A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED
Automatic extraction of tailing ponds from Very High-Resolution (VHR) remotely sensed images is vital for mineral resource management. This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network (PSVED) to achieve high accuracy tailing ponds extraction from VHR images. First,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2023.2234338 |
| _version_ | 1797678416589225984 |
|---|---|
| author | Chengye Zhang Jianghe Xing Jun Li Shouhang Du Qiming Qin |
| author_facet | Chengye Zhang Jianghe Xing Jun Li Shouhang Du Qiming Qin |
| author_sort | Chengye Zhang |
| collection | DOAJ |
| description | Automatic extraction of tailing ponds from Very High-Resolution (VHR) remotely sensed images is vital for mineral resource management. This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network (PSVED) to achieve high accuracy tailing ponds extraction from VHR images. First, handcrafted feature (HCF) images are calculated from VHR images based on the index calculation algorithm, highlighting the tailing ponds’ signals. Second, considering the information gap between VHR images and HCF images, the Pseudo-Siamese Visual Geometry Group (Pseudo-Siamese VGG) is utilized to extract independent and representative deep semantic features from VHR images and HCF images, respectively. Third, the deep supervision mechanism is attached to handle the optimization problem of gradients vanishing or exploding. A self-made tailing ponds extraction dataset (TPSet) produced with the Gaofen-6 images of part of Hebei province, China, was employed to conduct experiments. The results show that the proposed method achieves the best visual performance and accuracy for tailing ponds extraction in all the tested methods, whereas the running time of the proposed method maintains at the same level as other methods. This study has practical significance in automatically extracting tailing ponds from VHR images which is beneficial to tailing ponds management and monitoring. |
| first_indexed | 2024-03-11T22:59:28Z |
| format | Article |
| id | doaj.art-42afffdb577f4abf90eb616e735cd820 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T22:59:28Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-42afffdb577f4abf90eb616e735cd8202023-09-21T15:09:03ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552023-12-011612681270310.1080/17538947.2023.22343382234338A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVEDChengye Zhang0Jianghe Xing1Jun Li2Shouhang Du3Qiming Qin4China University of Mining and TechnologyChina University of Mining and TechnologyChina University of Mining and TechnologyChina University of Mining and TechnologyPeking UniversityAutomatic extraction of tailing ponds from Very High-Resolution (VHR) remotely sensed images is vital for mineral resource management. This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network (PSVED) to achieve high accuracy tailing ponds extraction from VHR images. First, handcrafted feature (HCF) images are calculated from VHR images based on the index calculation algorithm, highlighting the tailing ponds’ signals. Second, considering the information gap between VHR images and HCF images, the Pseudo-Siamese Visual Geometry Group (Pseudo-Siamese VGG) is utilized to extract independent and representative deep semantic features from VHR images and HCF images, respectively. Third, the deep supervision mechanism is attached to handle the optimization problem of gradients vanishing or exploding. A self-made tailing ponds extraction dataset (TPSet) produced with the Gaofen-6 images of part of Hebei province, China, was employed to conduct experiments. The results show that the proposed method achieves the best visual performance and accuracy for tailing ponds extraction in all the tested methods, whereas the running time of the proposed method maintains at the same level as other methods. This study has practical significance in automatically extracting tailing ponds from VHR images which is beneficial to tailing ponds management and monitoring.http://dx.doi.org/10.1080/17538947.2023.2234338semantic segmentationtailing storage facilitiespseudo-siamese networkvhr imagesdeep supervision mechanism |
| spellingShingle | Chengye Zhang Jianghe Xing Jun Li Shouhang Du Qiming Qin A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED International Journal of Digital Earth semantic segmentation tailing storage facilities pseudo-siamese network vhr images deep supervision mechanism |
| title | A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED |
| title_full | A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED |
| title_fullStr | A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED |
| title_full_unstemmed | A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED |
| title_short | A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED |
| title_sort | new method for the extraction of tailing ponds from very high resolution remotely sensed images psved |
| topic | semantic segmentation tailing storage facilities pseudo-siamese network vhr images deep supervision mechanism |
| url | http://dx.doi.org/10.1080/17538947.2023.2234338 |
| work_keys_str_mv | AT chengyezhang anewmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT jianghexing anewmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT junli anewmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT shouhangdu anewmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT qimingqin anewmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT chengyezhang newmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT jianghexing newmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT junli newmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT shouhangdu newmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved AT qimingqin newmethodfortheextractionoftailingpondsfromveryhighresolutionremotelysensedimagespsved |