The recently deployed Transition Region Explorer(TREx)-RGB(red-green-blue)all-sky imager(ASI)is designed to capture“true color”images of the aurora and airglow.Because the 557.7 nm green line is usually the brightes...The recently deployed Transition Region Explorer(TREx)-RGB(red-green-blue)all-sky imager(ASI)is designed to capture“true color”images of the aurora and airglow.Because the 557.7 nm green line is usually the brightest emission line in visible auroras,the green channel of a TREx-RGB camera is usually dominated by the 557.7 nm emission.Under this rationale,the TREx mission does not include a specific 557.7 nm imager and is designed to use the RGB green-channel data as a proxy for the 557.7 nm aurora.In this study,we present an initial effort to establish the conversion ratio or formula linking the RGB green-channel data to the absolute intensity of 557.7 nm auroras,which is crucial for quantitative uses of the RGB data.We illustrate two approaches:(1)through a comparison with the collocated measurement of green-line auroras from the TREx spectrograph,and(2)through a comparison with the modeled green-line intensity according to realistic electron precipitation flux measurements from low-Earth-orbit satellites,with the aid of an auroral transport model.We demonstrate the procedures and provide initial results for the TREx-RGB ASIs at the Rabbit Lake and Lucky Lake stations.The RGB response is found to be nonlinear.Empirical conversion ratios or formulas between RGB green-channel data and the green-line auroral intensity are given and can be applied immediately by TREx-RGB data users.The methodology established in this study will also be applicable to the upcoming SMILE ASI mission,which will adopt a similar RGB camera system in its deployment.展开更多
Recent advances in spectral sensing techniques and machine learning(ML)methods have enabled the estimation of plant physiochemical traits.Nitrogen(N)is a primary limiting factor for terrestrial forest growth,but tradi...Recent advances in spectral sensing techniques and machine learning(ML)methods have enabled the estimation of plant physiochemical traits.Nitrogen(N)is a primary limiting factor for terrestrial forest growth,but traditional methods for N determination are labor-intensive,time-consuming,and destructive.In this study,we present a rapid,non-destructive method to predict leaf N concentration(LNC)in Metasequoia glyptostroboides plantations under N and phosphorus(P)fertilization using ML techniques and unmanned aerial vehicle(UAV)-based RGB(red,green,blue)images.Nine spectral vegetation indices(VIs)were extracted from the RGB images.The spectral reflectance and VIs were used as input features to construct models for estimating LNC based on support vector machine,ran-dom forest(RF),and multiple linear regression,gradient boosting regression and classification and regression trees(CART).The results show that RF is the best fitting model for estimating LNC with a coefficient of determination(R2)of 0.73.Using this model,we evaluated the effects of N and P treatments on LNC and found a significant increase with N and a decrease with P.Height,diameter at breast height(DBH),and crown width of all M.glyptostroboides were analyzed by Pearson correlation with the predicted LNC.DBH was significantly correlated with LNC under N treat-ment.Our results highlight the potential of combining UAV RGB images with an ML algorithm as an efficient,scalable,and cost-effective method for LNC quantification.Future research can extend this approach to different tree species and different plant traits,paving the way for large-scale,time-efficient plant growth monitoring.展开更多
为推进富含花青素的紫苏品种选育,指导逆境胁迫下的紫苏生产管理,以紫苏为研究对象,采集田间叶片并使用数码相机拍照,结合红绿蓝色彩空间(red green blue color space,RGB)和CIELab色彩空间(CIELab color space)2种图像色彩分析手段处...为推进富含花青素的紫苏品种选育,指导逆境胁迫下的紫苏生产管理,以紫苏为研究对象,采集田间叶片并使用数码相机拍照,结合红绿蓝色彩空间(red green blue color space,RGB)和CIELab色彩空间(CIELab color space)2种图像色彩分析手段处理图片,与叶片花青素含量进行相关性和显著性分析,筛选出相关系数较高的色彩参数,建立单变量回归反演模型,最终综合建模得到预测效果最优的紫苏叶片花青素含量预测模型。结果表明,在RGB色彩空间中,红光标准化值(normalized redness intensity,NRI)、绿光标准化值(normalized greenness intensity,NGI)与花青素含量呈极显著相关,其中NGI的相关系数大于NRI。当叶片正反面色彩贡献比为2∶1时,NGI与花青素含量的相关性最大,相关系数为0.8532。对比不同模型发现,以NGI为自变量建立的指数模型拟合效果最好,相关系数为0.8381,决定系数(R^(2))达0.7550。在CIELab色彩空间中,红度(a^(*))与花青素含量的相关性最好,且相关系数同样在叶片正反面色彩贡献比为2∶1时达最大,为0.7356。基于a^(*)建立的幂模型拟合效果最好,相关系数和R^(2)分别为0.7438和0.6798。分别使用NGI模型和a^(*)模型对叶片花青素含量进行估测,验证后发现a^(*)模型的预测效果更好,准确性和稳定性更高,因此以a^(*)模型为预测紫苏叶片花青素含量的最优模型。展开更多
