Name
Title | ||
|---|---|---|
The Bag-Of-Visual-Words Scene Classifier Combining Local And Global Features For High Spatial Resolution Imagery |
Abstract | ||
|---|---|---|
Scene classification has been proved to be an effective method for high spatial resolution (HSR) image semantic interpretation. Considering the complex structure and abundant information, three issues should be discussed for HSR imagery: 1) Which kind of features should be combined to comprehensively describe the HSR imagery? 2) How to efficiently fuse the different types of features? 3) Which scene classification method is best for capturing the distinctive characteristics of HSR image scenes? In this paper, an easy but effective local-global-feature bag-of-visual-words classifier (LGFBOVW) is proposed to fuse the complementary features at the histogram level. The LGFBOVW representation is then classified by support vector machine (SVM) with a histogram intersection kernel (HIK) for HSR image scene classification. LGFBOVW can incorporate distinctive features with different characteristics, whether these features are local or global, continuous or discrete. The proposed approach introduces the novel use of shape-based invariant texture index (SITI) which was originally used to analyze the natural images. SITI is captured as the global texture feature descriptor for the challenging scene representation. The mean and standard deviation values (MeanStd) is utilized as the local spectral feature descriptor, and the dense scale-invariant feature transform (SIFT) is utilized as the local structural feature. The experimental results demonstrate that the proposed method is superior to the state-of-the-art methods with UCMERCED dataset. |
Year | Venue | Keywords |
|---|---|---|
2015 | 2015 12TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD) | scene classification, local and global features, SITI, bag-of-visual-words, fusion, high spatial resolution imagery |
Field | DocType | Citations |
Histogram,Scale-invariant feature transform,Computer science,Artificial intelligence,Classifier (linguistics),Kernel (linear algebra),Computer vision,Bag-of-words model in computer vision,Pattern recognition,Feature (computer vision),Support vector machine,Image resolution,Machine learning | Conference | 1 |
PageRank | References | Authors |
0.35 | 18 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qiqi Zhu | 1 | 29 | 3.55 |
| Yanfei Zhong | 2 | 1044 | 90.58 |
| Bei Zhao | 3 | 5 | 1.43 |
| Gui-Song Xia | 4 | 798 | 64.99 |
| Liangpei Zhang | 5 | 5448 | 307.02 |