MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images
Insulator detection is an essential task for the safety and reliable operation of intelligent grids. Owing to insulator images including various background interferences, most traditional image-processing methods cannot achieve good performance. Some You Only Look Once (YOLO) networks are employed t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/5/1426 |
| _version_ | 1827602590736580608 |
|---|---|
| author | Chuanyang Liu Yiquan Wu Jingjing Liu Jiaming Han |
| author_facet | Chuanyang Liu Yiquan Wu Jingjing Liu Jiaming Han |
| author_sort | Chuanyang Liu |
| collection | DOAJ |
| description | Insulator detection is an essential task for the safety and reliable operation of intelligent grids. Owing to insulator images including various background interferences, most traditional image-processing methods cannot achieve good performance. Some You Only Look Once (YOLO) networks are employed to meet the requirements of actual applications for insulator detection. To achieve a good trade-off among accuracy, running time, and memory storage, this work proposes the modified YOLO-tiny for insulator (MTI-YOLO) network for insulator detection in complex aerial images. First of all, composite insulator images are collected in common scenes and the “CCIN_detection” (Chinese Composite INsulator) dataset is constructed. Secondly, to improve the detection accuracy of different sizes of insulator, multi-scale feature detection headers, a structure of multi-scale feature fusion, and the spatial pyramid pooling (SPP) model are adopted to the MTI-YOLO network. Finally, the proposed MTI-YOLO network and the compared networks are trained and tested on the “CCIN_detection” dataset. The average precision (AP) of our proposed network is 17% and 9% higher than YOLO-tiny and YOLO-v2. Compared with YOLO-tiny and YOLO-v2, the running time of the proposed network is slightly higher. Furthermore, the memory usage of the proposed network is 25.6% and 38.9% lower than YOLO-v2 and YOLO-v3, respectively. Experimental results and analysis validate that the proposed network achieves good performance in both complex backgrounds and bright illumination conditions. |
| first_indexed | 2024-03-09T05:22:38Z |
| format | Article |
| id | doaj.art-da66652a1d954c94b1e43b1cf5adb08b |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T05:22:38Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-da66652a1d954c94b1e43b1cf5adb08b2023-12-03T12:39:55ZengMDPI AGEnergies1996-10732021-03-01145142610.3390/en14051426MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial ImagesChuanyang Liu0Yiquan Wu1Jingjing Liu2Jiaming Han3College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Mechanical and Electrical Engineering, Chizhou University, Chizhou 247000, ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, ChinaInsulator detection is an essential task for the safety and reliable operation of intelligent grids. Owing to insulator images including various background interferences, most traditional image-processing methods cannot achieve good performance. Some You Only Look Once (YOLO) networks are employed to meet the requirements of actual applications for insulator detection. To achieve a good trade-off among accuracy, running time, and memory storage, this work proposes the modified YOLO-tiny for insulator (MTI-YOLO) network for insulator detection in complex aerial images. First of all, composite insulator images are collected in common scenes and the “CCIN_detection” (Chinese Composite INsulator) dataset is constructed. Secondly, to improve the detection accuracy of different sizes of insulator, multi-scale feature detection headers, a structure of multi-scale feature fusion, and the spatial pyramid pooling (SPP) model are adopted to the MTI-YOLO network. Finally, the proposed MTI-YOLO network and the compared networks are trained and tested on the “CCIN_detection” dataset. The average precision (AP) of our proposed network is 17% and 9% higher than YOLO-tiny and YOLO-v2. Compared with YOLO-tiny and YOLO-v2, the running time of the proposed network is slightly higher. Furthermore, the memory usage of the proposed network is 25.6% and 38.9% lower than YOLO-v2 and YOLO-v3, respectively. Experimental results and analysis validate that the proposed network achieves good performance in both complex backgrounds and bright illumination conditions.https://www.mdpi.com/1996-1073/14/5/1426insulator detectionimage processingconvolution neural networksaerial imageYOLO networkcomplex background |
| spellingShingle | Chuanyang Liu Yiquan Wu Jingjing Liu Jiaming Han MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images Energies insulator detection image processing convolution neural networks aerial image YOLO network complex background |
| title | MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images |
| title_full | MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images |
| title_fullStr | MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images |
| title_full_unstemmed | MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images |
| title_short | MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images |
| title_sort | mti yolo a light weight and real time deep neural network for insulator detection in complex aerial images |
| topic | insulator detection image processing convolution neural networks aerial image YOLO network complex background |
| url | https://www.mdpi.com/1996-1073/14/5/1426 |
| work_keys_str_mv | AT chuanyangliu mtiyoloalightweightandrealtimedeepneuralnetworkforinsulatordetectionincomplexaerialimages AT yiquanwu mtiyoloalightweightandrealtimedeepneuralnetworkforinsulatordetectionincomplexaerialimages AT jingjingliu mtiyoloalightweightandrealtimedeepneuralnetworkforinsulatordetectionincomplexaerialimages AT jiaminghan mtiyoloalightweightandrealtimedeepneuralnetworkforinsulatordetectionincomplexaerialimages |