An Assembled Detector Based on Geometrical Constraint for Power Component Recognition
The intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene contain...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/16/3517 |
| _version_ | 1798024325200084992 |
|---|---|
| author | Zheng Ji Yifan Liao Li Zheng Liang Wu Manzhu Yu Yanjie Feng |
| author_facet | Zheng Ji Yifan Liao Li Zheng Liang Wu Manzhu Yu Yanjie Feng |
| author_sort | Zheng Ji |
| collection | DOAJ |
| description | The intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios. |
| first_indexed | 2024-04-11T18:00:44Z |
| format | Article |
| id | doaj.art-34fcb70ec74943c48df244a160cbc256 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:00:44Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-34fcb70ec74943c48df244a160cbc2562022-12-22T04:10:32ZengMDPI AGSensors1424-82202019-08-011916351710.3390/s19163517s19163517An Assembled Detector Based on Geometrical Constraint for Power Component RecognitionZheng Ji0Yifan Liao1Li Zheng2Liang Wu3Manzhu Yu4Yanjie Feng5School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaDepartment of Geography, Pennsylvania State University, State College, PA 16801, USAShenzhen Power Supply Planning Design Institute Co., Ltd., Shenzhen 518054, ChinaThe intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios.https://www.mdpi.com/1424-8220/19/16/3517virtual imagevibration damperassembled detector based on the geometrical constraint (ADGC)object detectiondeep learning |
| spellingShingle | Zheng Ji Yifan Liao Li Zheng Liang Wu Manzhu Yu Yanjie Feng An Assembled Detector Based on Geometrical Constraint for Power Component Recognition Sensors virtual image vibration damper assembled detector based on the geometrical constraint (ADGC) object detection deep learning |
| title | An Assembled Detector Based on Geometrical Constraint for Power Component Recognition |
| title_full | An Assembled Detector Based on Geometrical Constraint for Power Component Recognition |
| title_fullStr | An Assembled Detector Based on Geometrical Constraint for Power Component Recognition |
| title_full_unstemmed | An Assembled Detector Based on Geometrical Constraint for Power Component Recognition |
| title_short | An Assembled Detector Based on Geometrical Constraint for Power Component Recognition |
| title_sort | assembled detector based on geometrical constraint for power component recognition |
| topic | virtual image vibration damper assembled detector based on the geometrical constraint (ADGC) object detection deep learning |
| url | https://www.mdpi.com/1424-8220/19/16/3517 |
| work_keys_str_mv | AT zhengji anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT yifanliao anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT lizheng anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT liangwu anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT manzhuyu anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT yanjiefeng anassembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT zhengji assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT yifanliao assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT lizheng assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT liangwu assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT manzhuyu assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition AT yanjiefeng assembleddetectorbasedongeometricalconstraintforpowercomponentrecognition |