An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features
In the geological research of the Moon and other celestial bodies, the identification and analysis of impact craters are crucial for understanding the geological history of these bodies. With the rapid increase in the volume of high-resolution imagery data returned from exploration missions, traditi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/7/1262 |
| _version_ | 1797212691975110656 |
|---|---|
| author | Yingnan Zhang Zhizhong Kang Zhen Cao |
| author_facet | Yingnan Zhang Zhizhong Kang Zhen Cao |
| author_sort | Yingnan Zhang |
| collection | DOAJ |
| description | In the geological research of the Moon and other celestial bodies, the identification and analysis of impact craters are crucial for understanding the geological history of these bodies. With the rapid increase in the volume of high-resolution imagery data returned from exploration missions, traditional image retrieval methods face dual challenges of efficiency and accuracy when processing lunar complex crater image data. Deep learning techniques offer a potential solution. This paper proposes an image retrieval model for lunar complex craters that integrates visual and depth features (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula>) to overcome these difficulties. For depth feature extraction, we employ the Swin Transformer as the core architecture for feature extraction and enhance the recognition capability for key crater features by integrating the Convolutional Block Attention Module with Effective Channel Attention (CBAMwithECA). Furthermore, a triplet loss function is introduced to generate highly discriminative image embeddings, further optimizing the embedding space for similarity retrieval. In terms of visual feature extraction, we utilize Local Binary Patterns (LBP) and Hu moments to extract the texture and shape features of crater images. By performing a weighted fusion of these features and utilizing Principal Component Analysis (PCA) for dimensionality reduction, we effectively combine visual and depth features and optimize retrieval efficiency. Finally, cosine similarity is used to calculate the similarity between query images and images in the database, returning the most similar images as retrieval results. Validation experiments conducted on the lunar complex impact crater dataset constructed in this article demonstrate that <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula> achieves a retrieval precision of 83.75%, showcasing superior efficiency. These experimental results confirm the advantages of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula> in handling the task of lunar complex impact crater image retrieval. |
| first_indexed | 2024-04-24T10:46:25Z |
| format | Article |
| id | doaj.art-3cc7f7a5063f46cd8066f6e702ff4922 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-24T10:46:25Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3cc7f7a5063f46cd8066f6e702ff49222024-04-12T13:17:13ZengMDPI AGElectronics2079-92922024-03-01137126210.3390/electronics13071262An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth FeaturesYingnan Zhang0Zhizhong Kang1Zhen Cao2School of Land Science and Technology, China University of Geosciences, Beijing 100083, ChinaSchool of Land Science and Technology, China University of Geosciences, Beijing 100083, ChinaSchool of Land Science and Technology, China University of Geosciences, Beijing 100083, ChinaIn the geological research of the Moon and other celestial bodies, the identification and analysis of impact craters are crucial for understanding the geological history of these bodies. With the rapid increase in the volume of high-resolution imagery data returned from exploration missions, traditional image retrieval methods face dual challenges of efficiency and accuracy when processing lunar complex crater image data. Deep learning techniques offer a potential solution. This paper proposes an image retrieval model for lunar complex craters that integrates visual and depth features (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula>) to overcome these difficulties. For depth feature extraction, we employ the Swin Transformer as the core architecture for feature extraction and enhance the recognition capability for key crater features by integrating the Convolutional Block Attention Module with Effective Channel Attention (CBAMwithECA). Furthermore, a triplet loss function is introduced to generate highly discriminative image embeddings, further optimizing the embedding space for similarity retrieval. In terms of visual feature extraction, we utilize Local Binary Patterns (LBP) and Hu moments to extract the texture and shape features of crater images. By performing a weighted fusion of these features and utilizing Principal Component Analysis (PCA) for dimensionality reduction, we effectively combine visual and depth features and optimize retrieval efficiency. Finally, cosine similarity is used to calculate the similarity between query images and images in the database, returning the most similar images as retrieval results. Validation experiments conducted on the lunar complex impact crater dataset constructed in this article demonstrate that <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula> achieves a retrieval precision of 83.75%, showcasing superior efficiency. These experimental results confirm the advantages of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>LC</mi><mn>2</mn></msup><mrow><mi mathvariant="normal">R</mi><mo>-</mo><mi>Net</mi></mrow></mrow></semantics></math></inline-formula> in handling the task of lunar complex impact crater image retrieval.https://www.mdpi.com/2079-9292/13/7/1262LC<sup>2</sup>R-NetCBAMECAimpact craterimage retrievaldeep learning |
| spellingShingle | Yingnan Zhang Zhizhong Kang Zhen Cao An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features Electronics LC<sup>2</sup>R-Net CBAM ECA impact crater image retrieval deep learning |
| title | An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features |
| title_full | An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features |
| title_fullStr | An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features |
| title_full_unstemmed | An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features |
| title_short | An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features |
| title_sort | image retrieval method for lunar complex craters integrating visual and depth features |
| topic | LC<sup>2</sup>R-Net CBAM ECA impact crater image retrieval deep learning |
| url | https://www.mdpi.com/2079-9292/13/7/1262 |
| work_keys_str_mv | AT yingnanzhang animageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures AT zhizhongkang animageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures AT zhencao animageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures AT yingnanzhang imageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures AT zhizhongkang imageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures AT zhencao imageretrievalmethodforlunarcomplexcratersintegratingvisualanddepthfeatures |