[目的/意义]在农业生产的后期,对干制黄花菜等级进行准确分类至关重要。针对现有目标检测模型在干制黄花菜分级任务中精度不足及参数过多的问题,提出一种轻量级的YOLOv10-AD网络模型。[方法]该模型设计了全新的骨干网络AKVanillaNet,针...[目的/意义]在农业生产的后期,对干制黄花菜等级进行准确分类至关重要。针对现有目标检测模型在干制黄花菜分级任务中精度不足及参数过多的问题,提出一种轻量级的YOLOv10-AD网络模型。[方法]该模型设计了全新的骨干网络AKVanillaNet,针对干制黄花菜的特殊形状特征进行了优化,显著提升了检测精度,同时降低了模型的参数和计算成本。此外,还将DysnakeConv模块嵌入C2f结构中,进一步增强了对干制黄花菜特征的提取能力,并通过采用Powerful-IOU(PIOU)损失函数,更好地拟合数据,提升模型性能。[结果和讨论]在干制黄花菜等级分类的数据集上的测试结果表明,YOLOv10-AD模型的平均准确率mAP(Mean Average Precision)达到了85.7%,其参数量、计算量和模型大小分别为2.45 M、6.2 GFLOPs和5.0 M,帧率FPS(Frames Per Second)为156。与基准模型相比,YOLOv10-AD不仅将mAP提升了5.7%,FPS提升了25.8%,同时还将参数量、计算量及模型大小分别降低9.3%、24.4%和9.1%,不仅提升了检测精度,还降低了模型的部署难度。[结论]提出的YOLOv10-AD网络模型能够在不同光照条件下对干制黄花菜进行精准分类,且具有较好的实时性,为干制黄花菜等级的智能分类提供了有效的技术参考。展开更多
In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural N...In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural Network),YOLO(You Only Look Once),and their variants have demonstrated superiority in quickly detecting objects from images and videos,creating new opportunities to enhance automatic and efficient fire detection.The YOLO model,especially newer versions like YOLOv10,stands out for its fast processing capability,making it suitable for low-latency applications.However,when applied to real-world datasets,the accuracy of fire prediction is still not high.This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation.The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories,freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent(SGD)with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection.Experimental results demonstrate the effectiveness of the proposed fire prediction approach,where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano,medium,and balanced.Additionally,the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline,YOLOv8 and Faster R-CNN based on two criteria:accuracy and prediction time.展开更多
密集人群检测是计算机视觉领域的重要任务,在监控、防踩踏、公共安全、交通监控等应用中具有广泛的应用价值。尽管基于深度学习的人群检测方法取得了显著进展,但在处理密集人群、小目标等复杂场景时存在不足,在涉及不同尺度的目标时无...密集人群检测是计算机视觉领域的重要任务,在监控、防踩踏、公共安全、交通监控等应用中具有广泛的应用价值。尽管基于深度学习的人群检测方法取得了显著进展,但在处理密集人群、小目标等复杂场景时存在不足,在涉及不同尺度的目标时无法准确地对其进行识别。本文提出了一种改进的YOLOv5密集人群检测算法,采用多尺度检测和图像分割技术提升算法在复杂场景下的检测能力。实验数据表明改进后的算法在密集多尺度场景下的效果优于传统的YOLOv5和YOLOv10,改进后的算法为密集人群检测任务提供了更全面有效的解决方案,有望在实际应用中更好地满足公共安全领域、交通领域等对密集人群检测的需求,对于预防踩踏等安全事故也具有重要意义。Dense crowd detection is an important task in the field of computer vision and has extensive application value in applications such as monitoring, anti-stampede, public safety, and traffic monitoring. Although crowd detection methods based on deep learning have made remarkable progress, there are still deficiencies when dealing with complex scenes such as dense crowds and small targets, and they cannot accurately identify targets of different scales. This paper proposes a dense crowd detection algorithm based on improved YOLOv5, which uses multi-scale detection and image segmentation technology to improve the detection ability of the algorithm in complex scenes. Experimental data shows that the improved algorithm is better than the traditional YOLOv5 and YOLOv10 in dense multi-scale scenes. The improved algorithm provides a more comprehensive and effective solution for dense crowd detection tasks, and is expected to better meet the needs of dense crowd detection in the fields of public safety and transportation in practical applications, and is also of great significance for preventing safety accidents such as stampedes.展开更多
