Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images
To avoid using a large 4D-Hough counting space (HCS) and complex invariant features of generalized Hough transform (GHT) or its extensions when detecting objects in remote sensing image (RSI), a tensored GHT (TGHT) is proposed to extract object contour by simple gradient angle feature in a 2D-HCS us...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9119818/ |
| _version_ | 1818740167573241856 |
|---|---|
| author | Hao Chen Tong Gao Guodong Qian Wen Chen Ye Zhang |
| author_facet | Hao Chen Tong Gao Guodong Qian Wen Chen Ye Zhang |
| author_sort | Hao Chen |
| collection | DOAJ |
| description | To avoid using a large 4D-Hough counting space (HCS) and complex invariant features of generalized Hough transform (GHT) or its extensions when detecting objects in remote sensing image (RSI), a tensored GHT (TGHT) is proposed to extract object contour by simple gradient angle feature in a 2D-HCS using a single training sample. Considering that tensor can record the structure relationship of object contour, tensor representation R-table is constructed to record the contour information of template. For slice centered at each position of RSI, the tensor-space-based voting mechanism is presented to use the tensor that records the contour information of slice to gather votes at the same entry of 2D-HCS. Furthermore, a multiorder binary-tree-based searching method is presented to accelerate voting by searching the index numbers of elements in tensors. In addition, by solving the tensor-space-based optimization problem that is used to determine the candidates objects, the cause of false alarms (FAs) caused by interferences with complex contour and FAs caused by interferences that are partial-similar to objects is revealed, and the matching rate and matching sparsity-based strategies are then proposed to remove these FAs. Using public RSI datasets with different scenes, experimental results demonstrate that TGHT reduces nearly 99% storage requirement compared with GHT for RSI with size exceeding 1000 × 1000 under small time consumption, and outperforms the well-known contour extraction methods and state-of-the-art deep-learning-based methods in terms of precision and recall. |
| first_indexed | 2024-12-18T01:36:26Z |
| format | Article |
| id | doaj.art-593994e1265f49608a2ea46cf6122e0f |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-18T01:36:26Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-593994e1265f49608a2ea46cf6122e0f2022-12-21T21:25:26ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01133503352010.1109/JSTARS.2020.30031379119818Tensored Generalized Hough Transform for Object Detection in Remote Sensing ImagesHao Chen0https://orcid.org/0000-0002-1837-3986Tong Gao1Guodong Qian2Wen Chen3Ye Zhang4https://orcid.org/0000-0001-8721-4535School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaBeijing Institute of Remote Sensing Information, Beijing, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaTo avoid using a large 4D-Hough counting space (HCS) and complex invariant features of generalized Hough transform (GHT) or its extensions when detecting objects in remote sensing image (RSI), a tensored GHT (TGHT) is proposed to extract object contour by simple gradient angle feature in a 2D-HCS using a single training sample. Considering that tensor can record the structure relationship of object contour, tensor representation R-table is constructed to record the contour information of template. For slice centered at each position of RSI, the tensor-space-based voting mechanism is presented to use the tensor that records the contour information of slice to gather votes at the same entry of 2D-HCS. Furthermore, a multiorder binary-tree-based searching method is presented to accelerate voting by searching the index numbers of elements in tensors. In addition, by solving the tensor-space-based optimization problem that is used to determine the candidates objects, the cause of false alarms (FAs) caused by interferences with complex contour and FAs caused by interferences that are partial-similar to objects is revealed, and the matching rate and matching sparsity-based strategies are then proposed to remove these FAs. Using public RSI datasets with different scenes, experimental results demonstrate that TGHT reduces nearly 99% storage requirement compared with GHT for RSI with size exceeding 1000 × 1000 under small time consumption, and outperforms the well-known contour extraction methods and state-of-the-art deep-learning-based methods in terms of precision and recall.https://ieeexplore.ieee.org/document/9119818/Multiorder binary-tree-based searching methodobject detectiontensor-space-based contour extractiontensor-space-based false alarms (FAs) removaltensored generalized Hough transform (TGHT) |
| spellingShingle | Hao Chen Tong Gao Guodong Qian Wen Chen Ye Zhang Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Multiorder binary-tree-based searching method object detection tensor-space-based contour extraction tensor-space-based false alarms (FAs) removal tensored generalized Hough transform (TGHT) |
| title | Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images |
| title_full | Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images |
| title_fullStr | Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images |
| title_full_unstemmed | Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images |
| title_short | Tensored Generalized Hough Transform for Object Detection in Remote Sensing Images |
| title_sort | tensored generalized hough transform for object detection in remote sensing images |
| topic | Multiorder binary-tree-based searching method object detection tensor-space-based contour extraction tensor-space-based false alarms (FAs) removal tensored generalized Hough transform (TGHT) |
| url | https://ieeexplore.ieee.org/document/9119818/ |
| work_keys_str_mv | AT haochen tensoredgeneralizedhoughtransformforobjectdetectioninremotesensingimages AT tonggao tensoredgeneralizedhoughtransformforobjectdetectioninremotesensingimages AT guodongqian tensoredgeneralizedhoughtransformforobjectdetectioninremotesensingimages AT wenchen tensoredgeneralizedhoughtransformforobjectdetectioninremotesensingimages AT yezhang tensoredgeneralizedhoughtransformforobjectdetectioninremotesensingimages |