Semantic image segmentation with fused CNN features

被引：10

作者：

Geng H.-Q. ^{[1
]}

Zhang H. ^{[1
]}

Xue Y.-B. ^{[1
]}

Zhou M. ^{[1
]}

Xu G.-P. ^{[1
]}

Gao Z. ^{[1
]}

机构：

[1] Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin

来源：

Optoelectronics Letters | 2017年 / 13卷 / 05期

基金：

中国国家自然科学基金;

关键词：

D O I：

10.1007/s11801-017-7086-6

中图分类号：

学科分类号：

摘要：

Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network (CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field (CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively. © 2017, Tianjin University of Technology and Springer-Verlag GmbH Germany.

引用

页码：381 / 385

页数：4

共 50 条

[21] Random Forest for Semantic Segmentation Using Pre Trained CNN (VGG16) Features [J].

Faska, Zahra ;

Khrissi, Lahbib ;

Haddouch, Khalid ;

El Akkad, Nabil .

DIGITAL TECHNOLOGIES AND APPLICATIONS, ICDTA 2023, VOL 2, 2023, 669 :510-520

[22] Semantic Segmentation of Fused Mobile Mapping Data [J].

Villinger, Georg ;

Schmitt, Annette ;

Reiterer, Alexander .

OPTICAL SENSING AND DETECTION VIII, 2024, 12999

[23] Semantic Segmentation Network for Unstructured Rural Roads Based on Improved SPPM and Fused Multiscale Features [J].

Cao, Xinyu ;

Tian, Yongqiang ;

Yao, Zhixin ;

Zhao, Yunjie ;

Zhang, Taihong .

APPLIED SCIENCES-BASEL, 2024, 14 (19)

[24] Segmenting Objects in Day and Night: Edge-Conditioned CNN for Thermal Image Semantic Segmentation [J].

Li, Chenglong ;

Xia, Wei ;

Yan, Yan ;

Luo, Bin ;

Tang, Jin .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (07) :3069-3082

[25] CMTFNet: CNN and Multiscale Transformer Fusion Network for Remote-Sensing Image Semantic Segmentation [J].

Wu, Honglin ;

Huang, Peng ;

Zhang, Min ;

Tang, Wenlong ;

Yu, Xinyu .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61

[26] CTFNet: CNN-Transformer Fusion Network for Remote-Sensing Image Semantic Segmentation [J].

Wu, Honglin ;

Huang, Peng ;

Zhang, Min ;

Tang, Wenlong .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 :1-5

[27] Semantic segmentation of terrace image regions based on lightweight CNN-Transformer hybrid networks [J].

Liu X. ;

Yi S. ;

Li L. ;

Cheng X. ;

Wang C. .

Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2023, 39 (13) :171-181

[28] A BENCHMARK FOR SEMANTIC IMAGE SEGMENTATION [J].

Li, Hui ;

Cai, Jianfei ;

Thi Nhat Anh Nguyen ;

Zheng, Jianmin .

2013 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2013), 2013,

[29] IMAGE SEGMENTATION BY SEMANTIC METHOD [J].

BASU, S .

PATTERN RECOGNITION, 1987, 20 (05) :497-511

[30] Personalized Image Semantic Segmentation [J].

Zhang, Yu ;

Zhang, Chang-Bin ;

Jiang, Peng-Tao ;

Cheng, Ming-Ming ;

Mao, Feng .

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :10529-10539

← 1 2 3 4 5 →