<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Safety production is an important way to ensure the personal safety of workers and the safety of national property. This project focuses on addressing the safety generation problem in the power marketing profession, designing a set of intelligent dynamic warning systems for power marketing operations. MobileNetV1 is used as the backbone feature extraction network of SSD to create a lightweight target detection network, and it is combined with OpenVINO and NCS2 neural computation bars to construct an image analysis and dynamic warning model for power operation based on the SSD MobileNetV1 algorithm. We use the images of power marketing operation sites in a city as a dataset to test and compare the constructed model with other target detection algorithms, analyzing its dynamic warning effect on power operations and exploring the effectiveness of the model’s practical application. The results show that the SSD network model can significantly improve the detection efficiency and accuracy of the dynamic early warning system for electric power operations, and its accuracy is 15.15% and 18.82% higher than that of the Faster⁃RCNN algorithm and the YOLO algorithm, respectively. The early warning system reduced the irregular behavior of electric power marketing operations by 135.71%, demonstrating the effectiveness of the SSD model in detecting and warning electric power targets. This model not only meets practical requirements but also effectively reduces the irregular production behaviors of electric power marketing operations, thereby enhancing the safety coefficient of marketing field operations.</p>
</abstract>

Safety production is an important way to ensure the personal safety of workers and the safety of national property. This project focuses on addressing the safety generation problem in the power marketing profession, designing a set of intelligent dynamic warning systems for power marketing operations. MobileNetV1 is used as the backbone feature extraction network of SSD to create a lightweight target detection network, and it is combined with OpenVINO and NCS2 neural computation bars to construct an image analysis and dynamic warning model for power operation based on the SSD MobileNetV1 algorithm. We use the images of power marketing operation sites in a city as a dataset to test and compare the constructed model with other target detection algorithms, analyzing its dynamic warning effect on power operations and exploring the effectiveness of the model’s practical application. The results show that the SSD network model can significantly improve the detection efficiency and accuracy of the dynamic early warning system for electric power operations, and its accuracy is 15.15% and 18.82% higher than that of the Faster⁃RCNN algorithm and the YOLO algorithm, respectively. The early warning system reduced the irregular behavior of electric power marketing operations by 135.71%, demonstrating the effectiveness of the SSD model in detecting and warning electric power targets. This model not only meets practical requirements but also effectively reduces the irregular production behaviors of electric power marketing operations, thereby enhancing the safety coefficient of marketing field operations.

Research on Image Analysis and Dynamic Early Warning Mechanism of Power Marketing Operation Site Based on SSD Networks

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Safety production is an important way to ensure the personal safety of workers and the safety of national property. This project focuses on addressing the...

Research on Image Analysis and Dynamic Early Warning Mechanism of Power Marketing Operation Site Based on SSD Networks

Online veröffentlicht: 05. Aug. 2024

Seitenbereich: -

Eingereicht: 27. März 2024

Akzeptiert: 25. Juni 2024

DOI: https://doi.org/10.2478/amns-2024-2214

Schlüsselwörter
SSD network, MobileNetV1, Image analysis, Dynamic warning, Power marketing operations

© 2024 Jinteng Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on Image Analysis and Dynamic Early Warning Mechanism of Power Marketing Operation Site Based on SSD Networks

Online veröffentlicht: 05. Aug. 2024

Seitenbereich: -

Eingereicht: 27. März 2024

Akzeptiert: 25. Juni 2024

DOI: https://doi.org/10.2478/amns-2024-2214

SchlüsselwörterSSD network, MobileNetV1, Image analysis, Dynamic warning, Power marketing operations

© 2024 Jinteng Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
SSD network, MobileNetV1, Image analysis, Dynamic warning, Power marketing operations