MCA-YOLOV5-Light: A Faster, Stronger and Lighter Algorithm for Helmet-Wearing Detection

Sun, Chuen-Tsai; Zhang, Shiwen; Qu, Peiqi; Wu, Xingjin; Feng, Pingfa; Tao, Zhanya; Zhang, Jin; Wang, Ying

doi:10.3390/app12199697

Cited by 15 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tai et al [39] introduced a new dynamic anchor box mechanism based on YOLOv5 for safety helmet detection, improving the model's accuracy in handling target changes. Sun et al [40] integrated the MCA module into YOLOv5 to obtain more comprehensive feature map data. By employing strategies such as sparse training and channel pruning, they notably improved safety helmet detection performance.…”

Section: Related Workmentioning

confidence: 99%

GBSG-YOLOv8n: A Model for Enhanced Personal Protective Equipment Detection in Industrial Environments

Shi,

Zhu,

Shen

et al. 2023

Electronics

View full text Add to dashboard Cite

The timely and accurate detection of whether or not workers in an industrial environment are correctly wearing personal protective equipment (PPE) is paramount for worker safety. However, current PPE detection faces multiple inherent challenges, including complex backgrounds, varying target size ranges, and relatively low accuracy. In response to these challenges, this study presents a novel PPE safety detection model based on YOLOv8n, called GBSG-YOLOv8n. First, the global attention mechanism (GAM) is introduced to enhance the feature extraction capability of the backbone network. Second, the path aggregation network (PANet) structure is optimized in the Neck network, strengthening the model’s feature learning ability and achieving multi-scale feature fusion, further improving detection accuracy. Additionally, a new SimC2f structure has been designed to handle image features and more effectively improve detection efficiency. Finally, GhostConv is adopted to optimize the convolution operations, effectively reducing the model’s computational complexity. Experimental results demonstrate that, compared to the original YOLOv8n model, the proposed GBSG-YOLOv8n model in this study achieved a 3% improvement in the mean Average Precision (mAP), with a significant reduction in model complexity. This validates the model’s practicality in complex industrial environments, enabling a more effective detection of workers’ PPE usage and providing reliable protection for achieving worker safety. This study emphasizes the significant potential of computer vision technology in enhancing worker safety and provides a robust reference for future research regarding industrial safety.

show abstract

Section: Related Workmentioning

confidence: 99%

GBSG-YOLOv8n: A Model for Enhanced Personal Protective Equipment Detection in Industrial Environments

Shi,

Zhu,

Shen

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Several studies have proposed helmet detection methods using YOLOv5, a popular deep learning technology [9,10]. Additionally, other researchers [11][12][13][14][15] have made advancements in helmet detection by refning networks based on YOLOv5. Furthermore, CNNs have been employed to detect safety vests [16][17][18], safety belts [19][20][21], and insulators [22][23][24] worn by workers in surveillance videos of power substations.…”

Section: Related Workmentioning

confidence: 99%

FFA-YOLOv7: Improved YOLOv7 Based on Feature Fusion and Attention Mechanism for Wearing Violation Detection in Substation Construction Safety

Chang

Zhang

Zhu

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Ensuring compliance with safety regulations regarding wearing is essential for the safety and security of those working on substation construction sites. However, relying on supervisors to monitor workers in real time on the work site or through remote surveillance videos is both unreasonable and inefficient. A deep learning network approach named FFA-YOLOv7 is presented in this study that utilizes an improved version of YOLOv7 to detect violations of worker wearing in real time during power construction site surveillance. In YOLOv7, the feature pyramid network (FPN) of the neck stage is constructed through continuous upsampling and skip connections for feature fusion, after continuous downsampling of the backbone. However, this process can result in the loss of precise shallow position information. To tackle this issue, we have introduced a novel feature fusion pathway to the FPN architecture, enabling each layer not only to fuse feature maps from the same level during the downsampling course but also to fuse feature maps from shallower levels. This approach combines precise positional information from shallow layers with rich semantic information from deep layers. Additionally, we utilized attention after feature fusion in each layer to optimize the feature map fusion effect and achieve better detection accuracy performance. In order to conduct comparative experiments, we trained six variations of the YOLO model as detectors using a dataset gathered from realistic construction sites. The experimental results indicate that our proposed FFA-YOLOv7 attained a detection precision of 95.92% and a recall rate of 97.13%, demonstrating a high level of accuracy and a low rate of missed detections. These outcomes effectively satisfy the requirements for robust and accurate detection of real-world power construction violations.

