Real-Time Dense Semantic Labeling with Dual-Path Framework for High-Resolution Remote Sensing Image

被引:14
|
作者
Wang, Yuhao [1 ,2 ]
Chen, Chen [3 ]
Ding, Meng [4 ]
Li, Jiangyun [1 ,2 ]
机构
[1] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
[2] Minist Educ, Key Lab Knowledge Automat Ind Proc, Beijing 100083, Peoples R China
[3] Univ N Carolina, Dept Elect & Comp Engn, Charlotte, NC 28223 USA
[4] Thermo Fisher Sci, Richardson, TX 75081 USA
基金
中国国家自然科学基金;
关键词
remote sensing image; real-time dense semantic labeling; convolutional neural networks; light-weight;
D O I
10.3390/rs11243020
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Dense semantic labeling plays a pivotal role in high-resolution remote sensing image research. It provides pixel-level classification which is crucial in land cover mapping and urban planning. With the recent success of the convolutional neural network (CNN), accuracy has been greatly improved by previous works. However, most networks boost performance by involving too many parameters and computational overheads, which results in more inference time and hardware resources, while some attempts with light-weight networks do not achieve satisfactory results due to the insufficient feature extraction ability. In this work, we propose an efficient light-weight CNN based on dual-path architecture to address this issue. Our model utilizes three convolution layers as the spatial path to enhance the extraction of spatial information. Meanwhile, we develop the context path with the multi-fiber network (MFNet) followed by the pyramid pooling module (PPM) to obtain a sufficient receptive field. On top of these two paths, we adopt the channel attention block to refine the features from the context path and apply a feature fusion module to combine spatial information with context information. Moreover, a weighted cascade loss function is employed to enhance the learning procedure. With all these components, the performance can be significantly improved. Experiments on the Potsdam and Vaihingen datasets demonstrate that our network performs better than other light-weight networks, even some classic networks. Compared to the state-of-the-art U-Net, our model achieves higher accuracy on the two datasets with 2.5 times less network parameters and 22 times less computational floating point operations (FLOPs).
引用
收藏
页数:20
相关论文
共 50 条
  • [21] A Decision Fusion Framework For High-Resolution Remote-Sensing Image Classification
    Jafari, Ali
    Heidarpour, Mostafa
    2015 9TH IRANIAN CONFERENCE ON MACHINE VISION AND IMAGE PROCESSING (MVIP), 2015, : 219 - 222
  • [22] Dual-path Processing Network for High-resolution Salient Object Detection
    Wang, Jun
    Yang, Qingpeng
    Yang, Shangqin
    Chai, Xiuli
    Zhang, Wanjun
    APPLIED INTELLIGENCE, 2022, 52 (10) : 12034 - 12048
  • [23] Dual-path Processing Network for High-resolution Salient Object Detection
    Jun Wang
    Qingpeng Yang
    Shangqin Yang
    Xiuli Chai
    Wanjun Zhang
    Applied Intelligence, 2022, 52 : 12034 - 12048
  • [24] Dual Path Attention Net for Remote Sensing Semantic Image Segmentation
    Li, Jinglun
    Xiu, Jiapeng
    Yang, Zhengqiu
    Liu, Chen
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2020, 9 (10)
  • [25] Real-time image processing for remote sensing
    Konaré, D
    Pierre, S
    Weng, JY
    Morand, E
    CCECE 2003: CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, VOLS 1-3, PROCEEDINGS: TOWARD A CARING AND HUMANE TECHNOLOGY, 2003, : 699 - 702
  • [26] Semantic Multigranularity Feature Learning for High-Resolution Remote Sensing Image Scene Classification
    Ma, Xinyi
    Xiao, Zhifeng
    Yun, Hong-sik
    Lee, Seung-Jun
    APPLIED SCIENCES-BASEL, 2021, 11 (19):
  • [27] High-Resolution Aerial Imagery Semantic Labeling with Dense Pyramid Network
    Pan, Xuran
    Gao, Lianru
    Zhang, Bing
    Yang, Fan
    Liao, Wenzhi
    SENSORS, 2018, 18 (11)
  • [28] A Real-time Transport System for High-resolution Measure Image
    Zhang, Feng
    Ren, Guoqiang
    Wu, Qin-zhang
    MATERIALS, MECHATRONICS AND AUTOMATION, PTS 1-3, 2011, 467-469 : 104 - 107
  • [29] DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework
    Zhang, Zhongyu
    Liu, Yunpeng
    Liu, Tianci
    Lin, Zhiyuan
    Wang, Sikui
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (11) : 1884 - 1888
  • [30] Multibranch Spatial-Channel Attention for Semantic Labeling of Very High-Resolution Remote Sensing Images
    Han, Bingnan
    Yin, Jihao
    Luo, Xiaoyan
    Jia, Xiuping
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (12) : 2167 - 2171