Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery

被引:54
|
作者
Mboga, Nicholus [1 ]
Georganos, Stefanos [1 ]
Grippa, Tais [1 ]
Lennert, Moritz [1 ]
Vanhuysse, Sabine [1 ]
Wolff, Eleonore [1 ]
机构
[1] ULB, Dept Geosci Environm & Soc, B-1050 Brussels, Belgium
关键词
fully convolutional networks; convolutional neural networks; remote sensing; very high resolution; landcover classification; geographical object-based image analysis; NEURAL-NETWORKS; SELECTION;
D O I
10.3390/rs11050597
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Land cover Classified maps obtained from deep learning methods such as Convolutional neural networks (CNNs) and fully convolutional networks (FCNs) usually have high classification accuracy but with the detailed structures of objects lost or smoothed. In this work, we develop a methodology based on fully convolutional networks (FCN) that is trained in an end-to-end fashion using aerial RGB images only as input. Skip connections are introduced into the FCN architecture to recover high spatial details from the lower convolutional layers. The experiments are conducted on the city of Goma in the Democratic Republic of Congo. We compare the results to a state-of-the art approach based on a semi-automatic Geographic object image-based analysis (GEOBIA) processing chain. State-of-the art classification accuracies are obtained by both methods whereby FCN and the best baseline method have an overall accuracy of 91.3% and 89.5% respectively. The maps have good visual quality and the use of an FCN skip architecture minimizes the rounded edges that is characteristic of FCN maps. Additional experiments are done to refine FCN classified maps using segments obtained from GEOBIA generated at different scale and minimum segment size. High OA of up to 91.5% is achieved accompanied with an improved edge delineation in the FCN maps, and future work will involve explicitly incorporating boundary information from the GEOBIA segmentation into the FCN pipeline in an end-to-end fashion. Finally, we observe that FCN has a lower computational cost than the standard patch-based CNN approach especially at inference.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Extraction of Building Information Using Geographic Object-based Image Analysis
    Fan, Shudi
    Liu, Zhenhua
    Hu, Yueming
    [J]. 2016 4rth International Workshop on Earth Observation and Remote Sensing Applications (EORSA), 2016,
  • [32] Hierarchical object-based image analysis of high-resolution imagery for urban land use classification
    Zhan, QM
    Molenaar, M
    Xiao, YH
    [J]. IEEE/ISPRS JOINT WORKSHOP ON REMOTE SENSING AND DATA FUSION OVER URBAN AREAS, 2001, : 35 - 39
  • [33] Object-based Image Analysis Using VHR Satellite Imagery for Monitoring the Dismantling of a Refugee Camp after a Crisis: The Case of Lukole, Tanzania
    Staengel, Matthias
    Tiede, Dirk
    Luethje, Fritjof
    Fuereder, Petra
    Lang, Stefan
    [J]. GI FORUM 2014: GEOSPATIAL INNOVATION FOR SOCIETY, 2014, : 45 - 48
  • [34] A Combined Object- and Pixel-Based Image Analysis Framework for Urban Land Cover Classification of VHR Imagery
    Salehi, Bahram
    Zhang, Yun
    Zhong, Ming
    [J]. PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2013, 79 (11): : 999 - 1014
  • [35] Classification of Siachen Glacier Using Object-Based Image Analysis
    Sharda, Shikha
    Srivastava, Mohit
    [J]. 2ND INTERNATIONAL CONFERENCE ON INTELLIGENT CIRCUITS AND SYSTEMS (ICICS 2018), 2018, : 271 - 274
  • [36] Support vector machine classification for object-based image analysis
    Laboratory of Remote Sensing, Department of Surveying, School of Rural and Surveying Engineering, National Technical University of Athens, Greece
    [J]. Lect. Notes Geoinformation Cartogr, 2008, 9783540770572 (663-677):
  • [37] A Joint Bayesian Optimization for the Classification of Fine Spatial Resolution Remotely Sensed Imagery Using Object-Based Convolutional Neural Networks
    Azeez, Omer Saud
    Shafri, Helmi Z. M.
    Alias, Aidi Hizami
    Haron, Nuzul Azam
    [J]. LAND, 2022, 11 (11)
  • [38] Geospatial mapping of Antarctic coastal oasis using geographic object-based image analysis and high resolution satellite imagery
    Jawak, Shridhar D.
    Luis, Alvarinho J.
    [J]. MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL REMOTE SENSING TECHNOLOGY, TECHNIQUES AND APPLICATIONS VI, 2016, 9880
  • [39] Developing an integrated approach based on geographic object-based image analysis and convolutional neural network for volcanic and glacial landforms mapping
    Garajeh, Mohammad Kazemi
    Li, Zhenlong
    Hasanlu, Saber
    Naghadehi, Saeid Zare
    Haghi, Vahid Hossein
    [J]. SCIENTIFIC REPORTS, 2022, 12 (01)
  • [40] Developing an integrated approach based on geographic object-based image analysis and convolutional neural network for volcanic and glacial landforms mapping
    Mohammad Kazemi Garajeh
    Zhenlong Li
    Saber Hasanlu
    Saeid Zare Naghadehi
    Vahid Hossein Haghi
    [J]. Scientific Reports, 12