FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach

doi:10.1109/TCSVT.2016.2615466

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach
	Xing, Junliang1 ; Hu, Weiming2,3 ; Ai, Haizhou 4; Yan, Shuicheng 5
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2018-03-01
卷号	28 期号:3 页码:601-615
文章类型	Article
摘要	Coherent image regions can be used as good features for many computer vision tasks, such as object tracking, segmentation, and recognition. Most of previous region extraction methods, however, are not suitable for online applications because of their either heavy computations or unsatisfactory results. We propose a seed-based region growing and merging approach to generate simultaneously coherent and discriminative image regions. We present a quadtree-based seed initialization algorithm to adaptively place seeds into different image areas and then grow them into regions by a color-and edge-guided growing procedure. To merge these regions in different levels, we propose to use the generalized boundary strength to measure the quality of region merging result. In addition, we present a region merging algorithm of linear time complexity to perform efficient and effective region merging. Overall, our new approach simultaneously holds these advantages: 1) it is extremely fast with linear complexity in both time and space, which takes less than 50 ms to process an HVGA image; 2) it can give a direct control of the region number and well adapt to image regions with various sizes and shapes; and 3) it provides a tree-structured representation of the regions and thus can model the image from multiple scales. We evaluate the proposed approach on the standard benchmarks with extensive comparisons with the state-of-the-art methods. The experimental results demonstrate its good comprehensive performances. Example applications using the extracted regions as features for online object tracking and multiclass object segmentation also exhibit its potential for many computer vision tasks.
关键词	Object Classification Object Segmentation Object Tracking Region Extraction Superpixel
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCSVT.2016.2615466
关键词[WOS]	IMAGE SEGMENTATION ; GRAPH CUTS ; TEXTURE SEGMENTATION ; ENERGY MINIMIZATION ; CLASSIFICATION ; MODEL
收录类别	SCI
语种	英语
项目资助者	973 Basic Research Program of China(2014CB349303) ; Natural Science Foundation of China(61303178 ; CAS(XDB02070003) ; CAS ; U1636218 ; 61472421)
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000426693100004
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21978
专题	多模态人工智能系统全国重点实验室_视频内容安全
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Tech, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 4.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China 5.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117576, Singapore
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Xing, Junliang,Hu, Weiming,Ai, Haizhou,et al. FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2018,28(3):601-615.
APA	Xing, Junliang,Hu, Weiming,Ai, Haizhou,&Yan, Shuicheng.(2018).FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,28(3),601-615.
MLA	Xing, Junliang,et al."FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 28.3(2018):601-615.