针对当前桥梁裂缝图像检测精度较低,算法规模较大不便于部署在资源受限的边缘设备等问题,提出一种改进YOLOv11n(you only look once version 11 nano)的轻量级桥梁裂缝图像检测算法,通过融合ShuffleNetV2模块与跨尺度融合模块(cross-sca...针对当前桥梁裂缝图像检测精度较低,算法规模较大不便于部署在资源受限的边缘设备等问题,提出一种改进YOLOv11n(you only look once version 11 nano)的轻量级桥梁裂缝图像检测算法,通过融合ShuffleNetV2模块与跨尺度融合模块(cross-scale fusion module,CCFM),构建Shuffle-CCFM结构,提高多尺度特征的融合能力并降低算法参数量;在跨通道局部空间注意力(cross-channel partial spatial attention,C2PSA)模块中引入倒置残差块注意力机制(inverted residual mobile block with attention,iRMB),形成C2PSA-iRMB模块,提高算法对复杂裂缝细节的识别能力,并增强同一裂缝结构区域内空间长距离特征的关联建模能力;在C3k2模块中集成小波卷积(wavelet transform convolution,WTConv),形成C3k2-WTConv模块,提高模型在不同尺度下的特征提取能力;采用动态上采样器DySample代替传统上采样模块,根据特征图内容自适应调整采样位置,提高上采样阶段的空间分辨率与细节还原能力。开展消融试验、对比试验和可视化检测效果试验验证改进YOLOv11n算法的检测性能,试验结果表明:相较于YOLOv11n算法,引入Shuffle-CCFM结构、C2PSA-iRMB模块、C3k2-WTConv模块和DySample模块后的改进YOLOv11n算法的参数量N_(P)、计算量N_(f)、权重文件大小T分别减小27.5%、23.8%、32.7%,交并比阈值为50时平均精度均值E_(mAP50)、交并比阈值从50增至95时平均精度均值E_(mAP50-95)和召回率R分别提高1.6%、3.8%、0.4%,算法轻量化和检测精度明显提高;改进YOLOv11n算法对桥梁裂缝图像的检测精度和性能指标明显优于YOLOv5n、YOLOv6n、YOLOv8n、YOLOv10n等轻量级算法,适合部署于计算资源受限的边缘设备;改进YOLOv11n算法在桥梁裂缝可视化检测试验中对检测结果精确率有更高的置信度,对尺寸微小、形态复杂的裂缝细节捕捉能力较强,在复杂背景下具有较强的抗干扰能力。展开更多
Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data ...Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data are critical for assessing wetland ecosystem health and biodiversity.However,prevailing recognition approaches often prioritize detection accuracy at the expense of computational efficiency.They are also hindered by complex background heterogeneity and interspecies visual similarity.These limitations hinder the scalability and practical deployment of such methods for on-site ecological monitoring within wetland ecosystems.To address these challenges,this study proposes an optimized end-to-end framework,ShuffleNetV2-iRMB-ShapeIoU-YOLO(SISYOLO),designed for robust recognition of wetland waterbirds in complex environments.Specifically,the proposed framework integrates ShuffleNetV2 with inverted Residual Mobile Blocks(iRMB) to improve computational efficiency while maintaining robust feature representation.This design further enables deployment on resource-constrained mobile and embedded platforms.Additionally,ShapeIoU,a refined bounding box similarity metric,is introduced to jointly optimize overlap and shape consistency,effectively mitigating misclassification among visually similar species.Experimental results on the IC-Beijing dataset show that SIS-YOLO achieves 91.1% precision and 79.1% mAP@0.5:0.95 with only 2.9 million parameters.Compared with the lightweight baseline YOLOv8n,it improves precision by 2% and mAP@0.5:0.95 by 1.2%,while requiring fewer parameters and offering higher computational efficiency.展开更多
苹果作为全球重要的经济作物之一,其产量和质量直接受到病害的影响。为解决目前传统人工检测病害过程中主观性强、效率低,以及农业检测设备资源有限等问题,基于YOLOv8(You Only Look Once Version 8)提出了一种高效、轻量化的病害检测...苹果作为全球重要的经济作物之一,其产量和质量直接受到病害的影响。为解决目前传统人工检测病害过程中主观性强、效率低,以及农业检测设备资源有限等问题,基于YOLOv8(You Only Look Once Version 8)提出了一种高效、轻量化的病害检测模型—YOLOv8-RIC。在YOLOv8的基础上对主干网络进行了优化,分别引入了轻量级卷积神经网络RGN(RepGhostNet)和改进型残差移动网络iRMB(Improved Residual MobileNet Backbone),替换了原有的C2f模块,有效提升了模型的特征提取能力并降低了硬件计算成本。与原始YOLOv8模型相比,YOLOv8-RIC在自建图像数据集上的目标检测任务中,mAP(多类别平均精度)提高了6.2%,Precision(精确度)提高了12.7%。实验结果表明,该方法在复杂场景下对苹果树病害的检测具有较高的效率和鲁棒性,为精准农业的发展提供了有力支持。展开更多
