TEXTURE-AWARE SUPERPIXEL SEGMENTATION

被引：0

作者：

Giraud, Remi ^{[1
]}

Vinh-Thong Ta ^{[2
]}

Papadakis, Nicolas ^{[3
]}

Berthoumieu, Yannick ^{[1
]}

机构：

[1] Univ Bordeaux, Bordeaux INP, CNRS, IMS,UMR 5218, F-33400 Talence, France

[2] Univ Bordeaux, Bordeaux INP, CNRS, LaBRI,UMR 5800, F-33400 Talence, France

[3] Univ Bordeaux, CNRS, IMB, UMR 5251, F-33400 Talence, France

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2019年

基金：

欧盟地平线“2020”;

关键词：

Superpixels; Texture; Patch; Segmentation;

D O I：

10.1109/icip.2019.8803085

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

Most superpixel algorithms compute a trade-off between spatial and color features at the pixel level. Hence, they may need fine parameter tuning to balance the two measures, and highly fail to group pixels with similar local texture properties. In this paper, we address these issues with a new Texture-Aware SuperPixel (TASP) method. To accurately segment textured and smooth areas, TASP automatically adjusts its spatial constraint according to the local feature variance. Then, to ensure texture homogeneity within superpixels, a new pixel to superpixel patch-based distance is proposed. TASP outperforms the segmentation accuracy of the state-of-the-art methods on texture and also natural color image datasets.

引用

页码：1465 / 1469

页数：5

共 50 条

[21] Texture-Aware Depth Prediction in 3D Video Coding
Zhu, Ce
Li, Shuai
Zheng, Jianhua
Gao, Yanbo
Yu, Lu
[J]. IEEE TRANSACTIONS ON BROADCASTING, 2016, 62 (02) : 482 - 486
[22] Inferring Camouflaged Objects by Texture-Aware Interactive Guidance Network
Zhu, Jinchao
Zhang, Xiaoyu
Zhang, Shuo
Liu, Junnan
[J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 3599 - 3607
[23] Blind Image Super-resolution with Rich Texture-Aware Codebooks
Qin, Rui
Sun, Ming
Zhang, Fangyuan
Wen, Xing
Wang, Bin
[J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 676 - 687
[24] Structure and Texture-Aware Image Decomposition via Training a Neural Network
Zhou, Fei
Chen, Qun
Liu, Bozhi
Qiu, Guoping
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 (29) : 3458 - 3473
[25] Fusion of infrared and visible images via structure and texture-aware retinex
Hu J.
Hao M.
Du Y.
Xie Q.
[J]. Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2022, 30 (24): : 3225 - 3228
[26] Robust Texture-Aware Local Adaptive Image Watermarking With Perceptual Guarantee
Huang, Ying
Guan, Hu
Liu, Jie
Zhang, Shuwu
Niu, Baoning
Zhang, Guixuan
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (09) : 4660 - 4674
[27] TEXTURE-AWARE DENSE IMAGE MATCHING USING TERNARY CENSUS TRANSFORM
Hu, Han
Chen, Chongtai
Wu, Bo
Yang, Xiaoxia
Zhu, Qing
Ding, Yulin
[J]. XXIII ISPRS CONGRESS, COMMISSION III, 2016, 3 (03): : 59 - 66
[28] Texture-Aware Ridgelet Transform and Machine Learning for Surface Roughness Prediction
Cooper, Clayton
Zhang, Jianjing
Hu, Liwen
Guo, Yuebin
Gao, Robert X.
[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[29] Structure- and Texture-Aware Learning for Low-Light Image Enhancement
Zhang, Jinghao
Huang, Jie
Yao, Mingde
Zhou, Man
Zhao, Feng
[J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 6483 - 6492
[30] Texture-Aware Spherical Rotation for High Efficiency Omnidirectional Intra Video Coding
Pi, Jinyong
Zhang, Yun
Zhu, Linwei
Lin, Jinzhi
Ho, Yo-Sung
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (12) : 8768 - 8780

← 1 2 3 4 5 →