Method for detection of unsafe actions in power field based on edge computing architecture

Abstract Due to the high risk factors in the electric power industry, the safety of power system can be improved by using the surveillance system to predict and warn the operators’ nonstandard and unsafe actions in real time. In this paper, aiming at the real-time and accuracy requirements in video...

Full description

Bibliographic Details
Main Authors: Yanfang Yin, Jinjiao Lin, Nongliang Sun, Qigang Zhu, Shuaishuai Zhang, Yanjie Zhang, Ming Liu
Format: Article
Language:English
Published: SpringerOpen 2021-02-01
Series:Journal of Cloud Computing: Advances, Systems and Applications
Subjects:
Online Access:https://doi.org/10.1186/s13677-021-00234-w
_version_ 1818668097659207680
author Yanfang Yin
Jinjiao Lin
Nongliang Sun
Qigang Zhu
Shuaishuai Zhang
Yanjie Zhang
Ming Liu
author_facet Yanfang Yin
Jinjiao Lin
Nongliang Sun
Qigang Zhu
Shuaishuai Zhang
Yanjie Zhang
Ming Liu
author_sort Yanfang Yin
collection DOAJ
description Abstract Due to the high risk factors in the electric power industry, the safety of power system can be improved by using the surveillance system to predict and warn the operators’ nonstandard and unsafe actions in real time. In this paper, aiming at the real-time and accuracy requirements in video intelligent surveillance, a method based on edge computing architecture is proposed to judge unsafe actions of electric power operations in time. In this method, the service of unsafe actions judgment is deployed to the edge cloud, which improves the real-time performance. In order to identify the action being executed, the end-to-end action recognition model proposed in this paper uses the Temporal Convolutional Neural Network (TCN) to extract local temporal features and a Gate Recurrent Unit (GRU) layer to extract global temporal features, which increases the accuracy of action fragment recognition. The result of action recognition is combined with the result of equipment target recognition based on the yolov3 model, and the classification rule is used to determine whether the current action is safe. Experiments show that the proposed method has better real-time performance, and the proposed action cognition is verified on the MSRAction Dataset, which improves the recognition accuracy of action segments. At the same time, the judgment results of unsafe actions also prove the effectiveness of the proposed method.
first_indexed 2024-12-17T06:30:54Z
format Article
id doaj.art-f3cff18fea5444948aae45b90a410ec0
institution Directory Open Access Journal
issn 2192-113X
language English
last_indexed 2024-12-17T06:30:54Z
publishDate 2021-02-01
publisher SpringerOpen
record_format Article
series Journal of Cloud Computing: Advances, Systems and Applications
spelling doaj.art-f3cff18fea5444948aae45b90a410ec02022-12-21T22:00:09ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2021-02-0110111410.1186/s13677-021-00234-wMethod for detection of unsafe actions in power field based on edge computing architectureYanfang Yin0Jinjiao Lin1Nongliang Sun2Qigang Zhu3Shuaishuai Zhang4Yanjie Zhang5Ming Liu6Shandong University of Science and TechnologyShandong University of Finance and EconomicsShandong University of Science and TechnologyShandong University of Science and TechnologyShandong University of Science and TechnologyShandong Electric Power CollegeShandong University of Science and TechnologyAbstract Due to the high risk factors in the electric power industry, the safety of power system can be improved by using the surveillance system to predict and warn the operators’ nonstandard and unsafe actions in real time. In this paper, aiming at the real-time and accuracy requirements in video intelligent surveillance, a method based on edge computing architecture is proposed to judge unsafe actions of electric power operations in time. In this method, the service of unsafe actions judgment is deployed to the edge cloud, which improves the real-time performance. In order to identify the action being executed, the end-to-end action recognition model proposed in this paper uses the Temporal Convolutional Neural Network (TCN) to extract local temporal features and a Gate Recurrent Unit (GRU) layer to extract global temporal features, which increases the accuracy of action fragment recognition. The result of action recognition is combined with the result of equipment target recognition based on the yolov3 model, and the classification rule is used to determine whether the current action is safe. Experiments show that the proposed method has better real-time performance, and the proposed action cognition is verified on the MSRAction Dataset, which improves the recognition accuracy of action segments. At the same time, the judgment results of unsafe actions also prove the effectiveness of the proposed method.https://doi.org/10.1186/s13677-021-00234-wUnsafe action predictionEdge computingThe Temporal Convolutional Neural Network (TCN)Gate Recurrent Unit (GRU)
spellingShingle Yanfang Yin
Jinjiao Lin
Nongliang Sun
Qigang Zhu
Shuaishuai Zhang
Yanjie Zhang
Ming Liu
Method for detection of unsafe actions in power field based on edge computing architecture
Journal of Cloud Computing: Advances, Systems and Applications
Unsafe action prediction
Edge computing
The Temporal Convolutional Neural Network (TCN)
Gate Recurrent Unit (GRU)
title Method for detection of unsafe actions in power field based on edge computing architecture
title_full Method for detection of unsafe actions in power field based on edge computing architecture
title_fullStr Method for detection of unsafe actions in power field based on edge computing architecture
title_full_unstemmed Method for detection of unsafe actions in power field based on edge computing architecture
title_short Method for detection of unsafe actions in power field based on edge computing architecture
title_sort method for detection of unsafe actions in power field based on edge computing architecture
topic Unsafe action prediction
Edge computing
The Temporal Convolutional Neural Network (TCN)
Gate Recurrent Unit (GRU)
url https://doi.org/10.1186/s13677-021-00234-w
work_keys_str_mv AT yanfangyin methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT jinjiaolin methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT nongliangsun methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT qigangzhu methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT shuaishuaizhang methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT yanjiezhang methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture
AT mingliu methodfordetectionofunsafeactionsinpowerfieldbasedonedgecomputingarchitecture