To establish valid indexes for streetscape visual evaluation, this paper proposed 6 quantitative indexes to refl ect objective visual properties of streetscapes based on the image processing concept, and took real dig...To establish valid indexes for streetscape visual evaluation, this paper proposed 6 quantitative indexes to refl ect objective visual properties of streetscapes based on the image processing concept, and took real digital images of 10 pedestrian streets to verify the validity. Mathematical analysis of subjective and objective indexes showed that street width/height ratio, street width, sky openness index, visual entropy and color richness index could refl ect objective visual properties of streetscape(correlation coeffi cient r > 0.633, signifi cance P < 0.05); visual complexity accounted for the highest percentage in the evaluation conclusion(22.6%), so it was the most signifi cant infl uence factor.展开更多
Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however...Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.展开更多
Protecting and preserving our environmental systems require the ability to understand the spatio-temporal distri- bution of soils, parent material, topography, and land cover as well as the effects of human activities...Protecting and preserving our environmental systems require the ability to understand the spatio-temporal distri- bution of soils, parent material, topography, and land cover as well as the effects of human activities on ecosystems. Space-time modelling of ecosystems in an environmental digital library is essential for visualizing past, present, and future impacts of changes occurring within such landscapes (e.g., shift in land use practices). In this paper, we describe three novel features, spa- tio-temporal indexing, visualization, and geostatistical genre, for the environmental digital library, Environmental Visualization and Geographic Enterprise System (ENVISAGE), currently in progress at the University of Florida.展开更多
In order to improve the development efficiency of the indexable insert tip, three-dimensional parametric and visualization applications program of indexable insert tip was developed in AutoCAD VBA （Visual Basic for A...In order to improve the development efficiency of the indexable insert tip, three-dimensional parametric and visualization applications program of indexable insert tip was developed in AutoCAD VBA （Visual Basic for Applications）. The software could significantly improve the modeling efficiency of indexable insert tip and the model could also be used to static analysis, dynamic analysis and thermodynamic analysis. All aspects of performance could be fully understood by the finite element analysis. The ref- erence for the blade parameters preferred is also provided.展开更多
Background: The associations between the severity of interstitial lung disease and the stage and histologic type of concurrent lung cancer remain unknown. Purpose: To evaluate whether the severity of interstitial lung...Background: The associations between the severity of interstitial lung disease and the stage and histologic type of concurrent lung cancer remain unknown. Purpose: To evaluate whether the severity of interstitial lung abnormality (ILA), as indicated by quantitative computed tomographic (CT) indexes and CT visual score, was correlated with the stage and histological type of concurrent lung cancer. Materials and Methods: Twenty-eight patients with surgically diagnosed lung cancer and ILA on CT were enrolled in this retrospective study. The subjects were allocated to one of three groups by histological type: adenocarcinoma group (13 subjects);squamous cell carcinoma group (10 subjects);and the other histological diagnosis group (5 subjects). Two independent observers evaluated the CT findings to determine the CT visual score, and the kurtosis and skewness of CT-based density histograms were determined. The relationships between severity of ILA and the pathological stage and histological type of concurrent lung cancer were evaluated. Results: There were no significant differences in the CT visual scores and quantitative indexes among the three groups. CT visual score was significantly negatively correlated with pathological stage (r = −0.43, P = 0.025). Conclusion: Patients can have only mild ILA on visual scoring but advanced lung cancer. Therefore, the frequency of follow-up examination should not be based on the severity of ILA on CT.展开更多
街道景观空间对市民健康和城市风貌具有重要影响。既往研究中常以归一化植被指数(NDVI)和绿视率(GVI)来分别代表二维和三维的绿色指标,但对二者的指标相关性研究甚少。采用基于深度学习的图像语义分割方法分析百度街景计算代表性街道的G...街道景观空间对市民健康和城市风貌具有重要影响。既往研究中常以归一化植被指数(NDVI)和绿视率(GVI)来分别代表二维和三维的绿色指标,但对二者的指标相关性研究甚少。采用基于深度学习的图像语义分割方法分析百度街景计算代表性街道的GVI,利用GF-1卫星数据计算NDVI,比较分析城市街道的GVI和NDVI指标特征及相关性。结果表明,1)中山市中心城区各代表街道GVI指标参差不齐,从8.06%到36.00%,其中石岐街道兴中道GVI最高;2)各街道观测点的NDVI均值随着缓冲区尺度的增加也随之呈现出不同变化,NDVI均值具有强烈的尺度敏感性;3)50 m GVI和DNVI均值的皮尔逊相关系数最高,达到0.832。在此基础上分析街道景观存在的不足并给出优化建议,为城市街景评估、空间优化、景观提升提供参考。展开更多
基金Sponsored by Natural Science Foundation of China(51408499)100 Young Teachers’ Program of the Special Fund from Central University Basal Research Foundation(SWJTU2012X03178)
文摘To establish valid indexes for streetscape visual evaluation, this paper proposed 6 quantitative indexes to refl ect objective visual properties of streetscapes based on the image processing concept, and took real digital images of 10 pedestrian streets to verify the validity. Mathematical analysis of subjective and objective indexes showed that street width/height ratio, street width, sky openness index, visual entropy and color richness index could refl ect objective visual properties of streetscape(correlation coeffi cient r > 0.633, signifi cance P < 0.05); visual complexity accounted for the highest percentage in the evaluation conclusion(22.6%), so it was the most signifi cant infl uence factor.