In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,th...In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.展开更多
基金jointly funded by the Canada Foundation for Innovationthe Alberta Economic Development and Trade organization+1 种基金the University of Calgarysupported by the Canadian Space Agency。
文摘The recently deployed Transition Region Explorer(TREx)-RGB(red-green-blue)all-sky imager(ASI)is designed to capture“true color”images of the aurora and airglow.Because the 557.7 nm green line is usually the brightest emission line in visible auroras,the green channel of a TREx-RGB camera is usually dominated by the 557.7 nm emission.Under this rationale,the TREx mission does not include a specific 557.7 nm imager and is designed to use the RGB green-channel data as a proxy for the 557.7 nm aurora.In this study,we present an initial effort to establish the conversion ratio or formula linking the RGB green-channel data to the absolute intensity of 557.7 nm auroras,which is crucial for quantitative uses of the RGB data.We illustrate two approaches:(1)through a comparison with the collocated measurement of green-line auroras from the TREx spectrograph,and(2)through a comparison with the modeled green-line intensity according to realistic electron precipitation flux measurements from low-Earth-orbit satellites,with the aid of an auroral transport model.We demonstrate the procedures and provide initial results for the TREx-RGB ASIs at the Rabbit Lake and Lucky Lake stations.The RGB response is found to be nonlinear.Empirical conversion ratios or formulas between RGB green-channel data and the green-line auroral intensity are given and can be applied immediately by TREx-RGB data users.The methodology established in this study will also be applicable to the upcoming SMILE ASI mission,which will adopt a similar RGB camera system in its deployment.
基金supported by the“Pioneer”and“Leading Goose”R&D Program of Zhejiang(2022C02053)National Natural Science Foundation of China(NSFC)(32201632).
文摘Recent advances in spectral sensing techniques and machine learning(ML)methods have enabled the estimation of plant physiochemical traits.Nitrogen(N)is a primary limiting factor for terrestrial forest growth,but traditional methods for N determination are labor-intensive,time-consuming,and destructive.In this study,we present a rapid,non-destructive method to predict leaf N concentration(LNC)in Metasequoia glyptostroboides plantations under N and phosphorus(P)fertilization using ML techniques and unmanned aerial vehicle(UAV)-based RGB(red,green,blue)images.Nine spectral vegetation indices(VIs)were extracted from the RGB images.The spectral reflectance and VIs were used as input features to construct models for estimating LNC based on support vector machine,ran-dom forest(RF),and multiple linear regression,gradient boosting regression and classification and regression trees(CART).The results show that RF is the best fitting model for estimating LNC with a coefficient of determination(R2)of 0.73.Using this model,we evaluated the effects of N and P treatments on LNC and found a significant increase with N and a decrease with P.Height,diameter at breast height(DBH),and crown width of all M.glyptostroboides were analyzed by Pearson correlation with the predicted LNC.DBH was significantly correlated with LNC under N treat-ment.Our results highlight the potential of combining UAV RGB images with an ML algorithm as an efficient,scalable,and cost-effective method for LNC quantification.Future research can extend this approach to different tree species and different plant traits,paving the way for large-scale,time-efficient plant growth monitoring.
文摘为推进富含花青素的紫苏品种选育,指导逆境胁迫下的紫苏生产管理,以紫苏为研究对象,采集田间叶片并使用数码相机拍照,结合红绿蓝色彩空间(red green blue color space,RGB)和CIELab色彩空间(CIELab color space)2种图像色彩分析手段处理图片,与叶片花青素含量进行相关性和显著性分析,筛选出相关系数较高的色彩参数,建立单变量回归反演模型,最终综合建模得到预测效果最优的紫苏叶片花青素含量预测模型。结果表明,在RGB色彩空间中,红光标准化值(normalized redness intensity,NRI)、绿光标准化值(normalized greenness intensity,NGI)与花青素含量呈极显著相关,其中NGI的相关系数大于NRI。当叶片正反面色彩贡献比为2∶1时,NGI与花青素含量的相关性最大,相关系数为0.8532。对比不同模型发现,以NGI为自变量建立的指数模型拟合效果最好,相关系数为0.8381,决定系数(R^(2))达0.7550。在CIELab色彩空间中,红度(a^(*))与花青素含量的相关性最好,且相关系数同样在叶片正反面色彩贡献比为2∶1时达最大,为0.7356。基于a^(*)建立的幂模型拟合效果最好,相关系数和R^(2)分别为0.7438和0.6798。分别使用NGI模型和a^(*)模型对叶片花青素含量进行估测,验证后发现a^(*)模型的预测效果更好,准确性和稳定性更高,因此以a^(*)模型为预测紫苏叶片花青素含量的最优模型。
基金supported by the National Natural Science Foundation of China(62073036,62076031)Beijing Natural Science Foundation(4242049).
文摘In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.
