Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each l...Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.展开更多
To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks o...To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre-trained deep convolution neural network,the true positives are segmented,and crack properties are extracted using two different methods.The first method is primarily based on active contour models and level-set segmentation and the second method consists of the domain adaptation of a mathematical morphology-based method known as FIL-FINDER.A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method.An advanced convolution neural network-based multi-output regression model has been proposed which was trained with the prepared database and validated with the held-out dataset for the prediction of crack-length,crack-width,and width-uncertainty directly from input image patches.The pro-posed model has been tested on crack patches collected from different locations.Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it.Additionally,an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the pre-diction results.Finally,the best performing model HHc-X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.展开更多
Objective:Urethral stricture is a highly prevalent disease and has a continued ris-ing incidence.The global burden of disease keeps rising as there are significant rates of recur-rence with the existing management opt...Objective:Urethral stricture is a highly prevalent disease and has a continued ris-ing incidence.The global burden of disease keeps rising as there are significant rates of recur-rence with the existing management options with the need for additional repeat procedures.Moreover,the existing treatment options are associated with significant morbidity in the pa-tient.Long segment urethral strictures are most commonly managed by augmentation urethro-plasty.We explored the potential for the application of an acellular tissue engineered bovine pericardial patch in augmentation urethroplasty in a series of our patients suffering from ure-thral stricture disease.The decreased morbidity due to the avoidance of harvest of buccal mu-cosa,decreased operative time and satisfactory postoperative results make it a promising option for augmentation urethroplasty.Methods:Nine patients with long segment anterior urethral strictures(involving penile and/or bulbar urethra and stricture length>4 cm)were included in the study after proper informed consent was obtained.Acellular tissue engineered indigenous bovine pericardial patch was used for urethroplasty using dorsal onlay technique.Results:A total of nine patients underwent tissue engineered indigenous pericardial patch ur-ethroplasty for long segment urethral strictures,mostly catheter injury induced or associated with balanitis xerotica obliterans.Median follow-up was 8 months(range:2-12 months).Out of nine patients,eight(88.9%)were classifed as success and one(11.1%)was classified as fail-ure.Conclusion:Our study brings a product of tissue engineering,already being used in the cardio-vascular surgery domain,into the urological surgery operating room with satisfactory results achieved using standard operating techniques of one stage urethroplasty.展开更多
Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.T...Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.Then the general multiphase image segmentation model of Potts model is extended for texture segmentation by adding the region information of the texture descriptor.A fast numerical scheme based on the split Bregman method is designed to speed up the computational process.The algorithm is efficient,and both the texture descriptor and the characteristic functions can be implemented easily.Experiments using synthetic texture images,real natural scene images and synthetic aperture radar images are presented to give qualitative comparisons between our method and other state-of-the-art techniques.The results show that our method can accurately segment object regions and is competitive compared with other methods especially in segmenting natural images.展开更多
现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个...现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个小块,分别计算这些小块的注意力得分,增强对局部信息的感知能力。使用一组空洞卷积计算整个特征图的得分,获得全局多尺度信息的权衡。实验中,将PGMA集成到U-Net、DeepLab、SegNet等语义分割网络中,有效提升了它们的分割性能。这表明PGMA在增强CNN性能方面优于当前主流方法。展开更多
传统的高斯混合模型(Gaussian mixture model,GMM)算法在图像分割中未考虑像素的空间信息,导致其对于噪声十分敏感.马尔科夫随机场(Markov random field,MRF)模型通过像素类别标记的Gibbs分布先验概率引入了图像的空间信息,能较好地分...传统的高斯混合模型(Gaussian mixture model,GMM)算法在图像分割中未考虑像素的空间信息,导致其对于噪声十分敏感.马尔科夫随机场(Markov random field,MRF)模型通过像素类别标记的Gibbs分布先验概率引入了图像的空间信息,能较好地分割含有噪声的图像,然而MRF模型的分割结果容易出现过平滑现象.为了解决上述缺陷,提出了一种新的基于图像片权重方法的马尔科夫随机场图像分割模型,对邻域内的不同图像片根据相似度赋予不同的权重,使其在克服噪声影响的同时能保持图像细节信息.同时,采用KL距离引入先验概率与后验概率关于熵的惩罚项,并对该惩罚项进行平滑,得到最终的分割结果.实验结果表明,算法具有较强的自适应性,能够有效克服噪声对于分割结果的影响,并获得较高的分割精度.展开更多
提出了一种基于代理缓存的移动流媒体动态调度算法DS2AM2PC(Dynamic Scheduling Algorithm for Mobile Streaming Mediabased on Proxy Caching),采用代理缓存窗口自适应伸缩和分段缓存补丁块方案,在代理缓存中根据具体情况每次缓存相...提出了一种基于代理缓存的移动流媒体动态调度算法DS2AM2PC(Dynamic Scheduling Algorithm for Mobile Streaming Mediabased on Proxy Caching),采用代理缓存窗口自适应伸缩和分段缓存补丁块方案,在代理缓存中根据具体情况每次缓存相同或者不同大小的段补丁块,同时隔一段时间,根据移动媒体流行度更新一次缓存窗口大小,动态决定其最大缓存大小,实现了移动流媒体对象在代理服务器中缓存的数据量和其流行度成正比的原则.仿真结果表明,对于客户请求到达速率的变化,DS2AM2PC算法比P3S2A(Proxy-assisted Patch Pre-fetching and Service Scheduling Algorithm)算法和OBP(Optimized Batch Patching)+prefix & patchcaching算法具有更好的适应性,在最大缓存空间相同的情况下,能显著减少通过补丁通道传输的补丁数据,从而降低了服务器和骨干网络带宽的使用,能快速缓存媒体对象到缓存窗口,同时减少了代理服务器的缓存平均占有量.展开更多
基金supported in part by the Gansu Haizhi Characteristic Demonstration Project(No.GSHZTS2022-2).
