In this paper, the distribution of the phase deviations for the ghosting of Vernier based imagers is provided. The equality of the phase errors is shown. The relationship between the charge noise amplitude of electrod...In this paper, the distribution of the phase deviations for the ghosting of Vernier based imagers is provided. The equality of the phase errors is shown. The relationship between the charge noise amplitude of electrodes and the total charge noise amplitude is provided. The relationship between the phase error and the total charge noise amplitude is also provided, which reveals the magnitude of 10 4 electrons for the ghosting occurrence threshold for the 4-coarse-pixel anode imagers.展开更多
The unique advantage of x-ray ghost imaging(XGI)is its potential in low dose radiology.One of the practical ways to reduce the radiation exposure is to reduce the measurements while remaining sufficient image quality....The unique advantage of x-ray ghost imaging(XGI)is its potential in low dose radiology.One of the practical ways to reduce the radiation exposure is to reduce the measurements while remaining sufficient image quality.Synthetic aperture x-ray ghost imaging(SAXGI)is invented to achieve megapixel XGI with limited measurements,which is expected to implement XGI simultaneously with large field of view and low radiation exposure.In this paper,we experimentally investigate the effect of measurements reduction on the spatial resolution and image quality of SAXGI with standard sample and biomedical specimen.The results with a resolution chart demonstrated that at 360 measurements,SAXGI successfully retrieved the sample image of 1960×1960 pixels with spatial resolution of 4μm.With measurement reduction,the spatial resolution deteriorates but the sparser structures are still discernable.Even with measurements reduced to 10,a spatial resolution of 10μm can still be achieved by SAXGI.A biomedical sample of a fish specimen is employed to evaluate the method and the fish image of 2000×1000 pixels with an SSIM of 0.962 is reconstructed by SAXGI with 770measurements,corresponding to an accumulative exposure reduction of more than 2 times.With the measurements reduced to 10 which corresponds to 1/160 of the accumulative radiation exposure for conventional radiology,bulky structure like the fish skeleton can still be definitely discerned and the SSIM for the reconstructed image still retained 0.9179.Results of this paper demonstrate that measurements reduction is practicable for the radiation exposure reduction of the sample,which implicates that SAXGI with limited measurements is an efficient solution for low dose radiology.展开更多
针对现有集装箱编号识别算法结构复杂以及难以应用在低成本设备上的问题,文中提出一种基于深度学习的轻量型算法YOLOv4-GSE(You Only Look Once version 4-Ghost-SPPFA-Effective),利用Ghost-Enet网络替代YOLOv4的主干特征提取网络,使用...针对现有集装箱编号识别算法结构复杂以及难以应用在低成本设备上的问题,文中提出一种基于深度学习的轻量型算法YOLOv4-GSE(You Only Look Once version 4-Ghost-SPPFA-Effective),利用Ghost-Enet网络替代YOLOv4的主干特征提取网络,使用Ghost卷积替换所有3×3卷积方式来削减模型的参数量。在加强特征提取部分,提出一种改进后的SPPFA(Spatial Pyramid Pooling with Feature Aggregation)模块来解决由于连续最大池化操作造成的信息丢失问题。添加CBAM(Convolutional Block Attention Module)注意力机制模块对不同通道和空间进行权重分析,增强模型的特征提取能力。相较于YOLOv4,所提算法在集装箱数据集上的mAP(mean Average Precision)值提升了1.02%,参数量减少了91.95%,FLOPs(Floating-point Operations Per Second)减少了94.62%。展开更多
为了对心理健康自动检测仪目标的反常现象进行检测,研究设计了包含目标检测、目标跟踪和反常行为识别的综合模型。研究设计了基于You Only Look Once 5小型的目标检测模型,并引入卷积注意力模块来进行改进。也设计了基于深度简单在线实...为了对心理健康自动检测仪目标的反常现象进行检测,研究设计了包含目标检测、目标跟踪和反常行为识别的综合模型。研究设计了基于You Only Look Once 5小型的目标检测模型,并引入卷积注意力模块来进行改进。也设计了基于深度简单在线实时跟踪技术的跟踪模型,并引入了Ghost模块来进行改进。研究构建了基于SlowFast结构和特征金字塔的反常行为识别模型。结果显示,检测模型的准确率最大值为98.57%,跟踪模型的曲线下面积为0.987。反常行为识别模型在正常、抹眼泪、打脸和一个地方来回走动的动作上的准确率最大值分别为95.57%、96.17%、96.58%和97.06%。所设计的综合模型具有良好的性能,能够为心理健康自动检测仪目标的反常现象检测提供目标检测、跟踪和行为识别上的技术支持。展开更多
基金the National Natural Science Foundations of China (Grant Nos. 10878005/A03 and 61007017)
文摘In this paper, the distribution of the phase deviations for the ghosting of Vernier based imagers is provided. The equality of the phase errors is shown. The relationship between the charge noise amplitude of electrodes and the total charge noise amplitude is provided. The relationship between the phase error and the total charge noise amplitude is also provided, which reveals the magnitude of 10 4 electrons for the ghosting occurrence threshold for the 4-coarse-pixel anode imagers.
