Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks
The ship detection field faces many challenges due to the large-scale and high complexity of optical remote sensing images. Therefore, an innovative ship detection method that is simple, accurate, and stable is proposed in this paper. The algorithm consists of the following two steps: 1) the AdaBoos...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8536380/ |
| _version_ | 1819120433835802624 |
|---|---|
| author | Ye Yu Hua Ai Xiaojun He Shuhai Yu Xing Zhong Mu Lu |
| author_facet | Ye Yu Hua Ai Xiaojun He Shuhai Yu Xing Zhong Mu Lu |
| author_sort | Ye Yu |
| collection | DOAJ |
| description | The ship detection field faces many challenges due to the large-scale and high complexity of optical remote sensing images. Therefore, an innovative ship detection method that is simple, accurate, and stable is proposed in this paper. The algorithm consists of the following two steps: 1) the AdaBoost classifier, combined with Haar-like features, is used to rapidly extract candidate area slices, and 2) according to the characteristics of ships, a periphery-cropped network is designed for ship verification. Furthermore, we analyze the characteristics of ocean images to improve the contrast between the target and the background. Thus, an RGB spectrum-stretching method is proposed. Finally, we evaluate our method using spaceborne optical images from the Jilin-1 satellite, Google satellites, and the public dataset NWPU VHR-10. Our experimental results indicate that the proposed algorithm achieves a high detection rate. |
| first_indexed | 2024-12-22T06:20:36Z |
| format | Article |
| id | doaj.art-2ed91c59660b4b828447d79995402c74 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T06:20:36Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2ed91c59660b4b828447d79995402c742022-12-21T18:35:58ZengIEEEIEEE Access2169-35362018-01-016711227113110.1109/ACCESS.2018.28814798536380Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural NetworksYe Yu0https://orcid.org/0000-0003-0011-9055Hua Ai1Xiaojun He2Shuhai Yu3Xing Zhong4Mu Lu5Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, ChinaChang Guang Satellite Technology Co., Ltd., Changchun, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, ChinaChang Guang Satellite Technology Co., Ltd., Changchun, ChinaThe ship detection field faces many challenges due to the large-scale and high complexity of optical remote sensing images. Therefore, an innovative ship detection method that is simple, accurate, and stable is proposed in this paper. The algorithm consists of the following two steps: 1) the AdaBoost classifier, combined with Haar-like features, is used to rapidly extract candidate area slices, and 2) according to the characteristics of ships, a periphery-cropped network is designed for ship verification. Furthermore, we analyze the characteristics of ocean images to improve the contrast between the target and the background. Thus, an RGB spectrum-stretching method is proposed. Finally, we evaluate our method using spaceborne optical images from the Jilin-1 satellite, Google satellites, and the public dataset NWPU VHR-10. Our experimental results indicate that the proposed algorithm achieves a high detection rate.https://ieeexplore.ieee.org/document/8536380/Object detectionfeature extractionCNNAdaBoost classifier |
| spellingShingle | Ye Yu Hua Ai Xiaojun He Shuhai Yu Xing Zhong Mu Lu Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks IEEE Access Object detection feature extraction CNN AdaBoost classifier |
| title | Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks |
| title_full | Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks |
| title_fullStr | Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks |
| title_full_unstemmed | Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks |
| title_short | Ship Detection in Optical Satellite Images Using Haar-like Features and Periphery-Cropped Neural Networks |
| title_sort | ship detection in optical satellite images using haar like features and periphery cropped neural networks |
| topic | Object detection feature extraction CNN AdaBoost classifier |
| url | https://ieeexplore.ieee.org/document/8536380/ |
| work_keys_str_mv | AT yeyu shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks AT huaai shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks AT xiaojunhe shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks AT shuhaiyu shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks AT xingzhong shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks AT mulu shipdetectioninopticalsatelliteimagesusinghaarlikefeaturesandperipherycroppedneuralnetworks |