Discovering discriminative graphlets for aerial image categories recognition

Zhang, Luming, Han, Yahong, Yang, Yi, Song, Mingli, Yan, Shuicheng and Tian, Qi (2013) Discovering discriminative graphlets for aerial image categories recognition. IEEE Transactions on Image Processing, 22 12: 5071-5084. doi:10.1109/TIP.2013.2278465

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Zhang, Luming
Han, Yahong
Yang, Yi
Song, Mingli
Yan, Shuicheng
Tian, Qi
Title Discovering discriminative graphlets for aerial image categories recognition
Journal name IEEE Transactions on Image Processing   Check publisher's open access policy
ISSN 1057-7149
Publication date 2013-12-01
Sub-type Article (original research)
DOI 10.1109/TIP.2013.2278465
Open Access Status Not yet assessed
Volume 22
Issue 12
Start page 5071
End page 5084
Total pages 14
Place of publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Language eng
Abstract Recognizing aerial image categories is useful for scene annotation and surveillance. Local features have been demonstrated to be robust to image transformations, including occlusions and clutters. However, the geometric property of an aerial image (i.e., the topology and relative displacement of local features), which is key to discriminating aerial image categories, cannot be effectively represented by state-of-the-art generic visual descriptors. To solve this problem, we propose a recognition model that mines graphlets from aerial images, where graphlets are small connected subgraphs reflecting both the geometric property and color/texture distribution of an aerial image. More specifically, each aerial image is decomposed into a set of basic components (e.g., road and playground) and a region adjacency graph (RAG) is accordingly constructed to model their spatial interactions. Aerial image categories recognition can subsequently be casted as RAG-to-RAG matching. Based on graph theory, RAG-to-RAG matching is conducted by comparing all their respective graphlets. Because the number of graphlets is huge, we derive a manifold embedding algorithm to measure different-sized graphlets, after which we select graphlets that have highly discriminative and low redundancy topologies. Through quantizing the selected graphlets from each aerial image into a feature vector, we use support vector machine to discriminate aerial image categories. Experimental results indicate that our method outperforms several state-of-the-art object/scene recognition models, and the visualized graphlets indicate that the discriminative patterns are discovered by our proposed approach.
Keyword Aerial image category
Topologies selection
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2014 Collection
School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 103 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 104 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Sun, 10 Nov 2013, 10:04:09 EST by System User on behalf of School of Information Technol and Elec Engineering