Contextual Aerial Image Categorization Using Codebook

	Contextual Aerial Image Categorization Using Codebook
	Zhijun Meng; Yan Wang; Xinyu Wu; Yating Yin; Teng Li
刊名	Journal of Visual Communication and Image Representation
	2017
文献子类	期刊论文
英文摘要	Effective categorization of the millions of aerial images from unmanned planes is a useful technique with several important applications. Previous methods on this task usually encountered such problems: (1) it is hard to represent the aerial images’ topologies efﬁciently, which are the key feature to distinguish the arial images rather than conventional appearance, and (2) the computational load is usually too high to build a realtime image categorization system. Addressing these problems, this paper proposes an efﬁcient and effective aerial image categorization method based on a contextual topological codebook. The codebook of aerial images is learned with a multitask learning framework. The topology of each aerial image is represented with the region adjacency graph (RAG). Furthermore, a codebook containing topologies is learned by jointly modeling the contextual information, based on the extracted discriminative graphlets. These graphlets are integrated into a Bag-of-Words (BoW) representation for predicting aerial image categories. Contextual relation among local patches are taken into account in categorization to yield high categorization performance. Experimental results show that our approach is both effective and efﬁcient.
URL标识	查看原文
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/11721]
专题	深圳先进技术研究院_集成所
作者单位	Journal of Visual Communication and Image Representation
推荐引用方式 GB/T 7714	Zhijun Meng,Yan Wang,Xinyu Wu,et al. Contextual Aerial Image Categorization Using Codebook[J]. Journal of Visual Communication and Image Representation,2017.
APA	Zhijun Meng,Yan Wang,Xinyu Wu,Yating Yin,&Teng Li.(2017).Contextual Aerial Image Categorization Using Codebook.Journal of Visual Communication and Image Representation.
MLA	Zhijun Meng,et al."Contextual Aerial Image Categorization Using Codebook".Journal of Visual Communication and Image Representation (2017).