在人体姿态检测任务中,现有的深度学习网络存在检测精度不足、网络参数复杂和计算成本高等问题,严重限制了它们的应用。为了解决这些问题,提出一种轻量且高精度的姿态检测改进网络HG-YOLO(High-precision and Ghost YOLO)。针对检测精...在人体姿态检测任务中,现有的深度学习网络存在检测精度不足、网络参数复杂和计算成本高等问题,严重限制了它们的应用。为了解决这些问题,提出一种轻量且高精度的姿态检测改进网络HG-YOLO(High-precision and Ghost YOLO)。针对检测精度不足的问题,在HG-YOLO的主干网络,融合基于Transformer的检测网络RT-DETR(Real-Time DEtection TRansformer),并将大型可分离核注意力(LSKA)模块嵌入主干网络中,以在不增加内存占用和计算复杂性的基础上,提高网络应对复杂场景的特征提取能力,从而提高人体姿态的检测精度。针对网络参数复杂和计算成本高的问题,引入轻量化的Ghost卷积模块替换部分标准卷积,此外,在HG-YOLO的检测头部分,设计一种共享卷积检测头,以通过参数和权重共享机制减少卷积计算,从而降低网络的参数量和计算复杂度。在COCO(Common Objects in COntext)2017-Keypoints数据集和CrowdPose数据集上的实验结果表明,与基准的YOLOv8-Pose网络相比,HG-YOLO的参数量减少了32%,浮点运算量减少了18%;在规模为小型(s)时,在COCO 2017-Keypoints数据集上,AP50(Average Precision at OKS(Object Keypoint Similarity)of 0.50)提升了0.8个百分点,在CrowdPose数据集上,AP提升了2.9个百分点。可见,HG-YOLO不仅轻量,而且检测精度高,是人体姿态检测领域的优秀网络模型。展开更多
With the development of computer vision technology,deep learning-based pose estimation and target detection have been widely used in the fields of human behavior analysis and intelligent security.However,owing to the ...With the development of computer vision technology,deep learning-based pose estimation and target detection have been widely used in the fields of human behavior analysis and intelligent security.However,owing to the complexity of animal poses and the diversity of species,the existing pose estimation methods still face many challenges when applied to animal targets.To solve this problem,an improved YOLO-Pose model is proposed to improve the accuracy and efficiency of animal pose estimation.On the basis of the original YOLO-Pose model,a separable kernel attention mechanism is introduced and improved to make it conform to the animal target,and combined with the spatial pyramid pool of YOLO-Pose,the multiscale feature fusion capability of the model is improved.The experimental results show that the improved YOLO-Pose model achieves excellent performance on both the public animal pose dataset and the AP-10K dataset,significantly improving the ability of target detection and pose estimation.展开更多
为提高自然环境中玉米害虫识别的准确性,开发一种基于优化YOLOv8的深度学习模型YOLOv8-LAP。该模型将大型可分离卷积核注意力(LSKA)机制引入特征融合模块空间快速金字塔池化(SPPF),增强多尺度特征提取能力,提升检测性能。针对玉米害虫...为提高自然环境中玉米害虫识别的准确性,开发一种基于优化YOLOv8的深度学习模型YOLOv8-LAP。该模型将大型可分离卷积核注意力(LSKA)机制引入特征融合模块空间快速金字塔池化(SPPF),增强多尺度特征提取能力,提升检测性能。针对玉米害虫图像检测中小目标难以捕捉、背景复杂和光照变化等挑战,在主干网络中加入AFGC(Attention for Fine-Grained Categorization)层,以进一步增强图像特征提取的效果,提升模型的泛化能力和鲁棒性。为保证实时检测和模型轻量化,引入可编程梯度信息(PGI)技术,通过辅助监督优化训练过程,减少参数并加速推理。在9种常见玉米害虫的检测中,YOLOv8-LAP模型的平均精度均值(mAP0.5)达到了95.7%,相较于原始YOLOv8模型提高了4.9个百分点。此外,为验证YOLOv8-LAP模型的效果,开发一款基于PySide6的应用程序,该应用拥有用户友好的图形用户界面(GUI),具有实时图像处理和视频分析功能,并支持静态图像、动态视频和摄像头实时目标检测。可见,YOLOv8-LAP模型在降低漏检率和误检率方面表现突出,目标定位更精准,适用于自然环境下的玉米害虫识别,并为精准施药提供技术支持。展开更多
基金funded by the second batch of Tianchi Talents(Leading Tal-ents)project in Xinjiang Uygur Autonomous Region.Project leader:Lei Liu from School of Computer Science and Technology,Xinjiang University.
文摘With the development of computer vision technology,deep learning-based pose estimation and target detection have been widely used in the fields of human behavior analysis and intelligent security.However,owing to the complexity of animal poses and the diversity of species,the existing pose estimation methods still face many challenges when applied to animal targets.To solve this problem,an improved YOLO-Pose model is proposed to improve the accuracy and efficiency of animal pose estimation.On the basis of the original YOLO-Pose model,a separable kernel attention mechanism is introduced and improved to make it conform to the animal target,and combined with the spatial pyramid pool of YOLO-Pose,the multiscale feature fusion capability of the model is improved.The experimental results show that the improved YOLO-Pose model achieves excellent performance on both the public animal pose dataset and the AP-10K dataset,significantly improving the ability of target detection and pose estimation.
文摘为提高自然环境中玉米害虫识别的准确性,开发一种基于优化YOLOv8的深度学习模型YOLOv8-LAP。该模型将大型可分离卷积核注意力(LSKA)机制引入特征融合模块空间快速金字塔池化(SPPF),增强多尺度特征提取能力,提升检测性能。针对玉米害虫图像检测中小目标难以捕捉、背景复杂和光照变化等挑战,在主干网络中加入AFGC(Attention for Fine-Grained Categorization)层,以进一步增强图像特征提取的效果,提升模型的泛化能力和鲁棒性。为保证实时检测和模型轻量化,引入可编程梯度信息(PGI)技术,通过辅助监督优化训练过程,减少参数并加速推理。在9种常见玉米害虫的检测中,YOLOv8-LAP模型的平均精度均值(mAP0.5)达到了95.7%,相较于原始YOLOv8模型提高了4.9个百分点。此外,为验证YOLOv8-LAP模型的效果,开发一款基于PySide6的应用程序,该应用拥有用户友好的图形用户界面(GUI),具有实时图像处理和视频分析功能,并支持静态图像、动态视频和摄像头实时目标检测。可见,YOLOv8-LAP模型在降低漏检率和误检率方面表现突出,目标定位更精准,适用于自然环境下的玉米害虫识别,并为精准施药提供技术支持。
