Superpixels with Content-Awareness via a Two-Stage Generation Framework

被引:0
|
作者
Li, Cheng [1 ]
Liao, Nannan [2 ]
Huang, Zhe [3 ]
Bian, He [1 ]
Zhang, Zhe [1 ]
Ren, Long [1 ]
机构
[1] Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
[2] Xidian Univ, Inst Intelligent Control & Image Engn, Xian 710071, Peoples R China
[3] Wuhan Second Ship Design & Res Inst, Wuhan 430025, Peoples R China
来源
SYMMETRY-BASEL | 2024年 / 16卷 / 08期
关键词
superpixels; content awareness; centroid relocation; online average clustering;
D O I
10.3390/sym16081011
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
The superpixel usually serves as a region-level feature in various image processing tasks, and is known for segmentation accuracy, spatial compactness and running efficiency. However, since these properties are intrinsically incompatible, there is still a compromise within the overall performance of existing superpixel algorithms. In this work, the property constraint in superpixels is relaxed by in-depth understanding of the image content, and a novel two-stage superpixel generation framework is proposed to produce content-aware superpixels. In the global processing stage, a diffusion-based online average clustering framework is introduced to efficiently aggregate image pixels into multiple superpixel candidates according to color and spatial information. During this process, a centroid relocation strategy is established to dynamically guide the region updating. According to the area feature in manifold space, several superpixel centroids are then split or merged to optimize the regional representation of image content. Subsequently, local updating is adopted on pixels in those superpixel regions to further improve the performance. As a result, the dynamic centroid relocating strategy offers online averaging clustering the property of content awareness through coarse-to-fine label updating. Extensive experiments verify that the produced superpixels achieve desirable and comprehensive performance on boundary adherence, visual satisfactory and time consumption. The quantitative results are on par with existing state-of-the-art algorithms in terms with several common property metrics.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] An efficient two-stage framework for image annotation
    Hu, Jiwei
    Lam, Kin-Man
    PATTERN RECOGNITION, 2013, 46 (03) : 936 - 947
  • [22] A two-stage framework for UML specification matching
    Park, Wei-Jin
    Bae, Doo-Hwan
    INFORMATION AND SOFTWARE TECHNOLOGY, 2011, 53 (03) : 230 - 244
  • [23] Blind Image Quality Assessment via A Two-Stage Non-Parametric Framework
    Manap, Redzuan Abdul
    Frangi, Alejandro F.
    Shao, Ling
    PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, 2015, : 796 - 800
  • [24] A Novel Two-Stage Training Method for Unbiased Scene Graph Generation via Distribution
    Jia, Dongdong
    Zhou, Meili
    Wei, Wei
    Wang, Dong
    Bai, Zongwen
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2023, 17 (12): : 3383 - 3397
  • [25] Consumer environmental awareness and competition in two-stage supply chains
    Liu, Zugang
    Anderson, Trisha D.
    Cruz, Jose M.
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2012, 218 (03) : 602 - 613
  • [26] A two-stage simulation-based framework for optimal resilient generation and transmission expansion planning
    Firoozjaee, Mahdi Golchoob
    Sheikh-El-Eslami, Mohammad Kazem
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2022, 16 (21) : 4273 - 4290
  • [27] Two-stage clustering via neural networks
    Wang, JH
    Rau, JD
    Liu, WJ
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (03): : 606 - 615
  • [28] A Two-stage Method of Synchronization Prediction Framework in TDD
    Chao-Hsien Hsieh
    Ziyi Wang
    Arabian Journal for Science and Engineering, 2022, 47 : 2345 - 2357
  • [29] Progressive Training of A Two-Stage Framework for Video Restoration
    Zheng, Meisong
    Xing, Qunliang
    Qiao, Minglang
    Xu, Mai
    Jiang, Lai
    Liu, Huaida
    Chen, Ying
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 1023 - 1030
  • [30] Rethinking the Two-Stage Framework for Grounded Situation Recognition
    Wei, Meng
    Chen, Long
    Ji, Wei
    Yue, Xiaoyu
    Chua, Tat-Seng
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 2651 - 2658