文摘Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.
文摘To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre-trained deep convolution neural network,the true positives are segmented,and crack properties are extracted using two different methods.The first method is primarily based on active contour models and level-set segmentation and the second method consists of the domain adaptation of a mathematical morphology-based method known as FIL-FINDER.A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method.An advanced convolution neural network-based multi-output regression model has been proposed which was trained with the prepared database and validated with the held-out dataset for the prediction of crack-length,crack-width,and width-uncertainty directly from input image patches.The pro-posed model has been tested on crack patches collected from different locations.Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it.Additionally,an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the pre-diction results.Finally,the best performing model HHc-X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.
文摘Objective:Urethral stricture is a highly prevalent disease and has a continued ris-ing incidence.The global burden of disease keeps rising as there are significant rates of recur-rence with the existing management options with the need for additional repeat procedures.Moreover,the existing treatment options are associated with significant morbidity in the pa-tient.Long segment urethral strictures are most commonly managed by augmentation urethro-plasty.We explored the potential for the application of an acellular tissue engineered bovine pericardial patch in augmentation urethroplasty in a series of our patients suffering from ure-thral stricture disease.The decreased morbidity due to the avoidance of harvest of buccal mu-cosa,decreased operative time and satisfactory postoperative results make it a promising option for augmentation urethroplasty.Methods:Nine patients with long segment anterior urethral strictures(involving penile and/or bulbar urethra and stricture length>4 cm)were included in the study after proper informed consent was obtained.Acellular tissue engineered indigenous bovine pericardial patch was used for urethroplasty using dorsal onlay technique.Results:A total of nine patients underwent tissue engineered indigenous pericardial patch ur-ethroplasty for long segment urethral strictures,mostly catheter injury induced or associated with balanitis xerotica obliterans.Median follow-up was 8 months(range:2-12 months).Out of nine patients,eight(88.9%)were classifed as success and one(11.1%)was classified as fail-ure.Conclusion:Our study brings a product of tissue engineering,already being used in the cardio-vascular surgery domain,into the urological surgery operating room with satisfactory results achieved using standard operating techniques of one stage urethroplasty.
基金supported by the National Natural Science Foundation of China(No.61170106)
文摘Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.Then the general multiphase image segmentation model of Potts model is extended for texture segmentation by adding the region information of the texture descriptor.A fast numerical scheme based on the split Bregman method is designed to speed up the computational process.The algorithm is efficient,and both the texture descriptor and the characteristic functions can be implemented easily.Experiments using synthetic texture images,real natural scene images and synthetic aperture radar images are presented to give qualitative comparisons between our method and other state-of-the-art techniques.The results show that our method can accurately segment object regions and is competitive compared with other methods especially in segmenting natural images.
文摘现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个小块,分别计算这些小块的注意力得分,增强对局部信息的感知能力。使用一组空洞卷积计算整个特征图的得分,获得全局多尺度信息的权衡。实验中,将PGMA集成到U-Net、DeepLab、SegNet等语义分割网络中,有效提升了它们的分割性能。这表明PGMA在增强CNN性能方面优于当前主流方法。
文摘传统的高斯混合模型(Gaussian mixture model,GMM)算法在图像分割中未考虑像素的空间信息,导致其对于噪声十分敏感.马尔科夫随机场(Markov random field,MRF)模型通过像素类别标记的Gibbs分布先验概率引入了图像的空间信息,能较好地分割含有噪声的图像,然而MRF模型的分割结果容易出现过平滑现象.为了解决上述缺陷,提出了一种新的基于图像片权重方法的马尔科夫随机场图像分割模型,对邻域内的不同图像片根据相似度赋予不同的权重,使其在克服噪声影响的同时能保持图像细节信息.同时,采用KL距离引入先验概率与后验概率关于熵的惩罚项,并对该惩罚项进行平滑,得到最终的分割结果.实验结果表明,算法具有较强的自适应性,能够有效克服噪声对于分割结果的影响,并获得较高的分割精度.
文摘提出了一种基于代理缓存的移动流媒体动态调度算法DS2AM2PC(Dynamic Scheduling Algorithm for Mobile Streaming Mediabased on Proxy Caching),采用代理缓存窗口自适应伸缩和分段缓存补丁块方案,在代理缓存中根据具体情况每次缓存相同或者不同大小的段补丁块,同时隔一段时间,根据移动媒体流行度更新一次缓存窗口大小,动态决定其最大缓存大小,实现了移动流媒体对象在代理服务器中缓存的数据量和其流行度成正比的原则.仿真结果表明,对于客户请求到达速率的变化,DS2AM2PC算法比P3S2A(Proxy-assisted Patch Pre-fetching and Service Scheduling Algorithm)算法和OBP(Optimized Batch Patching)+prefix & patchcaching算法具有更好的适应性,在最大缓存空间相同的情况下,能显著减少通过补丁通道传输的补丁数据,从而降低了服务器和骨干网络带宽的使用,能快速缓存媒体对象到缓存窗口,同时减少了代理服务器的缓存平均占有量.
