目的受成像距离、光照条件、动态模糊等因素影响,监控系统拍摄的车牌图像往往并不具备较高的可辨识度。为改善成像质量,提升对车牌的识别能力,提出一种基于亮度与梯度联合约束的车牌图像超分辨率重建方法。方法首先充分结合亮度约束和...目的受成像距离、光照条件、动态模糊等因素影响,监控系统拍摄的车牌图像往往并不具备较高的可辨识度。为改善成像质量,提升对车牌的识别能力,提出一种基于亮度与梯度联合约束的车牌图像超分辨率重建方法。方法首先充分结合亮度约束和梯度约束的优势,实现对运动位移和模糊函数的精确估计;为抑制重建图像中的噪声与伪影,基于车牌图像的文字化特征,进一步确定了亮度与梯度联合约束的图像先验模型。结果为验证该方法的有效性,利用监控系统获得4组车牌图像,分别进行模拟和真实的超分辨率重建实验。在模拟实验中将联合约束图像先验重建结果与拉普拉斯、Huber-Markov(HMRF)以及总变分(TV)先验的处理结果进行对比,联合约束先验对车牌纹理信息的恢复效果优于其他3种常见图像先验;同时,在模拟和真实实验中,将本文算法与双三次插值、传统最大后验概率、非线性扩散正则化和自适应范数正则化方法的超分辨率重建结果进行比较,模拟实验的结果表明,在不添加噪声情况下,该算法峰值信噪比(PSNR)和结构相似性(SSIM)指标分别为35.326 d B和0.958,优于其他4种算法;该算法在真实实验中,能够有效增强车牌图像纹理信息,获得较优的视觉效果,通过对重建车牌图像的字符识别精度比较,本文算法重建结果的识别精度远高于其他3种算法,平均字符差距为1.3。结论模拟和真实图像序列的实验结果证明,基于亮度—梯度联合约束的超分辨率重建方法,能够降低运动和模糊等参数的估计误差,有效减少图像中存在的模糊和噪声,提高车牌的识别精度。该算法广泛适用于因光照变化、相对运动等因素影响下的低质量车牌图像超分辨率重建。展开更多
超声图像中的斑点噪声,降低图像分辨率和对比度,不利于后续图像处理.本文基于最大后验概率(Maximum A Posteriori,MAP)推导出一种新的超声图像分解算法,将原始超声图像分解为无散斑真实图像和散斑图像.使用六组不同的参数值,对Field II...超声图像中的斑点噪声,降低图像分辨率和对比度,不利于后续图像处理.本文基于最大后验概率(Maximum A Posteriori,MAP)推导出一种新的超声图像分解算法,将原始超声图像分解为无散斑真实图像和散斑图像.使用六组不同的参数值,对Field II仿真的超声图像进行分解试验,得出算法中比例参数对分解结果的影响规律.用该方法分解三幅人体超声图像,得到的真实图像平滑性好,且能较好的保留细节和边缘.本文提出的分解算法可用于超声图像的去噪,且分解得到的真实图像和散斑图像可用于特征提取、图像分割和图像分类等.展开更多
This paper presents a method for unsupervised segmentation of images consisting of multiple textures. The images under study are modeled by a proposed hierarchical random field model, which has two layers. The first l...This paper presents a method for unsupervised segmentation of images consisting of multiple textures. The images under study are modeled by a proposed hierarchical random field model, which has two layers. The first layer is modeled as a Markov Random Field (MRF) representing an unobservable region image and the second layer uses 'Filters, Random and Maximum Entropy (Abb. FRAME)' model to represent multiple textures which cover each region. Compared with the traditional Hierarchical Markov Random Field (HMRF), the FRAME can use a bigger neighborhood system and model more complex patterns. The segmentation problem is formulated as Maximum a Posteriori (MAP) estimation according to the Bayesian rule. The iterated conditional modes (ICM) algorithm is carried out to find the solution of the MAP estimation. An algorithm based on the local entropy rate is proposed to simplify the estimation of the parameters of MRF. The parameters of FRAME are estimated by the ExpectationMaximum (EM) algorithm. Finally, an experiment with synthesized and real images is given, which shows that the method can segment images with complex textures efficiently and is robust to noise.展开更多
Based on an extended Gauss-Markov model where the unknown parameters has the prior normal distribution, this paper derives the maximum posterior estimate formulas of the parameters which are proved to be unbiased,effi...Based on an extended Gauss-Markov model where the unknown parameters has the prior normal distribution, this paper derives the maximum posterior estimate formulas of the parameters which are proved to be unbiased,efficient, and of variance of unit weight which is biased. Finally, the marginal maximum posterior estimate formula of the variance with unbiased and efficient , properties is derived.展开更多
