变权无参考视频质量评价模型研究

传输信道失真是导致视频图像质量损失的重要原因,而不需要任何附加传输信息的无参考客观评价是监测视频传输质量受损的主要方法。为了提高无参考客观评价模型的准确性和效率,提出模拟人类视觉特性的变权评价模型。变权评价模型综合考虑视频的空域和时域两类质量指标,引入运动强度来量化视频内容中的运动变化程度,根据统计学习的非线性回归法建立变权控制函数;通过变权控制函数动态调整清晰度和平滑度权值来模仿人类视觉特性。实验结果表明该变权评价模型与主观评价符合度高,优于现有评价方案。

一种针对高斯模糊图像的无参质量评价方法

针对模糊图像高频分量的特性,提出了一种针对高斯模糊图像的无参质量评价方法。该方法利用小波变换对模糊图像提取高频分量,在高频分量功率谱上构造评价指标。实验结果表明提出的评价指标优于PSNR和SSIM,其客观评价分数与主观评价分数具有更好的一致性。

非主观值训练的盲视频质量评价算法

针对现有基于机器学习的无参考视频质量评价方法中需要利用大量主观评价分值进行训练,导致复杂度高的问题,提出一种非主观值训练的盲视频质量评价算法.首先,利用高斯差分滤波器提取视频结构特征矢量,通过计算与质量感知中心的距离,来评估视频空域感知质量;然后,利用聚类算法获取对运动矢量进行分类的阈值,进而得到运动感知因子;最后,结合视频空域感知质量和运动加权因子得到视频客观质量.实验结果表明:该算法在LIVE video quality数据库中对视频质量预测的单调性和精确性分别达到了0.817,7和0.828,5,优于对比的其他盲视频质量评价算法;同时,该算法计算复杂度低,易于实现.

NR-IQA模型的人类视觉系统补偿方法

在暗视觉环境下,人类视觉对比度分辨率非常低。针对低照度图像,提出一种基于无参图像质量评价体系的补偿方法(NR-IQA)。首先,建立一种用于提取视觉评价参数的数学模型。其次,建立最好图像质量评价综合函数,用于评价图像补偿的质量。然后,计算评价函数和补偿因子k的数学关系。这种自动寻优方法用于迅速获取暗视觉下的最佳图像质量,特别是在视频图像处理中的实时补偿。

基于图像评价的显微镜自动对焦方法

针对显微镜观测动态平面目标时的自动对焦需求,提出一种基于图像清晰度评价的显微镜静/动态自动对焦方法。首先,根据对聚焦-失焦图像特征的分析,建立加权Tenengrad评价函数评估方法和图像分块对焦窗口模式。其次,针对搜索过程中的局部极大值问题,利用模拟退火理论建立对焦搜索模型。最后,为了对动态图像进行评价,利用图像模糊法来判断动态无参考图像失焦水平。在此基础上,形成了静态调焦模型,动态失焦检测与实时对焦模型。通过搭建显微镜自动对焦实验平台,结果表明:该静态调焦模型能够使显微镜快速准确地静态自动调焦,动态失焦检测和实时对焦模型能够使显微镜满足在动态观测下离焦检测和实时调焦的要求。

No-reference blur assessment method based on gradient and saliency

To evaluate the quality of blurred images effectively,this study proposes a no-reference blur assessment method based on gradient distortion measurement and salient region maps.First,a Gaussian low-pass filter is used to construct a reference image by blurring a given image.Gradient similarity is included to obtain the gradient distortion measurement map,which can finely reflect the smallest possible changes in textures and details.Second,a saliency model is utilized to calculate image saliency.Specifically,an adaptive method is used to calculate the specific salient threshold of the blurred image,and the blurred image is binarized to yield the salient region map.Block-wise visual saliency serves as the weight to obtain the final image quality.Experimental results based on the image and video engineering database,categorial image quality database,and camera image database demonstrate that the proposed method correlates well with human judgment.Its computational complexity is also relatively low.

Wireless Channel Parameter Estimation Algorithms: Recent Advances and Future Challenges

Temporal and three-dimensional(3 D) spatial information is important for the characterization of wireless channels. In this paper, the commonly used array signal processing(ASP) methods to estimate channel parameters are summarized. Firstly, algorithms that can be used to estimate azimuth angle of arrival(AAo A) and elevation Ao A(EAo A) are introduced. They include multiple signal classification(MUSIC), estimation of signal parameter via rotational invariance techniques(ESPRIT), and Unitary ESPRIT algorithms. Secondly, algorithms that can be used to jointly estimate delay, AAo A, and EAo A are given. They include joint angle and delay estimation(JADE) MUSIC, JADE ESPRIT, shift-invariance(SI) JADE, and space-alternating generalized expectation-maximization(SAGE) algorithms. We also propose an improved SIJADE algorithm to further reduce computation complexity by incorporating with the Unitary ESPRIT algorithm. Performance of the above algorithms to extract only spatial information and to jointly extract temporal and spatial information is compared in both synthetic and 60 GHz real channel environments. Simulation results show that with the inclusion of delay estimation, the joint temporal and spatial estimation algorithms can provide better resolution than algorithms estimating only angles.Measurement data processing results show that MUSIC algorithm can provide comparable results with SAGE algorithm in estimating AAoA and EAoA. SI-JADE and the improved SI-JADE algorithms are also applicable to process 60 GHz channel measurement data.However, MUSIC, SI-JADE, and the improved SI-JADE algorithms can greatly reduce computational burden compared with SAGE algorithm. At last, some future directions are pointed out.

底层图像挖掘技术中的参数自动寻优

研究了基于人类视觉对比度分辨率限制的底层图像挖掘技术中挖掘参数的自动寻优问题。在用Zadeh-X变换进行底层图像挖掘中,需要求得最佳挖掘参数Sita和Delta。首先筛选出与图像视觉感知质量相关的客观物理质量指标体系:信息熵和平均对比度。其次研究信息熵和平均对比度与图像挖掘参数的函数关系,然后研究其函数特性与主观评价结果的关系,以此建立以信息熵和平均对比度为基础的无参考图像质量评价函数,通过视觉质量最佳图像判据,寻求最佳质量图像所对应的Sita和Delta,从而实现挖掘参数的自动寻优。