基金Project supported by the National Key Research and Development Program of China(Grant Nos.2022YFA1603601,2021YFF0601203,and 2021YFA1600703)。
文摘The unique advantage of x-ray ghost imaging(XGI)is its potential in low dose radiology.One of the practical ways to reduce the radiation exposure is to reduce the measurements while remaining sufficient image quality.Synthetic aperture x-ray ghost imaging(SAXGI)is invented to achieve megapixel XGI with limited measurements,which is expected to implement XGI simultaneously with large field of view and low radiation exposure.In this paper,we experimentally investigate the effect of measurements reduction on the spatial resolution and image quality of SAXGI with standard sample and biomedical specimen.The results with a resolution chart demonstrated that at 360 measurements,SAXGI successfully retrieved the sample image of 1960×1960 pixels with spatial resolution of 4μm.With measurement reduction,the spatial resolution deteriorates but the sparser structures are still discernable.Even with measurements reduced to 10,a spatial resolution of 10μm can still be achieved by SAXGI.A biomedical sample of a fish specimen is employed to evaluate the method and the fish image of 2000×1000 pixels with an SSIM of 0.962 is reconstructed by SAXGI with 770measurements,corresponding to an accumulative exposure reduction of more than 2 times.With the measurements reduced to 10 which corresponds to 1/160 of the accumulative radiation exposure for conventional radiology,bulky structure like the fish skeleton can still be definitely discerned and the SSIM for the reconstructed image still retained 0.9179.Results of this paper demonstrate that measurements reduction is practicable for the radiation exposure reduction of the sample,which implicates that SAXGI with limited measurements is an efficient solution for low dose radiology.
文摘针对现有集装箱编号识别算法结构复杂以及难以应用在低成本设备上的问题,文中提出一种基于深度学习的轻量型算法YOLOv4-GSE(You Only Look Once version 4-Ghost-SPPFA-Effective),利用Ghost-Enet网络替代YOLOv4的主干特征提取网络,使用Ghost卷积替换所有3×3卷积方式来削减模型的参数量。在加强特征提取部分,提出一种改进后的SPPFA(Spatial Pyramid Pooling with Feature Aggregation)模块来解决由于连续最大池化操作造成的信息丢失问题。添加CBAM(Convolutional Block Attention Module)注意力机制模块对不同通道和空间进行权重分析,增强模型的特征提取能力。相较于YOLOv4,所提算法在集装箱数据集上的mAP(mean Average Precision)值提升了1.02%,参数量减少了91.95%,FLOPs(Floating-point Operations Per Second)减少了94.62%。
文摘为了对心理健康自动检测仪目标的反常现象进行检测,研究设计了包含目标检测、目标跟踪和反常行为识别的综合模型。研究设计了基于You Only Look Once 5小型的目标检测模型,并引入卷积注意力模块来进行改进。也设计了基于深度简单在线实时跟踪技术的跟踪模型,并引入了Ghost模块来进行改进。研究构建了基于SlowFast结构和特征金字塔的反常行为识别模型。结果显示,检测模型的准确率最大值为98.57%,跟踪模型的曲线下面积为0.987。反常行为识别模型在正常、抹眼泪、打脸和一个地方来回走动的动作上的准确率最大值分别为95.57%、96.17%、96.58%和97.06%。所设计的综合模型具有良好的性能,能够为心理健康自动检测仪目标的反常现象检测提供目标检测、跟踪和行为识别上的技术支持。
