Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology
This paper builds a power operation target detection model based on the YOLOv4 algorithm in intelligent image recognition, and optimizes the YOLOv4 algorithm by combining with the loss function to improve the accuracy of power target operation detection. The kmeans++ algorithm was used to cluster th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-01-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns-2024-0364 |
| _version_ | 1797279101817454592 |
|---|---|
| author | Feng Xinwen Chen Shikuan Zhou Mingzhe Yu Qiheng Ma Hongbo Liu Jie Sun Yingxue |
| author_facet | Feng Xinwen Chen Shikuan Zhou Mingzhe Yu Qiheng Ma Hongbo Liu Jie Sun Yingxue |
| author_sort | Feng Xinwen |
| collection | DOAJ |
| description | This paper builds a power operation target detection model based on the YOLOv4 algorithm in intelligent image recognition, and optimizes the YOLOv4 algorithm by combining with the loss function to improve the accuracy of power target operation detection. The kmeans++ algorithm was used to cluster the electric power operation behaviors to obtain a more accurate electric power operation behavior dataset. Three sets of tests were conducted after the model was constructed, targeting the behavioral set of electric power workers in a certain place and the behavior in VOC format, followed by the multi-target tracking effect test. The analysis based on the obtained data showed that the helmet placement detection confidence, fatigue detection confidence, smoking detection confidence, and fall detection confidence reached 0.97, 0.93, 0.89, and 0.93, respectively. The transmission speed got 53.58 fps, and the recall and precision of the multi-target tracking were also above 93%. The YOLOv4 detection model based on keans++ clustering algorithm can effectively detect and identify the variable power operation behavior images. |
| first_indexed | 2024-03-07T16:20:26Z |
| format | Article |
| id | doaj.art-1878f61b4d49428b9806ef3e70c727e0 |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-03-07T16:20:26Z |
| publishDate | 2024-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-1878f61b4d49428b9806ef3e70c727e02024-03-04T07:30:40ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562024-01-019110.2478/amns-2024-0364Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key TechnologyFeng Xinwen0Chen Shikuan1Zhou Mingzhe2Yu Qiheng3Ma Hongbo4Liu Jie5Sun Yingxue61STATE GRID EAST INNER MONGOLIA ELECTRIC POWER SUPPLY COMPANY LTD., Hohhot, Inner Mongolia, 010010, China.1STATE GRID EAST INNER MONGOLIA ELECTRIC POWER SUPPLY COMPANY LTD., Hohhot, Inner Mongolia, 010010, China.1STATE GRID EAST INNER MONGOLIA ELECTRIC POWER SUPPLY COMPANY LTD., Hohhot, Inner Mongolia, 010010, China.2STATE GRID HULUNBEIR POWER SUPPLY COMPANY, Hulunbeir, Inner Mongolia, 021000, China.3State Grid Information and Communication Industry Group Co., Ltd., Beijing Branch, Beijing, 100052, China.3State Grid Information and Communication Industry Group Co., Ltd., Beijing Branch, Beijing, 100052, China.3State Grid Information and Communication Industry Group Co., Ltd., Beijing Branch, Beijing, 100052, China.This paper builds a power operation target detection model based on the YOLOv4 algorithm in intelligent image recognition, and optimizes the YOLOv4 algorithm by combining with the loss function to improve the accuracy of power target operation detection. The kmeans++ algorithm was used to cluster the electric power operation behaviors to obtain a more accurate electric power operation behavior dataset. Three sets of tests were conducted after the model was constructed, targeting the behavioral set of electric power workers in a certain place and the behavior in VOC format, followed by the multi-target tracking effect test. The analysis based on the obtained data showed that the helmet placement detection confidence, fatigue detection confidence, smoking detection confidence, and fall detection confidence reached 0.97, 0.93, 0.89, and 0.93, respectively. The transmission speed got 53.58 fps, and the recall and precision of the multi-target tracking were also above 93%. The YOLOv4 detection model based on keans++ clustering algorithm can effectively detect and identify the variable power operation behavior images.https://doi.org/10.2478/amns-2024-0364yolov4kmeans++loss functionpower operationbehavior recognition62n01 |
| spellingShingle | Feng Xinwen Chen Shikuan Zhou Mingzhe Yu Qiheng Ma Hongbo Liu Jie Sun Yingxue Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology Applied Mathematics and Nonlinear Sciences yolov4 kmeans++ loss function power operation behavior recognition 62n01 |
| title | Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology |
| title_full | Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology |
| title_fullStr | Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology |
| title_full_unstemmed | Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology |
| title_short | Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology |
| title_sort | research on electricity operation behaviour recognition strategy combined with intelligent image recognition and its key technology |
| topic | yolov4 kmeans++ loss function power operation behavior recognition 62n01 |
| url | https://doi.org/10.2478/amns-2024-0364 |
| work_keys_str_mv | AT fengxinwen researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT chenshikuan researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT zhoumingzhe researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT yuqiheng researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT mahongbo researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT liujie researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology AT sunyingxue researchonelectricityoperationbehaviourrecognitionstrategycombinedwithintelligentimagerecognitionanditskeytechnology |