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
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
【目的】研究芦苇(Phragmites australis)湿地土地类型变化、监测覆被特征,为湿地保护和开发提供参考。【方法】基于2017—2023年9月扎龙湿地Sentinel-2遥感影像,制作了包含湖泊、芦苇地、建筑地、耕地、盐碱地5种土地类型的遥感影像数...【目的】研究芦苇(Phragmites australis)湿地土地类型变化、监测覆被特征,为湿地保护和开发提供参考。【方法】基于2017—2023年9月扎龙湿地Sentinel-2遥感影像,制作了包含湖泊、芦苇地、建筑地、耕地、盐碱地5种土地类型的遥感影像数据集。通过视觉状态空间(visual state space model,Vmamba)联合注意力机制并结合水体指数NDWI生成水体掩膜对研究区进行信息提取,统计各土地类型的位置和面积变化信息。利用像元二分法提取植被覆盖度(fractional vegetation cover,FVC),计算叶面积指数(leaf area index,LAI)和生态质量指数(ecosystem quality index,EQI)。【结果】通过本研究提出的方法对研究区内分布信息进行提取,整体精度(overall accuracy,OA)为80.85%、平均交并比(mean intersection over union,MIoU)为71.59%,宏观平均F1值(macro-F1,MF1)为79.93%。2017—2023年,在扎龙湿地内湖泊、芦苇地的覆盖面积呈增加趋势;耕地、建筑地的覆盖面积呈减少趋势;盐碱地的覆盖面积呈波动趋势。植被覆盖度、生态质量指数先升高后降低,与中国气候公报内容基本一致。【结论】Vmamba联合注意力机制并结合水体掩膜的模型,在湿地信息提取方面效果良好,一定程度上提高土地利用分类与变化监测的精度。植被覆盖度、叶面积指数、生态质量指数的监测对湿地资源管理与可持续利用提供借鉴。展开更多
可逆信息隐藏(reversible data hiding,RDH)失真包括像素失真和结构失真。考虑到人类视觉系统(human visual system,HVS)对图像结构失真的高敏感性,本文提出使用结构相似性指数(structural similarity index measure,SSIM)作为RDH的评...可逆信息隐藏(reversible data hiding,RDH)失真包括像素失真和结构失真。考虑到人类视觉系统(human visual system,HVS)对图像结构失真的高敏感性,本文提出使用结构相似性指数(structural similarity index measure,SSIM)作为RDH的评价指标。首先,通过分析峰值信噪比(peak signal-to-noise ratio,PSNR)与SSIM的理论增益关系,实现对两个指标的动态同步评估。随后,提出一种基于纹理区域优先选择的高SSIM的RDH方法。将载体图像划分为4个独立像素集进行图像预处理,精准找到纹理区域,进而按照背景复杂度由高到低的顺序嵌入信息。实验结果表明,优先在纹理区域中嵌入信息的策略减小了图像结构失真。在相同的嵌入率下,SSIM值及图像视觉质量均得到了提高。展开更多
目的评估基于中国人群数据构建的可视化角膜生物力学分析仪(corneal visualization Scheimpflug technology,Corvis ST)生物力学指数(Corvis biomechanical index for Chinese populations,cCBI)鉴别临床期圆锥角膜(keratoconus,KC)、...目的评估基于中国人群数据构建的可视化角膜生物力学分析仪(corneal visualization Scheimpflug technology,Corvis ST)生物力学指数(Corvis biomechanical index for Chinese populations,cCBI)鉴别临床期圆锥角膜(keratoconus,KC)、顿挫型圆锥角膜(forme fruste keratoconus,FFKC)的效能,并与传统Corvis生物力学指数(Corvis biomechanical index,CBI)进行比较。方法本文为单中心回顾性病例对照研究。纳入101例KC患者(101眼)、132例FFKC患者(132眼);单纯屈光不正患者随机选取单眼纳入对照组(104人,104眼)。采用三维眼前节分析系统Pentacam HR进行角膜地形图评估,采用Corvis ST进行角膜生物力学评估。对生物力学参数进行受试者工作特征(receiver operating characteristic curve,ROC)曲线分析,比较CBI、cCBI鉴别KC、FFKC的能力,并以Youden指数最大为原则确定最优阈值(cut-off值)、灵敏度和特异度。采用DeLong检验对KC组和FFKC组的ROC曲线下面积(area under the curve,AUC)进行两两比较。结果cCBI区分KC组与对照组的AUC为0.942,取Youden指数最大对应的cut-off值0.87时,敏感度为94.1%,特异度为100%;CBI的AUC为0.980,取cut-off值0.88时,敏感度为98.0%,特异度为100.0%。cCBI区分FFKC组与对照组的AUC为0.729,取cut-off值0.28时,敏感度为59.1%,特异度为78.8%;CBI的AUC为0.775,取cut-off值0.72时,敏感度为48.5%,特异度为97.1%。结论cCBI与CBI在诊断典型KC时效能相当;针对FFKC,cCBI灵敏度更高、假阴性率更低,更适用于中国人群屈光手术的术前初筛。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
AIMTo analyze the relationship between two visual functions and refractive, topographic, pachymetric and aberrometric indicators in eyes with keratoconus.METHODSCorrected distance visual acuity (CDVA), and letter cont...AIMTo analyze the relationship between two visual functions and refractive, topographic, pachymetric and aberrometric indicators in eyes with keratoconus.METHODSCorrected distance visual acuity (CDVA), and letter contrast sensitivity (CS) were correlated with refraction, corneal topography, pachymetry, and total corneal wavefront data prospectively in 71 eyes with keratoconus. The topographic indices assessed were simulated keratometry for the flattest and steepest