). Pp. 4238-4249. Issn 0196-2892 Effective and Efficient M (unknown): “…on pixel or object-level thematic classification, the scene-level land-use classification using very high resolution (VHR) remote sensing images has attracted more and more attentions [3] [4] [5] [6] [7] [19] [20] because of its foundation and importance in automated image content understanding.”
• A Comparative Study of Sampling Analysis in the Scene Classification of Optical High-Spatial Resolution Remote Sensing Imagery (2015, methodology): “For instance, without sampling, it is intractable or even infeasible to train a BoVW model or unsupervised feature learning-based model for scene classification [4,9,10,13,14] with a computer of advanced configurations, as the volume of optical HSR-RS imagery generally amounts to several gigabytes.”
• Feature significance-based multibag-of-visual-words model for remote sensing image scene classification (2016, methodology): “Although the radial basis function (RBF) kernel is the most commonly used kernel in most SVM classification tasks,(43) for BOVW-type features, the histogram intersection (HI) kernel has been proved to perform better than the RBF kernel.(17,44) Note that in the first phase, the features for classific”
• Hierarchical Coding Vectors for Scene Level Land-Use Classification (2016, result): “To be consistent with other researchers’ experimental settings on the LU database [1,27–29], the database was randomly partitioned into five equal subsets.”
• Land-Use Scene Classification Using a Concentric Circle-Structured Multiscale Bag-of-Visual-Words Model (2014, background): “Although these variants of the original BOVW model have a good descriptive ability to depict spatial layout information of scene images, they are designed mainly for natural image scene classification, and seldom have they been applied in the field of remote sensing image scene classification, excep”