The construction of high-filled loess project has some engineering and technical challenges, such as excavation of earth and backfilling of earth are both large, complex construction environment, variety of influence ...The construction of high-filled loess project has some engineering and technical challenges, such as excavation of earth and backfilling of earth are both large, complex construction environment, variety of influence factors. According to this situation, this paper presents a dynamic 3D visualization method for high-filled project based on volume rendering. Through comparative analysis and visual analysis, realized at different times of the Loess fill internal detection data visualization and analysis presented. The results show that this visualization method can directly and accurately display the construction process, help decision makers master construction information and process.展开更多
This paper proposes a necessary clarification about the problematic of super-quantum correlations, whose mainstream debate relies on an incorrect, statistical interpretation of the no-signaling condition. The no-signa...This paper proposes a necessary clarification about the problematic of super-quantum correlations, whose mainstream debate relies on an incorrect, statistical interpretation of the no-signaling condition. The no-signaling condition is an informational constraint that limits the strength of non-local correlations to the Tsirelson bound.展开更多
场景文本图像超分辨率(Scene Text Image Super-Resolution, STISR)旨在提高文本在低分辨率图像中的分辨率和可读性.但是在空间变形或低分辨率的文本图像中,由于缺乏文本区域细节,语义线索和视觉特征信息难以与字符位置匹配对齐,文本识...场景文本图像超分辨率(Scene Text Image Super-Resolution, STISR)旨在提高文本在低分辨率图像中的分辨率和可读性.但是在空间变形或低分辨率的文本图像中,由于缺乏文本区域细节,语义线索和视觉特征信息难以与字符位置匹配对齐,文本识别效果不佳.针对该问题,本文提出多域字符距离感知的场景文本图像超高分辨率重建方法(Perceiving Multi-Domain Character distance super-resolution, PMDC),强化视觉语义特征,提高文本区域和纹理信息.首先,采用非对称卷积以及语义先验信息模块,提取文本图像的视觉和语义特征信息;其次,融合字符距离感知模块中的视觉和语义特征,得到增强位置编码感知字符间的间距变化和语义相似性;最后,结合引导线索和视觉特征对像素进行重组得到超分辨率文本图像.在公开数据集TextZoom上的实验结果,与最近TATT文本超分网络性能相比,在峰值信噪比指标上提高0.11 dB,有效提高文本清晰度和边缘纹理细节,同时提升1.5%的平均识别准确率,改进文本图像的可读性.展开更多
二维条码作为一种能够存储大量信息的图形标识,在工业生产的自动化控制、物流管理、质量追溯以及运输的信息交换等环节起着非常重要的作用。二维条码的高精度识别是实现快速、准确信息交换的基础。但是受拍摄环境和拍摄设备精度的制约,...二维条码作为一种能够存储大量信息的图形标识,在工业生产的自动化控制、物流管理、质量追溯以及运输的信息交换等环节起着非常重要的作用。二维条码的高精度识别是实现快速、准确信息交换的基础。但是受拍摄环境和拍摄设备精度的制约,经常由于分辨率低而无法正确识别。针对此问题,提出了一种面向实际降质二维条码的超分辨率重建算法。考虑到实际降质的复杂性,提出了基于降质先验的超分辨率算法。首先,设计了一个降质先验信息编码器,用于提取和编码因拍摄环境和设备限制导致的图像质量降低的相关信息。然后,提出了一个降质先验引导模块,使用编码器提取的信息来引导主体结构的特征重建,包括降质特征图引导与降质先验引导两部分。由于目前缺少相关数据集,所以率先构建了真实退化条件下的二维条码超分辨率数据集(包含4944对低分辨率-高分辨率二维条码图像)。考虑到真实数据对之间有轻微位移,引入位移不敏感的损失函数对网络进行优化。实验表明,所提方法重建结果的峰值信噪比(Peak Signal to Noise Ratio,PSNR)、结构相似性(Structural Similarity,SSIM)以及扫出率这3种指标均优于5种经典的超分辨率重建算法,充分说明了所提方法的优越性。展开更多
基金Supported by Science and Technology Project of Anhui Province(No.1401b042009)the National Key Technology R&D Program(No.2013BAJ06B)
文摘The construction of high-filled loess project has some engineering and technical challenges, such as excavation of earth and backfilling of earth are both large, complex construction environment, variety of influence factors. According to this situation, this paper presents a dynamic 3D visualization method for high-filled project based on volume rendering. Through comparative analysis and visual analysis, realized at different times of the Loess fill internal detection data visualization and analysis presented. The results show that this visualization method can directly and accurately display the construction process, help decision makers master construction information and process.
文摘This paper proposes a necessary clarification about the problematic of super-quantum correlations, whose mainstream debate relies on an incorrect, statistical interpretation of the no-signaling condition. The no-signaling condition is an informational constraint that limits the strength of non-local correlations to the Tsirelson bound.
文摘二维条码作为一种能够存储大量信息的图形标识,在工业生产的自动化控制、物流管理、质量追溯以及运输的信息交换等环节起着非常重要的作用。二维条码的高精度识别是实现快速、准确信息交换的基础。但是受拍摄环境和拍摄设备精度的制约,经常由于分辨率低而无法正确识别。针对此问题,提出了一种面向实际降质二维条码的超分辨率重建算法。考虑到实际降质的复杂性,提出了基于降质先验的超分辨率算法。首先,设计了一个降质先验信息编码器,用于提取和编码因拍摄环境和设备限制导致的图像质量降低的相关信息。然后,提出了一个降质先验引导模块,使用编码器提取的信息来引导主体结构的特征重建,包括降质特征图引导与降质先验引导两部分。由于目前缺少相关数据集,所以率先构建了真实退化条件下的二维条码超分辨率数据集(包含4944对低分辨率-高分辨率二维条码图像)。考虑到真实数据对之间有轻微位移,引入位移不敏感的损失函数对网络进行优化。实验表明,所提方法重建结果的峰值信噪比(Peak Signal to Noise Ratio,PSNR)、结构相似性(Structural Similarity,SSIM)以及扫出率这3种指标均优于5种经典的超分辨率重建算法,充分说明了所提方法的优越性。