Improved Lightweight YOLOv5 Using Attention Mechanism for Satellite Components Recognition

Li, Cong; Zhao, Gangming; Gu, Dongqing; Wang, Zebin

doi:10.1109/jsen.2022.3222868

Cited by 13 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, since it was applied to fire and smoke detection, further improvements in detection accuracy are required for practical real-life applications. Li et al [10] completed the detection of typical satellite components using YOLOv5 and achieved an mAP of 95.8%, while reducing the model size by 66%. This provided a possibility for practical applications in this domain.…”

Section: A Application Of Yolov5 In Object Detectionmentioning

confidence: 99%

Steel Surface Defect Detection Using Improved Deep Learning Algorithm: ECA-SimSPPF-SIoU-Yolov5

Ren,

Fei,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Steel surface defect detection is an indispensable part of industrial production and processing processes. It helps to reduce production costs, ensure product quality, improve production safety and compliance, and maintain sustainability and competitiveness. To address the low detection accuracy of traditional methods, this paper developed and investigated an improved algorithm based on YOLO for steel surface defect detection: ECA(Efficient Channel Attention) -SimSPPF (Simplified Spatial Pooling -Fast) -SIoU (Scylla Intersection over Union) -Yolov5. First, deformable convolutions were used to replace some conventional convolutions in the model, which expanded the receptive field and improved detection accuracy. Additionally, Efficient Channel Attention was integrated into the model to improve the weight of important information. Then, the SimSPPF was employed in place of the SPP module in the model, reducing computational complexity. Finally, the SIoU loss function was utilized to handle bounding box regression more effectively. The paper conducted different ablation experiments, and the improved ECA-SimSPPF-SIoU-Yolov5 algorithm demonstrated superior detection performance. Using the NEU-DET dataset, the mAP reached 78.8%, which was a 7.1% improvement higher than the original model, while the Recall reached 76.4% and improved by 3.7% compared to the original model. The improved model showed significant improvements in terms of mAP and Recall. Furthermore, the paper conducted multiple comparative experiments, comparing the model with other attention mechanisms and loss functions. The results demonstrated that the improved ECA-SimSPPF-SIoU-Yolov5 algorithm achieved good detection results in terms of mAP and Recall. In the third comparative experiment, the model was compared with YOLOv5 model with different network depths and the latest Yolov8 model, and the improved model also achieved good detection accuracy.

show abstract

Section: A Application Of Yolov5 In Object Detectionmentioning

confidence: 99%

Steel Surface Defect Detection Using Improved Deep Learning Algorithm: ECA-SimSPPF-SIoU-Yolov5

Ren,

Fei,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Tere are many detection methods based on machine learning at present. Te YOLOv5 model launched by Ultralytics in 2020 is implemented in the ecologically mature PyTorch, which has the advantages of small volume, high precision, and fast speed, and the efect of YOLOv5 has been recognized [24][25][26]. In this article, the detection of the obstacle vehicles in the left and right front directions of the ego vehicle is based on YOLOv5, and a monocular-binocular vision switching system is developed using an improved artifcial potential feld.…”

Section: Right Front Direction Based On the Monocular-binocular Visio...mentioning

confidence: 99%

Conflict Judgment and Safety Assessment at Unsignalized Intersections Based on Machine Vision

Wang

Li-ming

Zhu

et al. 2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

This article aims to explore an effective method for reducing vehicle collisions at unsignalized intersections. First, a monocular-binocular vision switching system is built to enable machine vision-based detection of obstacle vehicles in the left and right front directions. Then, the motion state and trajectory of each obstacle vehicle are predicted, and the intersection points of the trajectories of the obstacle vehicle and the ego vehicle are calculated. On this basis, a cross-conflict judgment model based on trajectories and collision times and a safety assessment model based on safety distance are established. Finally, the conflict judgment and safety assessment for the obstacle vehicles are simulated. The results of the simulation demonstrate that the monocular-binocular vision switching system proposed in this article can achieve a detection accuracy of 95%, a ranging accuracy of 96%, and a cross-conflict detection accuracy of 97%, while ensuring a maximum detection area, which can meet the requirements of traffic safety assurance at unsignalized intersections.

show abstract

“…Li et al [9] explained a framework for a computationally constrained satellite components recognition model based on YOLOv5 (YSCRM). The difficult multimodal component identification problem is addressed using feature fusion layers and SKNets (selective kernel networks) ,which enhance the model's feature representation and selection capabilities and dramatically increase recognition accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Onboard Processing of Drone Imagery for Military Vehicles Classification Using Enhanced YOLOv5

Raj,

Sahithi

et al. 2023

JAIT

View full text Add to dashboard Cite

Recently, drones are used in all fields. The video captured by this drone is sent to the terminal for analysis. In terms of speed, performance, and latency, it would be an advantage if the analysis of the image or video is done onboard, the drone, and the result is sent to terminal, this is called onboard processing. For faster recognition speed and higher frame rate, YOLOv5 is used for image detection along with EfficientNet-b0 for classification and de-blurring with DeblurGan v2. A custom dataset of 6999 military vehicle images is created and annotated. This model is loaded in Raspberrypi4 as it is used as a platform to implement real-time image processing applications since their framework can leverage spatial and temporal parallelism. Integrate the Raspberry Pi board into the drone. The classified images are received in a telegram at the terminal. The accuracy of the model is 88%.

show abstract

Improved Lightweight YOLOv5 Using Attention Mechanism for Satellite Components Recognition

Cited by 13 publications

References 32 publications

Steel Surface Defect Detection Using Improved Deep Learning Algorithm: ECA-SimSPPF-SIoU-Yolov5

Steel Surface Defect Detection Using Improved Deep Learning Algorithm: ECA-SimSPPF-SIoU-Yolov5

Conflict Judgment and Safety Assessment at Unsignalized Intersections Based on Machine Vision

Onboard Processing of Drone Imagery for Military Vehicles Classification Using Enhanced YOLOv5

Contact Info

Product

Resources

About