A Violation Behaviors Detection Method for Substation Operators based on YOLOv5 And Pose Estimation

Wang, Jing; Zhou, Hualiang; Sun, Han; Su, Zhantao; Li, Yongming

doi:10.1109/ciycee55749.2022.9958961

Cited by 5 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, those methods only focus on the target features of safety helmets and ignore the human pose features, which can provide position information about helmets. Inspired by [42,43], we designed High-Resolution YOLO (HR-YOLO) combined with HRNet and YOLOv5 to take multi-branch information from helmet object detection and human pose estimation, which improves recognition accuracy in the cases of target occlusion, insufficient light, complex backgrounds and other problems.…”

Section: Helmet Detectionmentioning

confidence: 99%

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Lian,

Li,

Dong

et al. 2024

Electronics

View full text Add to dashboard Cite

Automatic detection of safety helmet wearing is significant in ensuring safe production. However, the accuracy of safety helmet detection can be challenged by various factors, such as complex environments, poor lighting conditions and small-sized targets. This paper presents a novel and efficient deep learning framework named High-Resolution You Only Look Once (HR-YOLO) for safety helmet wearing detection. The proposed framework synthesizes safety helmet wearing information from the features of helmet objects and human pose. HR-YOLO can use features from two branches to make the bounding box of suppression predictions more accurate for small targets. Then, to further improve the iterative efficiency and accuracy of the model, we design an optimized residual network structure by using Optimized Powered Stochastic Gradient Descent (OP-SGD). Moreover, a Laplace-Aware Attention Model (LAAM) is designed to make the YOLOv5 decoder pay more attention to the feature information from human pose and suppress interference from irrelevant features, which enhances network representation. Finally, non-maximum suppression voting (PA-NMS voting) is proposed to improve detection accuracy for occluded targets, using pose information to constrain the confidence of bounding boxes and select optimal bounding boxes through a modified voting process. Experimental results demonstrate that the presented safety helmet detection network outperforms other approaches and has practical value in application scenarios. Compared with the other algorithms, the proposed algorithm improves the precision, recall and mAP by 7.27%, 5.46% and 7.3%, on average, respectively.

show abstract

Section: Helmet Detectionmentioning

confidence: 99%

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Lian,

Li,

Dong

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…where 1 j d and 2 j d represent two consecutive pixel points 1 j and 2 j of a person respectively; ( ) p u is the value of the line between consecutive pixel points, as shown in (3), where u is (0,1) . ( ) (1 )…”

Section: Key Point Detection Network Based On Openposementioning

confidence: 99%

“…Power accidents can not only cause personal injury, but also affect the stable operation of the power system [1,2]. In order to ensure the life safety of power operators, the electric power industry has formulated comprehensive safety work procedures, and trained operators before they take up their posts to standardize their behavior and operation to improve their safety quality [3]. Through investigation and research, it is found that the main reasons for the occurrence of power accidents are the weak safety awareness of the operators, illegal operations and the lack of management responsibility of the on-site supervisors.…”

Section: Introductionmentioning

confidence: 99%

Power operator behavior recognition method based on deep learning

Liu,

Qin,

Yang

et al. 2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

“…Electricity is a crucial industry for ensuring national development and daily life. The power industry has experienced significant growth, resulting in widespread coverage of power systems [1]. The State Grid Corporation of China (State Grid) has a vast transmission range with numerous power work sites.…”

Section: Introductionmentioning

confidence: 99%

Hardhat-YOLO: A YOLOv5-based Lightweight Hardhat-Wearing Detection Algorithm in Substation Sites

Luo,

Yassin,

Shariff

et al. 2024

ijacsa

View full text Add to dashboard Cite

Accidents at substation sites have occurred frequently in recent years due to workers violating power safety regulations by not wearing hardhats. Therefore, it is necessary to provide real-time warnings when detecting workers without hardhats. Nevertheless, the deployment of deep learning-based algorithms necessitates the utilization of a multitude of parameters and computations, which consequently engenders an augmented expenditure on hardware. Therefore, using a lightweight backbone can address this issue well. This paper explored methods, such as deep learning, power Internet of Things (PIoT), and edge computing and proposed a lightweight and effective method called hardhat-YOLO for hardhat-wearing detection. First, the MobileNetv3-small backbone replaced the backbone of You Only Look Once (YOLO) v5s to reduce parameters and increase detection speed. In addition, the Convolutional Block Attention Module (CBAM) was effectively integrated into the network to improve detection precision. Finally, the hardhat-YOLO model, trained with a customized dataset, was transmitted to edge computing terminals in substations through PIoT for hardhat-wearing detection. Compared to the YOLOv5s model, the Parameters and Giga Floating Point Operations (GFLOPs) of the proposed model decreased by about 35.5% and 54.4%, respectively, and Frame per Second (FPS) increased by 17.3% approximately. The experimental results indicated that the hardhat-YOLO model achieved a Mean Average Precision of 83.3% at 50% intersection over union (mAP50), correctly and effectively conducting hardhat-wearing detection tasks.

show abstract

A Violation Behaviors Detection Method for Substation Operators based on YOLOv5 And Pose Estimation

Cited by 5 publications

References 7 publications

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Power operator behavior recognition method based on deep learning

Hardhat-YOLO: A YOLOv5-based Lightweight Hardhat-Wearing Detection Algorithm in Substation Sites

Contact Info

Product

Resources

About