SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests
Efficient and precise forest surveys are crucial for in-depth understanding of the present state of forest resources and conducting scientific forest management. Close-range photogrammetry (CRP) technology enables the convenient and fast collection of highly overlapping sequential images, facilitati...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/2/416 |
| _version_ | 1797342610188140544 |
|---|---|
| author | Xuanhao Yan Guoqi Chai Xinyi Han Lingting Lei Geng Wang Xiang Jia Xiaoli Zhang |
| author_facet | Xuanhao Yan Guoqi Chai Xinyi Han Lingting Lei Geng Wang Xiang Jia Xiaoli Zhang |
| author_sort | Xuanhao Yan |
| collection | DOAJ |
| description | Efficient and precise forest surveys are crucial for in-depth understanding of the present state of forest resources and conducting scientific forest management. Close-range photogrammetry (CRP) technology enables the convenient and fast collection of highly overlapping sequential images, facilitating the reconstruction of 3D models of forest scenes, which significantly improves the efficiency of forest surveys and holds great potential for forestry visualization management. However, in practical forestry applications, CRP technology still presents challenges, such as low image quality and low reconstruction rates when dealing with complex undergrowth vegetation or forest terrain scenes. In this study, we utilized an iPad Pro device equipped with high-resolution cameras to collect sequential images of four plots in Gaofeng Forest Farm in Guangxi and Genhe Nature Reserve in Inner Mongolia, China. First, we compared the image enhancement effects of two algorithms: histogram equalization (HE) and median–Gaussian filtering (MG). Then, we proposed a deep learning network model called SA-Pmnet based on self-attention mechanisms for 3D reconstruction of forest scenes. The performance of the SA-Pmnet model was compared with that of the traditional SfM+MVS algorithm and the Patchmatchnet network model. The results show that histogram equalization significantly increases the number of matched feature points in the images and improves the uneven distribution of lighting. The deep learning networks demonstrate better performance in complex environmental forest scenes. The SA-Pmnet network, which employs self-attention mechanisms, improves the 3D reconstruction rate in the four plots to 94%, 92%, 94%, and 96% by capturing more details and achieves higher extraction accuracy of diameter at breast height (DBH) with values of 91.8%, 94.1%, 94.7%, and 91.2% respectively. These findings demonstrate the potential of combining of the image enhancement algorithm with deep learning models based on self-attention mechanisms for 3D reconstruction of forests, providing effective support for forest resource surveys and visualization management. |
| first_indexed | 2024-03-08T10:35:46Z |
| format | Article |
| id | doaj.art-c7c1eb50f682491d8946f687fbd1edef |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T10:35:46Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c7c1eb50f682491d8946f687fbd1edef2024-01-26T18:20:10ZengMDPI AGRemote Sensing2072-42922024-01-0116241610.3390/rs16020416SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of ForestsXuanhao Yan0Guoqi Chai1Xinyi Han2Lingting Lei3Geng Wang4Xiang Jia5Xiaoli Zhang6State Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaState Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing 100083, ChinaEfficient and precise forest surveys are crucial for in-depth understanding of the present state of forest resources and conducting scientific forest management. Close-range photogrammetry (CRP) technology enables the convenient and fast collection of highly overlapping sequential images, facilitating the reconstruction of 3D models of forest scenes, which significantly improves the efficiency of forest surveys and holds great potential for forestry visualization management. However, in practical forestry applications, CRP technology still presents challenges, such as low image quality and low reconstruction rates when dealing with complex undergrowth vegetation or forest terrain scenes. In this study, we utilized an iPad Pro device equipped with high-resolution cameras to collect sequential images of four plots in Gaofeng Forest Farm in Guangxi and Genhe Nature Reserve in Inner Mongolia, China. First, we compared the image enhancement effects of two algorithms: histogram equalization (HE) and median–Gaussian filtering (MG). Then, we proposed a deep learning network model called SA-Pmnet based on self-attention mechanisms for 3D reconstruction of forest scenes. The performance of the SA-Pmnet model was compared with that of the traditional SfM+MVS algorithm and the Patchmatchnet network model. The results show that histogram equalization significantly increases the number of matched feature points in the images and improves the uneven distribution of lighting. The deep learning networks demonstrate better performance in complex environmental forest scenes. The SA-Pmnet network, which employs self-attention mechanisms, improves the 3D reconstruction rate in the four plots to 94%, 92%, 94%, and 96% by capturing more details and achieves higher extraction accuracy of diameter at breast height (DBH) with values of 91.8%, 94.1%, 94.7%, and 91.2% respectively. These findings demonstrate the potential of combining of the image enhancement algorithm with deep learning models based on self-attention mechanisms for 3D reconstruction of forests, providing effective support for forest resource surveys and visualization management.https://www.mdpi.com/2072-4292/16/2/416close-range photogrammetry (CRP)image enhancementdeep learningself-attentionSA-Pmnet3D reconstruction |
| spellingShingle | Xuanhao Yan Guoqi Chai Xinyi Han Lingting Lei Geng Wang Xiang Jia Xiaoli Zhang SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests Remote Sensing close-range photogrammetry (CRP) image enhancement deep learning self-attention SA-Pmnet 3D reconstruction |
| title | SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests |
| title_full | SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests |
| title_fullStr | SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests |
| title_full_unstemmed | SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests |
| title_short | SA-Pmnet: Utilizing Close-Range Photogrammetry Combined with Image Enhancement and Self-Attention Mechanisms for 3D Reconstruction of Forests |
| title_sort | sa pmnet utilizing close range photogrammetry combined with image enhancement and self attention mechanisms for 3d reconstruction of forests |
| topic | close-range photogrammetry (CRP) image enhancement deep learning self-attention SA-Pmnet 3D reconstruction |
| url | https://www.mdpi.com/2072-4292/16/2/416 |
| work_keys_str_mv | AT xuanhaoyan sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT guoqichai sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT xinyihan sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT lingtinglei sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT gengwang sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT xiangjia sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests AT xiaolizhang sapmnetutilizingcloserangephotogrammetrycombinedwithimageenhancementandselfattentionmechanismsfor3dreconstructionofforests |