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
  • [1] Two-stage Content-Aware Layout Generation for Poster Designs
    Chai, Shang
    Zhuang, Liansheng
    Yan, Fengying
    Zhou, Zihan
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 8415 - 8423
  • [2] Hydroclimatic scenario generation using two-stage stochastic simulation framework
    Awasthi, Chandramauli
    Chalise, Dol Raj
    Wang, Hui
    Erkyihun, Solomon Tassew
    Asefa, Tirusew
    Sankarasubramanian, A.
    ADVANCES IN WATER RESOURCES, 2024, 190
  • [3] Towards Automatic Model Compression via a Unified Two-Stage Framework
    Chen, Weihan
    Wang, Peisong
    Cheng, Jian
    PATTERN RECOGNITION, 2023, 140
  • [4] Efficient Image-Warping Framework for Content-Adaptive Superpixels Generation
    Chuchvara, Aleksandra
    Gotchev, Atanas
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 1948 - 1952
  • [5] Text to Image Synthesis Using Two-Stage Generation and Two-Stage Discrimination
    Zhang, Zhiqiang
    Zhang, Yunye
    Yu, Wenxin
    He, Gang
    Jiang, Ning
    He, Gang
    Fan, Yibo
    Yang, Zhuo
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2019, PT II, 2019, 11776 : 110 - 114
  • [6] Unbiased Scene Graph Generation via Two-Stage Causal Modeling
    Sun, Shuzhou
    Zhi, Shuaifeng
    Liao, Qing
    Heikkila, Janne
    Liu, Li
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (10) : 12562 - 12580
  • [7] Parameter estimation via artificial data generation with the "two-stage" approach
    Garatti, Simone
    Bittanti, Sergio
    2008 7TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-23, 2008, : 5605 - 5610
  • [8] A two-stage framework for bat algorithm
    Boyang Zhang
    Haiwen Yuan
    Lingjie Sun
    Jian Shi
    Zhao Ma
    Limei Zhou
    Neural Computing and Applications, 2017, 28 : 2605 - 2619
  • [9] A two-stage framework for polygon retrieval
    Tung, LH
    King, I
    MULTIMEDIA TOOLS AND APPLICATIONS, 2000, 11 (02) : 235 - 255
  • [10] A two-stage framework for bat algorithm
    Zhang, Boyang
    Yuan, Haiwen
    Sun, Lingjie
    Shi, Jian
    Ma, Zhao
    Zhou, Limei
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 (09): : 2605 - 2619