基金supported by a Korea Agency for Infrastructure Technology Advancement(KAIA)grant funded by the Ministry of Land,Infrastructure,and Transport(Grant 22CTAP-C163951-02).
文摘Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.
文摘Protecting and preserving our environmental systems require the ability to understand the spatio-temporal distri- bution of soils, parent material, topography, and land cover as well as the effects of human activities on ecosystems. Space-time modelling of ecosystems in an environmental digital library is essential for visualizing past, present, and future impacts of changes occurring within such landscapes (e.g., shift in land use practices). In this paper, we describe three novel features, spa- tio-temporal indexing, visualization, and geostatistical genre, for the environmental digital library, Environmental Visualization and Geographic Enterprise System (ENVISAGE), currently in progress at the University of Florida.
基金Supported by Program for Liaoning Scientific Research Project in University(No.LS2010073)
文摘In order to improve the development efficiency of the indexable insert tip, three-dimensional parametric and visualization applications program of indexable insert tip was developed in AutoCAD VBA （Visual Basic for Applications）. The software could significantly improve the modeling efficiency of indexable insert tip and the model could also be used to static analysis, dynamic analysis and thermodynamic analysis. All aspects of performance could be fully understood by the finite element analysis. The ref- erence for the blade parameters preferred is also provided.
文摘Background: The associations between the severity of interstitial lung disease and the stage and histologic type of concurrent lung cancer remain unknown. Purpose: To evaluate whether the severity of interstitial lung abnormality (ILA), as indicated by quantitative computed tomographic (CT) indexes and CT visual score, was correlated with the stage and histological type of concurrent lung cancer. Materials and Methods: Twenty-eight patients with surgically diagnosed lung cancer and ILA on CT were enrolled in this retrospective study. The subjects were allocated to one of three groups by histological type: adenocarcinoma group (13 subjects);squamous cell carcinoma group (10 subjects);and the other histological diagnosis group (5 subjects). Two independent observers evaluated the CT findings to determine the CT visual score, and the kurtosis and skewness of CT-based density histograms were determined. The relationships between severity of ILA and the pathological stage and histological type of concurrent lung cancer were evaluated. Results: There were no significant differences in the CT visual scores and quantitative indexes among the three groups. CT visual score was significantly negatively correlated with pathological stage (r = −0.43, P = 0.025). Conclusion: Patients can have only mild ILA on visual scoring but advanced lung cancer. Therefore, the frequency of follow-up examination should not be based on the severity of ILA on CT.
文摘街道景观空间对市民健康和城市风貌具有重要影响。既往研究中常以归一化植被指数(NDVI)和绿视率(GVI)来分别代表二维和三维的绿色指标,但对二者的指标相关性研究甚少。采用基于深度学习的图像语义分割方法分析百度街景计算代表性街道的GVI,利用GF-1卫星数据计算NDVI,比较分析城市街道的GVI和NDVI指标特征及相关性。结果表明,1)中山市中心城区各代表街道GVI指标参差不齐,从8.06%到36.00%,其中石岐街道兴中道GVI最高;2)各街道观测点的NDVI均值随着缓冲区尺度的增加也随之呈现出不同变化,NDVI均值具有强烈的尺度敏感性;3)50 m GVI和DNVI均值的皮尔逊相关系数最高,达到0.832。在此基础上分析街道景观存在的不足并给出优化建议,为城市街景评估、空间优化、景观提升提供参考。
