An automatic power line inspection method based on an improved SegNet network
UAVs （unmanned aerial vehicles） are now involved in intelligent transmission line inspection. Given the complex image backgrounds captured by UAVs and poor line inspection accuracy and low detection speed of UAVs， the paper proposes a power line inspection algorithm based on an improved SegNet model...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2023-06-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=1d747c03-f478-47a9-964b-f809e599c271 |
| _version_ | 1797788197236768768 |
|---|---|
| author | YANG Jian LI Jian XU Shuo |
| author_facet | YANG Jian LI Jian XU Shuo |
| author_sort | YANG Jian |
| collection | DOAJ |
| description | UAVs （unmanned aerial vehicles） are now involved in intelligent transmission line inspection. Given the complex image backgrounds captured by UAVs and poor line inspection accuracy and low detection speed of UAVs， the paper proposes a power line inspection algorithm based on an improved SegNet model. Firstly， residual modules and asymmetric convolutions are introduced into the encoder to reduce the computational burden on the network. Secondly， the network layers of the decoding layer are reduced， and the features of the encoder and decoder are fused to improve inspection accuracy. Finally， the improved SegNet algorithm is used to train the power line dataset. The accuracy and mean intersection over union reach up to 89.4% and 86.62% respectively， and the single detection time is 46 ms. The experimental results show that the algorithm based on the improved SegNet model can achieve high-precision and real-time power line detection. |
| first_indexed | 2024-03-13T01:32:11Z |
| format | Article |
| id | doaj.art-93e872b424814eb083f8fdd35dc8dd03 |
| institution | Directory Open Access Journal |
| issn | 1007-1881 |
| language | zho |
| last_indexed | 2024-03-13T01:32:11Z |
| publishDate | 2023-06-01 |
| publisher | zhejiang electric power |
| record_format | Article |
| series | Zhejiang dianli |
| spelling | doaj.art-93e872b424814eb083f8fdd35dc8dd032023-07-04T06:43:14Zzhozhejiang electric powerZhejiang dianli1007-18812023-06-0142611211810.19585/j.zjdl.2023060131007-1881（2023）06-0112-07An automatic power line inspection method based on an improved SegNet networkYANG JianLI JianXU ShuoUAVs （unmanned aerial vehicles） are now involved in intelligent transmission line inspection. Given the complex image backgrounds captured by UAVs and poor line inspection accuracy and low detection speed of UAVs， the paper proposes a power line inspection algorithm based on an improved SegNet model. Firstly， residual modules and asymmetric convolutions are introduced into the encoder to reduce the computational burden on the network. Secondly， the network layers of the decoding layer are reduced， and the features of the encoder and decoder are fused to improve inspection accuracy. Finally， the improved SegNet algorithm is used to train the power line dataset. The accuracy and mean intersection over union reach up to 89.4% and 86.62% respectively， and the single detection time is 46 ms. The experimental results show that the algorithm based on the improved SegNet model can achieve high-precision and real-time power line detection.https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=1d747c03-f478-47a9-964b-f809e599c271uav inspectiondeep learningimproved segnetresidual moduleasymmetric convolution |
| spellingShingle | YANG Jian LI Jian XU Shuo An automatic power line inspection method based on an improved SegNet network Zhejiang dianli uav inspection deep learning improved segnet residual module asymmetric convolution |
| title | An automatic power line inspection method based on an improved SegNet network |
| title_full | An automatic power line inspection method based on an improved SegNet network |
| title_fullStr | An automatic power line inspection method based on an improved SegNet network |
| title_full_unstemmed | An automatic power line inspection method based on an improved SegNet network |
| title_short | An automatic power line inspection method based on an improved SegNet network |
| title_sort | automatic power line inspection method based on an improved segnet network |
| topic | uav inspection deep learning improved segnet residual module asymmetric convolution |
| url | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=1d747c03-f478-47a9-964b-f809e599c271 |
| work_keys_str_mv | AT yangjian anautomaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork AT lijian anautomaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork AT xushuo anautomaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork AT yangjian automaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork AT lijian automaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork AT xushuo automaticpowerlineinspectionmethodbasedonanimprovedsegnetnetwork |