Village Building Identification Based on Ensemble Convolutional Neural Networks
In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for v...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/17/11/2487 |
| _version_ | 1828113805070041088 |
|---|---|
| author | Zhiling Guo Qi Chen Guangming Wu Yongwei Xu Ryosuke Shibasaki Xiaowei Shao |
| author_facet | Zhiling Guo Qi Chen Guangming Wu Yongwei Xu Ryosuke Shibasaki Xiaowei Shao |
| author_sort | Zhiling Guo |
| collection | DOAJ |
| description | In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86. |
| first_indexed | 2024-04-11T12:15:58Z |
| format | Article |
| id | doaj.art-48c7518e4afd4f479d8f36e88b4dbea9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:15:58Z |
| publishDate | 2017-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-48c7518e4afd4f479d8f36e88b4dbea92022-12-22T04:24:19ZengMDPI AGSensors1424-82202017-10-011711248710.3390/s17112487s17112487Village Building Identification Based on Ensemble Convolutional Neural NetworksZhiling Guo0Qi Chen1Guangming Wu2Yongwei Xu3Ryosuke Shibasaki4Xiaowei Shao5Center for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanCenter for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanCenter for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanCenter for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanCenter for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanCenter for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, JapanIn this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86.https://www.mdpi.com/1424-8220/17/11/2487Ensemble Convolutional Neural Networksremote sensingbuilding detectionvillage mappingmultiscale feature learning |
| spellingShingle | Zhiling Guo Qi Chen Guangming Wu Yongwei Xu Ryosuke Shibasaki Xiaowei Shao Village Building Identification Based on Ensemble Convolutional Neural Networks Sensors Ensemble Convolutional Neural Networks remote sensing building detection village mapping multiscale feature learning |
| title | Village Building Identification Based on Ensemble Convolutional Neural Networks |
| title_full | Village Building Identification Based on Ensemble Convolutional Neural Networks |
| title_fullStr | Village Building Identification Based on Ensemble Convolutional Neural Networks |
| title_full_unstemmed | Village Building Identification Based on Ensemble Convolutional Neural Networks |
| title_short | Village Building Identification Based on Ensemble Convolutional Neural Networks |
| title_sort | village building identification based on ensemble convolutional neural networks |
| topic | Ensemble Convolutional Neural Networks remote sensing building detection village mapping multiscale feature learning |
| url | https://www.mdpi.com/1424-8220/17/11/2487 |
| work_keys_str_mv | AT zhilingguo villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks AT qichen villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks AT guangmingwu villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks AT yongweixu villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks AT ryosukeshibasaki villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks AT xiaoweishao villagebuildingidentificationbasedonensembleconvolutionalneuralnetworks |