Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks
Today, hyperspectral imaging plays an integral part in the remote sensing and precision agriculture field. Identifying the matching key points between hyperspectral images is an important step in tasks such as image registration, localization, object recognition, and object tracking. Low-pixel resol...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/8004 |
| _version_ | 1797576890605633536 |
|---|---|
| author | Chamika Janith Perera Chinthaka Premachandra Hiroharu Kawanaka |
| author_facet | Chamika Janith Perera Chinthaka Premachandra Hiroharu Kawanaka |
| author_sort | Chamika Janith Perera |
| collection | DOAJ |
| description | Today, hyperspectral imaging plays an integral part in the remote sensing and precision agriculture field. Identifying the matching key points between hyperspectral images is an important step in tasks such as image registration, localization, object recognition, and object tracking. Low-pixel resolution hyperspectral imaging is a recent introduction to the field, bringing benefits such as lower cost and form factor compared to traditional systems. However, the use of limited pixel resolution challenges even state-of-the-art feature detection and matching methods, leading to difficulties in generating robust feature matches for images with repeated textures, low textures, low sharpness, and low contrast. Moreover, the use of narrower optics in these cameras adds to the challenges during the feature-matching stage, particularly for images captured during low-altitude flight missions. In order to enhance the robustness of feature detection and matching in low pixel resolution images, in this study we propose a novel approach utilizing 3D Convolution-based Siamese networks. Compared to state-of-the-art methods, this approach takes advantage of all the spectral information available in hyperspectral imaging in order to filter out incorrect matches and produce a robust set of matches. The proposed method initially generates feature matches through a combination of Phase Stretch Transformation-based edge detection and SIFT features. Subsequently, a 3D Convolution-based Siamese network is utilized to filter out inaccurate matches, producing a highly accurate set of feature matches. Evaluation of the proposed method demonstrates its superiority over state-of-the-art approaches in cases where they fail to produce feature matches. Additionally, it competes effectively with the other evaluated methods when generating feature matches in low-pixel resolution hyperspectral images. This research contributes to the advancement of low pixel resolution hyperspectral imaging techniques, and we believe it can specifically aid in mosaic generation of low pixel resolution hyperspectral images. |
| first_indexed | 2024-03-10T22:01:11Z |
| format | Article |
| id | doaj.art-2f7ee3df6f24466bbb36aa5e30d721de |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:01:11Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2f7ee3df6f24466bbb36aa5e30d721de2023-11-19T12:57:19ZengMDPI AGSensors1424-82202023-09-012318800410.3390/s23188004Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese NetworksChamika Janith Perera0Chinthaka Premachandra1Hiroharu Kawanaka2Graduate School of Engineering, Mie University, Tsu 514-0102, JapanDepartment of Electrical Engineering and Computer Science, Graduate School of Engineering and Science, Shibaura Institute of Technology, Tokyo 135-8548, JapanGraduate School of Engineering, Mie University, Tsu 514-0102, JapanToday, hyperspectral imaging plays an integral part in the remote sensing and precision agriculture field. Identifying the matching key points between hyperspectral images is an important step in tasks such as image registration, localization, object recognition, and object tracking. Low-pixel resolution hyperspectral imaging is a recent introduction to the field, bringing benefits such as lower cost and form factor compared to traditional systems. However, the use of limited pixel resolution challenges even state-of-the-art feature detection and matching methods, leading to difficulties in generating robust feature matches for images with repeated textures, low textures, low sharpness, and low contrast. Moreover, the use of narrower optics in these cameras adds to the challenges during the feature-matching stage, particularly for images captured during low-altitude flight missions. In order to enhance the robustness of feature detection and matching in low pixel resolution images, in this study we propose a novel approach utilizing 3D Convolution-based Siamese networks. Compared to state-of-the-art methods, this approach takes advantage of all the spectral information available in hyperspectral imaging in order to filter out incorrect matches and produce a robust set of matches. The proposed method initially generates feature matches through a combination of Phase Stretch Transformation-based edge detection and SIFT features. Subsequently, a 3D Convolution-based Siamese network is utilized to filter out inaccurate matches, producing a highly accurate set of feature matches. Evaluation of the proposed method demonstrates its superiority over state-of-the-art approaches in cases where they fail to produce feature matches. Additionally, it competes effectively with the other evaluated methods when generating feature matches in low-pixel resolution hyperspectral images. This research contributes to the advancement of low pixel resolution hyperspectral imaging techniques, and we believe it can specifically aid in mosaic generation of low pixel resolution hyperspectral images.https://www.mdpi.com/1424-8220/23/18/8004hyperspectral imagingfeature matching3D convolution Siamese network |
| spellingShingle | Chamika Janith Perera Chinthaka Premachandra Hiroharu Kawanaka Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks Sensors hyperspectral imaging feature matching 3D convolution Siamese network |
| title | Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks |
| title_full | Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks |
| title_fullStr | Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks |
| title_full_unstemmed | Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks |
| title_short | Enhancing Feature Detection and Matching in Low-Pixel-Resolution Hyperspectral Images Using 3D Convolution-Based Siamese Networks |
| title_sort | enhancing feature detection and matching in low pixel resolution hyperspectral images using 3d convolution based siamese networks |
| topic | hyperspectral imaging feature matching 3D convolution Siamese network |
| url | https://www.mdpi.com/1424-8220/23/18/8004 |
| work_keys_str_mv | AT chamikajanithperera enhancingfeaturedetectionandmatchinginlowpixelresolutionhyperspectralimagesusing3dconvolutionbasedsiamesenetworks AT chinthakapremachandra enhancingfeaturedetectionandmatchinginlowpixelresolutionhyperspectralimagesusing3dconvolutionbasedsiamesenetworks AT hiroharukawanaka enhancingfeaturedetectionandmatchinginlowpixelresolutionhyperspectralimagesusing3dconvolutionbasedsiamesenetworks |