A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features
In recent years, due to its strong nonlinear mapping and research capacities, the convolutional neural network (CNN) has been widely used in the field of hyperspectral image (HSI) processing. Recently, pixel pair features (PPFs) and spatial PPFs (SPPFs) for HSI classification have served as the new...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8438875/ |
| _version_ | 1818618840509054976 |
|---|---|
| author | Jinming Du Zhiyong Li |
| author_facet | Jinming Du Zhiyong Li |
| author_sort | Jinming Du |
| collection | DOAJ |
| description | In recent years, due to its strong nonlinear mapping and research capacities, the convolutional neural network (CNN) has been widely used in the field of hyperspectral image (HSI) processing. Recently, pixel pair features (PPFs) and spatial PPFs (SPPFs) for HSI classification have served as the new tools for feature extraction. In this paper, on top of PPF, improved subtraction pixel pair features (subtraction-PPFs) are applied for HSI target detection. Unlike original PPF and SPPF, the subtraction-PPF considers target classes to afford the CNN, a target detection function. Using subtraction-PPF, a sufficiently large number of samples are obtained to ensure the excellent performance of the multilayer CNN. For a testing pixel, the input of the trained CNN is the spectral difference between the central pixel and its adjacent pixels. When a test pixel belongs to the target, the output score will be close to the target label. To verify the effectiveness of the proposed method, aircrafts and vehicles are used as targets of interest, while another 27 objects are chosen as background classes (e.g., vegetation and runways). Our experimental results on four images indicate that the proposed detector outperforms classic hyperspectral target detection algorithms. |
| first_indexed | 2024-12-16T17:27:59Z |
| format | Article |
| id | doaj.art-40326ae634334645aad7372a9ac322d3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T17:27:59Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-40326ae634334645aad7372a9ac322d32022-12-21T22:23:00ZengIEEEIEEE Access2169-35362018-01-016455624557710.1109/ACCESS.2018.28659638438875A Hyperspectral Target Detection Framework With Subtraction Pixel Pair FeaturesJinming Du0https://orcid.org/0000-0003-3428-4729Zhiyong Li1School of Electronic Science, National University of Defense Technology, Changsha, ChinaHunan Shenfan Technology Co., Ltd., Changsha, ChinaIn recent years, due to its strong nonlinear mapping and research capacities, the convolutional neural network (CNN) has been widely used in the field of hyperspectral image (HSI) processing. Recently, pixel pair features (PPFs) and spatial PPFs (SPPFs) for HSI classification have served as the new tools for feature extraction. In this paper, on top of PPF, improved subtraction pixel pair features (subtraction-PPFs) are applied for HSI target detection. Unlike original PPF and SPPF, the subtraction-PPF considers target classes to afford the CNN, a target detection function. Using subtraction-PPF, a sufficiently large number of samples are obtained to ensure the excellent performance of the multilayer CNN. For a testing pixel, the input of the trained CNN is the spectral difference between the central pixel and its adjacent pixels. When a test pixel belongs to the target, the output score will be close to the target label. To verify the effectiveness of the proposed method, aircrafts and vehicles are used as targets of interest, while another 27 objects are chosen as background classes (e.g., vegetation and runways). Our experimental results on four images indicate that the proposed detector outperforms classic hyperspectral target detection algorithms.https://ieeexplore.ieee.org/document/8438875/Target detectionhyperspectral imagerydeep learningconvolutional neural networksubtraction pixel pair features |
| spellingShingle | Jinming Du Zhiyong Li A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features IEEE Access Target detection hyperspectral imagery deep learning convolutional neural network subtraction pixel pair features |
| title | A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features |
| title_full | A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features |
| title_fullStr | A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features |
| title_full_unstemmed | A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features |
| title_short | A Hyperspectral Target Detection Framework With Subtraction Pixel Pair Features |
| title_sort | hyperspectral target detection framework with subtraction pixel pair features |
| topic | Target detection hyperspectral imagery deep learning convolutional neural network subtraction pixel pair features |
| url | https://ieeexplore.ieee.org/document/8438875/ |
| work_keys_str_mv | AT jinmingdu ahyperspectraltargetdetectionframeworkwithsubtractionpixelpairfeatures AT zhiyongli ahyperspectraltargetdetectionframeworkwithsubtractionpixelpairfeatures AT jinmingdu hyperspectraltargetdetectionframeworkwithsubtractionpixelpairfeatures AT zhiyongli hyperspectraltargetdetectionframeworkwithsubtractionpixelpairfeatures |