meridians (SimK1 and SimK2), posterior steeper K (Ks), elevation value in best-fit sphere (BFS) maps, squared eccentricity (Є<sup>2</sup>), aspheric asymmetric index (AAI), pachymetry, thickness progression index (TPI), the amount of pachymetric decentralization (APD), and GalileiTM-keratoconus indices.RESULTSThe mean CDVA (expressed as logMAR) were 0.25±0.21. The mean CS was 1.25±0.46. The spherical refraction correlated well with CDVA (r=-0.526, P<0.001). From topographic indices, SRI correlated with CS (r=-0.695), and IAI with CS (r=-0.672) (P<0.001 for all). Root mean square (RMS) was 4.3±1.81 µm, spherical aberration (SA) was -0.4±0.67 µm, vertical and horizontal coma were -2.1±1.47 and -0.4±0.72 µm. All wavefront data (except horizontal coma), AAI, Є<sup>2</sup> and maximum BFS correlated significantly with the visual function (P≤0.001 for all).CONCLUSIONIn this study, CS is more affected than CDVA as a visual function. The quantity and quality of vision is significantly correlated with well-known and new topographic indices. There is not a significant correlation between visual function and pachymetric parameters. The significantly correlated indices can be used in staging keratoconus and to follow the outcome of a treatment.展开更多
An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, clo...An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, cloud data de-noising optimization, construction, display and operation of three-dimensional model, model editing, profile generation, calculation of goaf volume and roof area, Boolean calculation among models and interaction with the third party soft ware. Concerning this system with a concise interface, plentiful data input/output interfaces, it is featured with high integration, simple and convenient operations of applications. According to practice, in addition to being well-adapted, this system is favorably reliable and stable.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 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【目的】研究芦苇(Phragmites australis)湿地土地类型变化、监测覆被特征,为湿地保护和开发提供参考。【方法】基于2017—2023年9月扎龙湿地Sentinel-2遥感影像,制作了包含湖泊、芦苇地、建筑地、耕地、盐碱地5种土地类型的遥感影像数据集。通过视觉状态空间(visual state space model,Vmamba)联合注意力机制并结合水体指数NDWI生成水体掩膜对研究区进行信息提取,统计各土地类型的位置和面积变化信息。利用像元二分法提取植被覆盖度(fractional vegetation cover,FVC),计算叶面积指数(leaf area index,LAI)和生态质量指数(ecosystem quality index,EQI)。【结果】通过本研究提出的方法对研究区内分布信息进行提取,整体精度(overall accuracy,OA)为80.85%、平均交并比(mean intersection over union,MIoU)为71.59%,宏观平均F1值(macro-F1,MF1)为79.93%。2017—2023年,在扎龙湿地内湖泊、芦苇地的覆盖面积呈增加趋势;耕地、建筑地的覆盖面积呈减少趋势;盐碱地的覆盖面积呈波动趋势。植被覆盖度、生态质量指数先升高后降低,与中国气候公报内容基本一致。【结论】Vmamba联合注意力机制并结合水体掩膜的模型,在湿地信息提取方面效果良好,一定程度上提高土地利用分类与变化监测的精度。植被覆盖度、叶面积指数、生态质量指数的监测对湿地资源管理与可持续利用提供借鉴。
文摘可逆信息隐藏(reversible data hiding,RDH)失真包括像素失真和结构失真。考虑到人类视觉系统(human visual system,HVS)对图像结构失真的高敏感性,本文提出使用结构相似性指数(structural similarity index measure,SSIM)作为RDH的评价指标。首先,通过分析峰值信噪比(peak signal-to-noise ratio,PSNR)与SSIM的理论增益关系,实现对两个指标的动态同步评估。随后,提出一种基于纹理区域优先选择的高SSIM的RDH方法。将载体图像划分为4个独立像素集进行图像预处理,精准找到纹理区域,进而按照背景复杂度由高到低的顺序嵌入信息。实验结果表明,优先在纹理区域中嵌入信息的策略减小了图像结构失真。在相同的嵌入率下,SSIM值及图像视觉质量均得到了提高。
