Real-time detection of formation head vehicles based on improved YOLOv5s network

Ren, Zhigang; Ren, Guoyu; Wu, Dinhai

doi:10.1109/iccgiv57403.2022.00009

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second module involves incorporating anchor frame calculations into the training process. During training, the predicted frame is output based on preset anchor frames, compared with the actual frame to obtain the offset between them, and then updated in reverse to adaptively determine the optimal anchor box values within the training set [31]. Selfadaptive image scaling automatically calculates the ll ratio for images of varying sizes encountered in real projects, thereby reducing the computational load on the model.…”

Section: Methodsmentioning

confidence: 99%

Detection of Safety Helmet and Mask Wearing Using Improved YOLOv5

Li,

Lv,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

With the advancement of society, ensuring the safety of personnel involved in municipal construction projects, particularly in the context of pandemic control measures, has become a matter of utmost importance. Municipal engineering projects, distinct from other types of engineering endeavors, often unfold within urban environments, are characterized by extended durations, encompass a range of outdoor activities, and are susceptible to the influence of factors such as concurrent operations, traffic, climate, and environmental conditions. Consequently, the approach to safety management in municipal engineering necessitates unique considerations. This paper introduces a method that combines deep learning and target detection technology to propose a lightweight artificial intelligence (AI) detection method capable of simultaneously identifying mask-wearing and safety helmet-wearing individuals. The method primarily incorporates the ShuffleNetv2 feature extraction mechanism within the framework of the YOLOv5s network to reduce computational overhead. Additionally, it employs the ECA attention mechanism and optimized loss functions to generate feature maps with more comprehensive information, thereby enhancing the precision of target detection. Experimental results indicate that this algorithm improves the mean Average Precision (mAP) value by 4.3%. Furthermore, it reduces parameter and computational loads by 54.8% and 53.8%, respectively, effectively striking a balance between lightweight operation and precision. This study serves as a valuable reference for research pertaining to lightweight target detection in the realm of municipal construction safety measures.

show abstract

Section: Methodsmentioning

confidence: 99%

Detection of Safety Helmet and Mask Wearing Using Improved YOLOv5

Li,

Lv,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These images are then stitched together to create new training data. This process significantly enhances sample diversity and reduces During training, the predicted frame is output based on preset anchor frames, compared with the actual frame to obtain the offset between them, and then updated in reverse to adaptively determine the optimal anchor box values within the training set 32 . Self-adaptive image scaling automatically calculates the fill ratio for images of varying sizes encountered in real projects, thereby reducing the computational load on the model.…”

Section: Methodsmentioning

confidence: 99%

Detection of safety helmet and mask wearing using improved YOLOv5s

Li,

Lv,

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

With the advancement of society, ensuring the safety of personnel involved in municipal construction projects, particularly in the context of pandemic control measures, has become a matter of utmost importance. This paper introduces a security measure for municipal engineering, combining deep learning with object detection technology. It proposes a lightweight artificial intelligence (AI) detection method capable of simultaneously identifying individuals wearing masks and safety helmets. The method primarily incorporates the ShuffleNetv2 feature extraction mechanism within the framework of the YOLOv5s network to reduce computational overhead. Additionally, it employs the ECA attention mechanism and optimized loss functions to generate feature maps with more comprehensive information, thereby enhancing the precision of target detection. Experimental results indicate that this algorithm improves the mean average precision (mAP) value by 4.3%. Furthermore, it reduces parameter and computational loads by 54.8% and 53.8%, respectively, effectively striking a balance between lightweight operation and precision. This study serves as a valuable reference for research pertaining to lightweight target detection in the realm of municipal construction safety measures.

show abstract

Real-time detection of formation head vehicles based on improved YOLOv5s network

Cited by 2 publications

References 8 publications

Detection of Safety Helmet and Mask Wearing Using Improved YOLOv5

Detection of Safety Helmet and Mask Wearing Using Improved YOLOv5

Detection of safety helmet and mask wearing using improved YOLOv5s

Contact Info

Product

Resources

About