show abstract

“…This research developed an edge computing-based level crossing monitoring system that could detect violations by developing object detection and recognition models and optimizing computing performance using the computation offloading method on limited computing devices. In the initial stage, an object detection and recognition model were established using an object detection algorithm, referring to previous research [21], [22]. In the second stage, the results of model formation were applied to devices with limited computing resources using the computation offloading method to accelerate inference time and reduce the computational load [23].…”

Section: Introductionmentioning

confidence: 99%

Penerapan Computation Offloading Pada Sistem Deteksi Pelanggaran Perlintasan Sebidang Berbasis Komputasi Tepi

Rian Putra Pratama,

Suhono Harso Supangkat

2024

Jurnal Nasional Teknik Elektro dan Teknologi Informasi

View full text Add to dashboard Cite

Perlintasan sebidang masih menjadi permasalahan di beberapa kota akibat tingkat pelanggaran yang tinggi. Saat ini, pengawasan di perlintasan sebidang masih dilakukan secara konvensional. Permasalahan di perlintasan sebidang makin kompleks dan solusi konvensional tidak lagi efektif, sehingga diperlukan sistem pengawasan video cerdas sebagai solusi. Penerapan sistem pengawasan video cerdas merupakan tugas yang kompleks dan memerlukan perangkat dengan sumber daya komputasi besar. Penelitian ini bertujuan mengoptimalkan sistem dalam melakukan pemrosesan data secara real-time dengan melakukan komputasi dekat dengan sumber data dan membagi tugas komputasi ke beberapa perangkat tepi (edge device). Sistem pengawasan video cerdas berbasis komputasi tepi (edge computing) dengan metode computation offloading pada perangkat terbatas diusulkan sebagai solusi pada penelitian ini. Penelitian ini terdiri atas dua tahap pengembangan. Tahap pertama mengembangkan model deteksi objek menggunakan dataset perlintasan sebidang di Kota Bandung dan tahap kedua mengembangkan sistem berbasis komputasi tepi dengan menerapkan metode computation offloading pada perangkat komputasi terbatas. Metode komputasi tepi memperluas komputasi awan (cloud computing) ke tepi jaringan untuk melakukan perhitungan dekat dengan sumber data, sedangkan metode computation offloading meningkatkan kinerja komputasi tepi dengan membagi tugas komputasi. Hasil pengujian menunjukkan terjadinya peningkatan kecepatan komputasi sekitar 1,5 kali lebih cepat dengan tingkat akurasi deteksi pelanggaran mencapai 89,4%. Selain itu, terjadi penurunan suhu GPU sebesar 5,50 °C, penggunaan GPU turun 44,05%, penggunaan memori berkurang 301 Mb, dan konsumsi daya menurun 2,28 W. Sistem yang dikembangkan efektif dan efisien dalam mengoptimalkan kinerja sistem deteksi pelanggaran di perlintasan sebidang pada perangkat komputasi terbatas.

show abstract

MCA-YOLOV5-Light: A Faster, Stronger and Lighter Algorithm for Helmet-Wearing Detection

Cited by 15 publications

References 41 publications

GBSG-YOLOv8n: A Model for Enhanced Personal Protective Equipment Detection in Industrial Environments

GBSG-YOLOv8n: A Model for Enhanced Personal Protective Equipment Detection in Industrial Environments

FFA-YOLOv7: Improved YOLOv7 Based on Feature Fusion and Attention Mechanism for Wearing Violation Detection in Substation Construction Safety

Penerapan Computation Offloading Pada Sistem Deteksi Pelanggaran Perlintasan Sebidang Berbasis Komputasi Tepi

Contact Info

Product

Resources

About