Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency d...Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency domain. Theoretical analysis and simulation show the relation between the measurement matrix resolution and compressive sensing(CS)imaging quality. The matrix design is improved to provide multi-scale modulations, followed by individual reconstruction of images of different spatial frequencies. Compared with traditional single-scale CS imaging, the multi-scale method provides high quality imaging in both high and low frequencies, and effectively decreases the overall reconstruction error.Experimental results confirm the feasibility of this technique, especially at low sampling rate. The method may thus be helpful in promoting the implementation of compressive imaging in real applications.展开更多
To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease rec...To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.展开更多
Aims The relative roles of ecological processes in structuring beta diver-sity are usually quantified by variation partitioning of beta diversity with respect to environmental and spatial variables or gamma di-versity...Aims The relative roles of ecological processes in structuring beta diver-sity are usually quantified by variation partitioning of beta diversity with respect to environmental and spatial variables or gamma di-versity.However,if important environmental or spatial factors are omitted,or a scale mismatch occurs in the analysis,unaccounted spatial correlation will appear in the residual errors and lead to re-sidual spatial correlation and problematic inferences.Methods Multi-scale ordination(MSO)partitions the canonical ordination results by distance into a set of empirical variograms which charac-terize the spatial structures of explanatory,conditional and residual variance against distance.Then these variance components can be used to diagnose residual spatial correlation by checking assump-tions related to geostatistics or regression analysis.In this paper,we first illustrate the performance of MSO using a simulated data set with known properties,thus making statistical issues explicit.We then test for significant residual spatial correlation in beta diversity analyses of the Gutianshan(GTS)24-ha subtropical forest plot in eastern China.Important Findings Even though we used up to 24 topographic and edaphic variables mapped at high resolution and spatial variables representing spa-tial structures at all scales,we still found significant residual spatial correlation at the 10 m×10 m quadrat scale.This invalidated the analysis and inferences at this scale.We also show that MSO pro-vides a complementary tool to test for significant residual spatial correlation in beta diversity analyses.Our results provided a strong argument supporting the need to test for significant residual spatial correlation before interpreting the results of beta diversity analyses.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61601442,61605218,and 61575207)the National Key Research and Development Program of China(Grant No.2018YFB0504302)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(Grant Nos.2015124 and 2019154)。
文摘Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency domain. Theoretical analysis and simulation show the relation between the measurement matrix resolution and compressive sensing(CS)imaging quality. The matrix design is improved to provide multi-scale modulations, followed by individual reconstruction of images of different spatial frequencies. Compared with traditional single-scale CS imaging, the multi-scale method provides high quality imaging in both high and low frequencies, and effectively decreases the overall reconstruction error.Experimental results confirm the feasibility of this technique, especially at low sampling rate. The method may thus be helpful in promoting the implementation of compressive imaging in real applications.
基金funded by the Science and Technology Development Program of Jilin Province(20190301024NY)the Precision Agriculture and Big Data Engineering Research Center of Jilin Province(2020C005).
文摘To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.
基金The analyses reported in this paper were financially supported by the National Natural Science Foundation of China(Grant No.31470490 and 31770478).
文摘Aims The relative roles of ecological processes in structuring beta diver-sity are usually quantified by variation partitioning of beta diversity with respect to environmental and spatial variables or gamma di-versity.However,if important environmental or spatial factors are omitted,or a scale mismatch occurs in the analysis,unaccounted spatial correlation will appear in the residual errors and lead to re-sidual spatial correlation and problematic inferences.Methods Multi-scale ordination(MSO)partitions the canonical ordination results by distance into a set of empirical variograms which charac-terize the spatial structures of explanatory,conditional and residual variance against distance.Then these variance components can be used to diagnose residual spatial correlation by checking assump-tions related to geostatistics or regression analysis.In this paper,we first illustrate the performance of MSO using a simulated data set with known properties,thus making statistical issues explicit.We then test for significant residual spatial correlation in beta diversity analyses of the Gutianshan(GTS)24-ha subtropical forest plot in eastern China.Important Findings Even though we used up to 24 topographic and edaphic variables mapped at high resolution and spatial variables representing spa-tial structures at all scales,we still found significant residual spatial correlation at the 10 m×10 m quadrat scale.This invalidated the analysis and inferences at this scale.We also show that MSO pro-vides a complementary tool to test for significant residual spatial correlation in beta diversity analyses.Our results provided a strong argument supporting the need to test for significant residual spatial correlation before interpreting the results of beta diversity analyses.