文摘目的评估基于中国人群数据构建的可视化角膜生物力学分析仪(corneal visualization Scheimpflug technology,Corvis ST)生物力学指数(Corvis biomechanical index for Chinese populations,cCBI)鉴别临床期圆锥角膜(keratoconus,KC)、顿挫型圆锥角膜(forme fruste keratoconus,FFKC)的效能,并与传统Corvis生物力学指数(Corvis biomechanical index,CBI)进行比较。方法本文为单中心回顾性病例对照研究。纳入101例KC患者(101眼)、132例FFKC患者(132眼);单纯屈光不正患者随机选取单眼纳入对照组(104人,104眼)。采用三维眼前节分析系统Pentacam HR进行角膜地形图评估,采用Corvis ST进行角膜生物力学评估。对生物力学参数进行受试者工作特征(receiver operating characteristic curve,ROC)曲线分析,比较CBI、cCBI鉴别KC、FFKC的能力,并以Youden指数最大为原则确定最优阈值(cut-off值)、灵敏度和特异度。采用DeLong检验对KC组和FFKC组的ROC曲线下面积(area under the curve,AUC)进行两两比较。结果cCBI区分KC组与对照组的AUC为0.942,取Youden指数最大对应的cut-off值0.87时,敏感度为94.1%,特异度为100%;CBI的AUC为0.980,取cut-off值0.88时,敏感度为98.0%,特异度为100.0%。cCBI区分FFKC组与对照组的AUC为0.729,取cut-off值0.28时,敏感度为59.1%,特异度为78.8%;CBI的AUC为0.775,取cut-off值0.72时,敏感度为48.5%,特异度为97.1%。结论cCBI与CBI在诊断典型KC时效能相当;针对FFKC,cCBI灵敏度更高、假阴性率更低,更适用于中国人群屈光手术的术前初筛。
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AIMTo analyze the relationship between two visual functions and refractive, topographic, pachymetric and aberrometric indicators in eyes with keratoconus.METHODSCorrected distance visual acuity (CDVA), and letter contrast sensitivity (CS) were correlated with refraction, corneal topography, pachymetry, and total corneal wavefront data prospectively in 71 eyes with keratoconus. The topographic indices assessed were simulated keratometry for the flattest and steepest meridians (SimK1 and SimK2), posterior steeper K (Ks), elevation value in best-fit sphere (BFS) maps, squared eccentricity (Є<sup>2</sup>), aspheric asymmetric index (AAI), pachymetry, thickness progression index (TPI), the amount of pachymetric decentralization (APD), and GalileiTM-keratoconus indices.RESULTSThe mean CDVA (expressed as logMAR) were 0.25±0.21. The mean CS was 1.25±0.46. The spherical refraction correlated well with CDVA (r=-0.526, P<0.001). From topographic indices, SRI correlated with CS (r=-0.695), and IAI with CS (r=-0.672) (P<0.001 for all). Root mean square (RMS) was 4.3±1.81 µm, spherical aberration (SA) was -0.4±0.67 µm, vertical and horizontal coma were -2.1±1.47 and -0.4±0.72 µm. All wavefront data (except horizontal coma), AAI, Є<sup>2</sup> and maximum BFS correlated significantly with the visual function (P≤0.001 for all).CONCLUSIONIn this study, CS is more affected than CDVA as a visual function. The quantity and quality of vision is significantly correlated with well-known and new topographic indices. There is not a significant correlation between visual function and pachymetric parameters. The significantly correlated indices can be used in staging keratoconus and to follow the outcome of a treatment.
基金Project(51274250)supported by the National Natural Science Foundation of ChinaProject(2012BAK09B02-05)supported by the National Key Technology R&D Program during the 12th Five-year Plan of China
文摘An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, cloud data de-noising optimization, construction, display and operation of three-dimensional model, model editing, profile generation, calculation of goaf volume and roof area, Boolean calculation among models and interaction with the third party soft ware. Concerning this system with a concise interface, plentiful data input/output interfaces, it is featured with high integration, simple and convenient operations of applications. According to practice, in addition to being well-adapted, this system is favorably reliable and stable.