文摘针对当前桥梁裂缝图像检测精度较低,算法规模较大不便于部署在资源受限的边缘设备等问题,提出一种改进YOLOv11n(you only look once version 11 nano)的轻量级桥梁裂缝图像检测算法,通过融合ShuffleNetV2模块与跨尺度融合模块(cross-scale fusion module,CCFM),构建Shuffle-CCFM结构,提高多尺度特征的融合能力并降低算法参数量;在跨通道局部空间注意力(cross-channel partial spatial attention,C2PSA)模块中引入倒置残差块注意力机制(inverted residual mobile block with attention,iRMB),形成C2PSA-iRMB模块,提高算法对复杂裂缝细节的识别能力,并增强同一裂缝结构区域内空间长距离特征的关联建模能力;在C3k2模块中集成小波卷积(wavelet transform convolution,WTConv),形成C3k2-WTConv模块,提高模型在不同尺度下的特征提取能力;采用动态上采样器DySample代替传统上采样模块,根据特征图内容自适应调整采样位置,提高上采样阶段的空间分辨率与细节还原能力。开展消融试验、对比试验和可视化检测效果试验验证改进YOLOv11n算法的检测性能,试验结果表明:相较于YOLOv11n算法,引入Shuffle-CCFM结构、C2PSA-iRMB模块、C3k2-WTConv模块和DySample模块后的改进YOLOv11n算法的参数量N_(P)、计算量N_(f)、权重文件大小T分别减小27.5%、23.8%、32.7%,交并比阈值为50时平均精度均值E_(mAP50)、交并比阈值从50增至95时平均精度均值E_(mAP50-95)和召回率R分别提高1.6%、3.8%、0.4%,算法轻量化和检测精度明显提高;改进YOLOv11n算法对桥梁裂缝图像的检测精度和性能指标明显优于YOLOv5n、YOLOv6n、YOLOv8n、YOLOv10n等轻量级算法,适合部署于计算资源受限的边缘设备;改进YOLOv11n算法在桥梁裂缝可视化检测试验中对检测结果精确率有更高的置信度,对尺寸微小、形态复杂的裂缝细节捕捉能力较强,在复杂背景下具有较强的抗干扰能力。
基金supported by National Natural Science Foundation of China (32401569,32371874)Beijing Natural Science Foundation(6244053)。
文摘Wetland waterbirds serve as key ecological indicators for assessing habitat quality and biodiversity.Accurate identification of waterbird species is a cornerstone of long-term ecological monitoring.The resulting data are critical for assessing wetland ecosystem health and biodiversity.However,prevailing recognition approaches often prioritize detection accuracy at the expense of computational efficiency.They are also hindered by complex background heterogeneity and interspecies visual similarity.These limitations hinder the scalability and practical deployment of such methods for on-site ecological monitoring within wetland ecosystems.To address these challenges,this study proposes an optimized end-to-end framework,ShuffleNetV2-iRMB-ShapeIoU-YOLO(SISYOLO),designed for robust recognition of wetland waterbirds in complex environments.Specifically,the proposed framework integrates ShuffleNetV2 with inverted Residual Mobile Blocks(iRMB) to improve computational efficiency while maintaining robust feature representation.This design further enables deployment on resource-constrained mobile and embedded platforms.Additionally,ShapeIoU,a refined bounding box similarity metric,is introduced to jointly optimize overlap and shape consistency,effectively mitigating misclassification among visually similar species.Experimental results on the IC-Beijing dataset show that SIS-YOLO achieves 91.1% precision and 79.1% mAP@0.5:0.95 with only 2.9 million parameters.Compared with the lightweight baseline YOLOv8n,it improves precision by 2% and mAP@0.5:0.95 by 1.2%,while requiring fewer parameters and offering higher computational efficiency.
文摘苹果作为全球重要的经济作物之一,其产量和质量直接受到病害的影响。为解决目前传统人工检测病害过程中主观性强、效率低,以及农业检测设备资源有限等问题,基于YOLOv8(You Only Look Once Version 8)提出了一种高效、轻量化的病害检测模型—YOLOv8-RIC。在YOLOv8的基础上对主干网络进行了优化,分别引入了轻量级卷积神经网络RGN(RepGhostNet)和改进型残差移动网络iRMB(Improved Residual MobileNet Backbone),替换了原有的C2f模块,有效提升了模型的特征提取能力并降低了硬件计算成本。与原始YOLOv8模型相比,YOLOv8-RIC在自建图像数据集上的目标检测任务中,mAP(多类别平均精度)提高了6.2%,Precision(精确度)提高了12.7%。实验结果表明,该方法在复杂场景下对苹果树病害的检测具有较高的效率和鲁棒性,为精准农业的发展提供了有力支持。
