Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images
This paper is concerned with the problem of short circuit detection in infrared image for metal electrorefining with an improved Faster Region-based Convolutional Neural Network (Faster R-CNN). To address the problem of insufficient label data, a framework for automatically generating labeled infrar...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-11-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2021.751037/full |
| _version_ | 1818402131206471680 |
|---|---|
| author | Xin Li Yonggang Li Renchao Wu Can Zhou Hongqiu Zhu |
| author_facet | Xin Li Yonggang Li Renchao Wu Can Zhou Hongqiu Zhu |
| author_sort | Xin Li |
| collection | DOAJ |
| description | This paper is concerned with the problem of short circuit detection in infrared image for metal electrorefining with an improved Faster Region-based Convolutional Neural Network (Faster R-CNN). To address the problem of insufficient label data, a framework for automatically generating labeled infrared images is proposed. After discussing factors that affect sample diversity, background, object shape, and gray scale distribution are established as three key variables for synthesis. Raw infrared images without fault are used as backgrounds. By simulating the other two key variables on the background, different classes of objects are synthesized. To improve the detection rate of small scale targets, an attention module is introduced in the network to fuse the semantic segment results of U-Net and the synthetic dataset. In this way, the Faster R-CNN can obtain rich representation ability about small scale object on the infrared images. Strategies of parameter tuning and transfer learning are also applied to improve the detection precision. The detection system trains on only synthetic dataset and tests on actual images. Extensive experiments on different infrared datasets demonstrate the effectiveness of the synthetic methods. The synthetically trained network obtains a mAP of 0.826, and the recall rate of small latent short circuit is superior to that of Faster R-CNN and U-Net, effectively avoiding short-circuit missed detection. |
| first_indexed | 2024-12-14T08:03:29Z |
| format | Article |
| id | doaj.art-95510d06f88a4b78b72ff842179557a0 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-12-14T08:03:29Z |
| publishDate | 2021-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-95510d06f88a4b78b72ff842179557a02022-12-21T23:10:18ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182021-11-011510.3389/fnbot.2021.751037751037Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared ImagesXin LiYonggang LiRenchao WuCan ZhouHongqiu ZhuThis paper is concerned with the problem of short circuit detection in infrared image for metal electrorefining with an improved Faster Region-based Convolutional Neural Network (Faster R-CNN). To address the problem of insufficient label data, a framework for automatically generating labeled infrared images is proposed. After discussing factors that affect sample diversity, background, object shape, and gray scale distribution are established as three key variables for synthesis. Raw infrared images without fault are used as backgrounds. By simulating the other two key variables on the background, different classes of objects are synthesized. To improve the detection rate of small scale targets, an attention module is introduced in the network to fuse the semantic segment results of U-Net and the synthetic dataset. In this way, the Faster R-CNN can obtain rich representation ability about small scale object on the infrared images. Strategies of parameter tuning and transfer learning are also applied to improve the detection precision. The detection system trains on only synthetic dataset and tests on actual images. Extensive experiments on different infrared datasets demonstrate the effectiveness of the synthetic methods. The synthetically trained network obtains a mAP of 0.826, and the recall rate of small latent short circuit is superior to that of Faster R-CNN and U-Net, effectively avoiding short-circuit missed detection.https://www.frontiersin.org/articles/10.3389/fnbot.2021.751037/fullsample synthesisshort circuit detectioninfrared imagemetal electrorefiningattention-based Faster R-CNN |
| spellingShingle | Xin Li Yonggang Li Renchao Wu Can Zhou Hongqiu Zhu Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images Frontiers in Neurorobotics sample synthesis short circuit detection infrared image metal electrorefining attention-based Faster R-CNN |
| title | Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images |
| title_full | Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images |
| title_fullStr | Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images |
| title_full_unstemmed | Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images |
| title_short | Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images |
| title_sort | short circuit recognition for metal electrorefining using an improved faster r cnn with synthetic infrared images |
| topic | sample synthesis short circuit detection infrared image metal electrorefining attention-based Faster R-CNN |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2021.751037/full |
| work_keys_str_mv | AT xinli shortcircuitrecognitionformetalelectrorefiningusinganimprovedfasterrcnnwithsyntheticinfraredimages AT yonggangli shortcircuitrecognitionformetalelectrorefiningusinganimprovedfasterrcnnwithsyntheticinfraredimages AT renchaowu shortcircuitrecognitionformetalelectrorefiningusinganimprovedfasterrcnnwithsyntheticinfraredimages AT canzhou shortcircuitrecognitionformetalelectrorefiningusinganimprovedfasterrcnnwithsyntheticinfraredimages AT hongqiuzhu shortcircuitrecognitionformetalelectrorefiningusinganimprovedfasterrcnnwithsyntheticinfraredimages |