Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking
Deep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. Thi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/3161551 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550407435452416 |
|---|---|
| author | Wei Jiang Zhimin Guo Huanlong Zhang Liyun Cheng Yangyang Tian |
| author_facet | Wei Jiang Zhimin Guo Huanlong Zhang Liyun Cheng Yangyang Tian |
| author_sort | Wei Jiang |
| collection | DOAJ |
| description | Deep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. This paper presents a target-aware deep feature compression for power intelligent inspection tracking. First, a negative balance loss function is designed to mine channel features suitable for the current inspection scene by shrinking the contribution of pure background negative samples and enhancing the impact of difficult negative samples. Based on this, the deep feature compression model is combined with Siamese tracking framework to achieve real-time and robust tracking. Finally, we evaluate the proposed method on real application scenarios and general data to prove the practicability of the proposed method. |
| format | Article |
| id | doaj-art-369f7cc239f74b42a818e157addbc5db |
| institution | Kabale University |
| issn | 2090-0155 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-369f7cc239f74b42a818e157addbc5db2025-02-03T06:06:47ZengWileyJournal of Electrical and Computer Engineering2090-01552022-01-01202210.1155/2022/3161551Target-Aware Deep Feature Compression for Power Intelligent Inspection TrackingWei Jiang0Zhimin Guo1Huanlong Zhang2Liyun Cheng3Yangyang Tian4State Grid Corporation of ChinaState Grid Henan Electric Power Research InstituteCollege of Electric and Information EngineeringCollege of Electric and Information EngineeringState Grid Henan Electric Power Research InstituteDeep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. This paper presents a target-aware deep feature compression for power intelligent inspection tracking. First, a negative balance loss function is designed to mine channel features suitable for the current inspection scene by shrinking the contribution of pure background negative samples and enhancing the impact of difficult negative samples. Based on this, the deep feature compression model is combined with Siamese tracking framework to achieve real-time and robust tracking. Finally, we evaluate the proposed method on real application scenarios and general data to prove the practicability of the proposed method.http://dx.doi.org/10.1155/2022/3161551 |
| spellingShingle | Wei Jiang Zhimin Guo Huanlong Zhang Liyun Cheng Yangyang Tian Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking Journal of Electrical and Computer Engineering |
| title | Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking |
| title_full | Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking |
| title_fullStr | Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking |
| title_full_unstemmed | Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking |
| title_short | Target-Aware Deep Feature Compression for Power Intelligent Inspection Tracking |
| title_sort | target aware deep feature compression for power intelligent inspection tracking |
| url | http://dx.doi.org/10.1155/2022/3161551 |
| work_keys_str_mv | AT weijiang targetawaredeepfeaturecompressionforpowerintelligentinspectiontracking AT zhiminguo targetawaredeepfeaturecompressionforpowerintelligentinspectiontracking AT huanlongzhang targetawaredeepfeaturecompressionforpowerintelligentinspectiontracking AT liyuncheng targetawaredeepfeaturecompressionforpowerintelligentinspectiontracking AT yangyangtian targetawaredeepfeaturecompressionforpowerintelligentinspectiontracking |