文摘[目的/意义]在农业生产的后期,对干制黄花菜等级进行准确分类至关重要。针对现有目标检测模型在干制黄花菜分级任务中精度不足及参数过多的问题,提出一种轻量级的YOLOv10-AD网络模型。[方法]该模型设计了全新的骨干网络AKVanillaNet,针对干制黄花菜的特殊形状特征进行了优化,显著提升了检测精度,同时降低了模型的参数和计算成本。此外,还将DysnakeConv模块嵌入C2f结构中,进一步增强了对干制黄花菜特征的提取能力,并通过采用Powerful-IOU(PIOU)损失函数,更好地拟合数据,提升模型性能。[结果和讨论]在干制黄花菜等级分类的数据集上的测试结果表明,YOLOv10-AD模型的平均准确率mAP(Mean Average Precision)达到了85.7%,其参数量、计算量和模型大小分别为2.45 M、6.2 GFLOPs和5.0 M,帧率FPS(Frames Per Second)为156。与基准模型相比,YOLOv10-AD不仅将mAP提升了5.7%,FPS提升了25.8%,同时还将参数量、计算量及模型大小分别降低9.3%、24.4%和9.1%,不仅提升了检测精度,还降低了模型的部署难度。[结论]提出的YOLOv10-AD网络模型能够在不同光照条件下对干制黄花菜进行精准分类,且具有较好的实时性,为干制黄花菜等级的智能分类提供了有效的技术参考。
文摘In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural Network),YOLO(You Only Look Once),and their variants have demonstrated superiority in quickly detecting objects from images and videos,creating new opportunities to enhance automatic and efficient fire detection.The YOLO model,especially newer versions like YOLOv10,stands out for its fast processing capability,making it suitable for low-latency applications.However,when applied to real-world datasets,the accuracy of fire prediction is still not high.This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation.The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories,freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent(SGD)with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection.Experimental results demonstrate the effectiveness of the proposed fire prediction approach,where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano,medium,and balanced.Additionally,the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline,YOLOv8 and Faster R-CNN based on two criteria:accuracy and prediction time.
文摘密集人群检测是计算机视觉领域的重要任务,在监控、防踩踏、公共安全、交通监控等应用中具有广泛的应用价值。尽管基于深度学习的人群检测方法取得了显著进展,但在处理密集人群、小目标等复杂场景时存在不足,在涉及不同尺度的目标时无法准确地对其进行识别。本文提出了一种改进的YOLOv5密集人群检测算法,采用多尺度检测和图像分割技术提升算法在复杂场景下的检测能力。实验数据表明改进后的算法在密集多尺度场景下的效果优于传统的YOLOv5和YOLOv10,改进后的算法为密集人群检测任务提供了更全面有效的解决方案,有望在实际应用中更好地满足公共安全领域、交通领域等对密集人群检测的需求,对于预防踩踏等安全事故也具有重要意义。Dense crowd detection is an important task in the field of computer vision and has extensive application value in applications such as monitoring, anti-stampede, public safety, and traffic monitoring. Although crowd detection methods based on deep learning have made remarkable progress, there are still deficiencies when dealing with complex scenes such as dense crowds and small targets, and they cannot accurately identify targets of different scales. This paper proposes a dense crowd detection algorithm based on improved YOLOv5, which uses multi-scale detection and image segmentation technology to improve the detection ability of the algorithm in complex scenes. Experimental data shows that the improved algorithm is better than the traditional YOLOv5 and YOLOv10 in dense multi-scale scenes. The improved algorithm provides a more comprehensive and effective solution for dense crowd detection tasks, and is expected to better meet the needs of dense crowd detection in the fields of public safety and transportation in practical applications, and is also of great significance for preventing safety accidents such as stampedes.