针对传统Unscented卡尔曼滤波器(Unscented Kalman filter,UKF)在噪声先验统计未知时变情况下非线性滤波精度下降甚至发散的问题,设计了一种带噪声统计估计器的自适应UKF滤波算法.首先根据极大后验(Maximum a posterior,MAP)估计原理,...针对传统Unscented卡尔曼滤波器(Unscented Kalman filter,UKF)在噪声先验统计未知时变情况下非线性滤波精度下降甚至发散的问题,设计了一种带噪声统计估计器的自适应UKF滤波算法.首先根据极大后验(Maximum a posterior,MAP)估计原理,推导出一种次优无偏MAP常值噪声统计估计器;接着在此基础之上,采用指数加权的方法,给出了时变噪声统计估计器的递推公式;最后对自适应UKF算法进行了性能分析.相比于传统UKF,该自适应UKF算法在噪声统计未知时变情况下不仅滤波依然收敛,滤波精度及稳定性显著提高,而且其具有应对噪声变化的自适应能力.仿真实例验证了其有效性.展开更多
文摘目的受成像距离、光照条件、动态模糊等因素影响,监控系统拍摄的车牌图像往往并不具备较高的可辨识度。为改善成像质量,提升对车牌的识别能力,提出一种基于亮度与梯度联合约束的车牌图像超分辨率重建方法。方法首先充分结合亮度约束和梯度约束的优势,实现对运动位移和模糊函数的精确估计;为抑制重建图像中的噪声与伪影,基于车牌图像的文字化特征,进一步确定了亮度与梯度联合约束的图像先验模型。结果为验证该方法的有效性,利用监控系统获得4组车牌图像,分别进行模拟和真实的超分辨率重建实验。在模拟实验中将联合约束图像先验重建结果与拉普拉斯、Huber-Markov(HMRF)以及总变分(TV)先验的处理结果进行对比,联合约束先验对车牌纹理信息的恢复效果优于其他3种常见图像先验;同时,在模拟和真实实验中,将本文算法与双三次插值、传统最大后验概率、非线性扩散正则化和自适应范数正则化方法的超分辨率重建结果进行比较,模拟实验的结果表明,在不添加噪声情况下,该算法峰值信噪比(PSNR)和结构相似性(SSIM)指标分别为35.326 d B和0.958,优于其他4种算法;该算法在真实实验中,能够有效增强车牌图像纹理信息,获得较优的视觉效果,通过对重建车牌图像的字符识别精度比较,本文算法重建结果的识别精度远高于其他3种算法,平均字符差距为1.3。结论模拟和真实图像序列的实验结果证明,基于亮度—梯度联合约束的超分辨率重建方法,能够降低运动和模糊等参数的估计误差,有效减少图像中存在的模糊和噪声,提高车牌的识别精度。该算法广泛适用于因光照变化、相对运动等因素影响下的低质量车牌图像超分辨率重建。
文摘超声图像中的斑点噪声,降低图像分辨率和对比度,不利于后续图像处理.本文基于最大后验概率(Maximum A Posteriori,MAP)推导出一种新的超声图像分解算法,将原始超声图像分解为无散斑真实图像和散斑图像.使用六组不同的参数值,对Field II仿真的超声图像进行分解试验,得出算法中比例参数对分解结果的影响规律.用该方法分解三幅人体超声图像,得到的真实图像平滑性好,且能较好的保留细节和边缘.本文提出的分解算法可用于超声图像的去噪,且分解得到的真实图像和散斑图像可用于特征提取、图像分割和图像分类等.
文摘This paper presents a method for unsupervised segmentation of images consisting of multiple textures. The images under study are modeled by a proposed hierarchical random field model, which has two layers. The first layer is modeled as a Markov Random Field (MRF) representing an unobservable region image and the second layer uses 'Filters, Random and Maximum Entropy (Abb. FRAME)' model to represent multiple textures which cover each region. Compared with the traditional Hierarchical Markov Random Field (HMRF), the FRAME can use a bigger neighborhood system and model more complex patterns. The segmentation problem is formulated as Maximum a Posteriori (MAP) estimation according to the Bayesian rule. The iterated conditional modes (ICM) algorithm is carried out to find the solution of the MAP estimation. An algorithm based on the local entropy rate is proposed to simplify the estimation of the parameters of MRF. The parameters of FRAME are estimated by the ExpectationMaximum (EM) algorithm. Finally, an experiment with synthesized and real images is given, which shows that the method can segment images with complex textures efficiently and is robust to noise.
文摘Based on an extended Gauss-Markov model where the unknown parameters has the prior normal distribution, this paper derives the maximum posterior estimate formulas of the parameters which are proved to be unbiased,efficient, and of variance of unit weight which is biased. Finally, the marginal maximum posterior estimate formula of the variance with unbiased and efficient , properties is derived.
文摘针对传统Unscented卡尔曼滤波器(Unscented Kalman filter,UKF)在噪声先验统计未知时变情况下非线性滤波精度下降甚至发散的问题,设计了一种带噪声统计估计器的自适应UKF滤波算法.首先根据极大后验(Maximum a posterior,MAP)估计原理,推导出一种次优无偏MAP常值噪声统计估计器;接着在此基础之上,采用指数加权的方法,给出了时变噪声统计估计器的递推公式;最后对自适应UKF算法进行了性能分析.相比于传统UKF,该自适应UKF算法在噪声统计未知时变情况下不仅滤波依然收敛,滤波精度及稳定性显著提高,而且其具有应对噪声变化的自适应能力.仿真实例验证了其有效性.
