CASIA OpenIR  > 毕业生  > 博士学位论文
基于局部感知的若干视觉问题研究
Alternative TitleResearches on Some Vision Problem Based on Local Perception
汪凌峰
Subtype工学博士
Thesis Advisor潘春洪
2013-05-27
Degree Grantor中国科学院大学
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword局部感知 视觉目标跟踪 图像超分辨率 水平集 医学图像分割 背景建模 Local Perception Visual Target Tracking Image Super-resolution Level-set Medical Image Segmentation Background Subtraction
Abstract随着计算机软硬件的发展以及相关学科,如:模式识别、图像处理和计算机图形学等的逐步成熟,计算机视觉的发展也如火如荼,已成为目前的研究热点。近年来,研究人员提出了大量的计算机视觉问题,并对其作了深入地研究。对于多数视觉问题,由于其自身的复杂性,往往难以用全局模型对其进行表示。因此,将问题局部化,即:引入局部感知,能更灵活地并有效地解决视觉问题。本文将局部化思想应用于若干视觉问题,并由此提出多种基于局部感知的算法。论文的主要贡献如下: 1. 提出了基于局部背景感知的视觉目标跟踪算法。首先,跟踪算法将目标的局部背景看作上下文,将其引入目标表达。由此,提出了一种新的目标描述:局部背景加权直方图。局部背景加权直方图增强目标与背景的鉴别性,从而突出目标区域内的前景信息。因此,提出的跟踪算法可以有效地处理目标与背景相似且背景多变的难题。其次,提出了新的前向后向检验策略以及前向后向均值飘移算法。在前向后向检验策略中,跟踪结果由前向后向误差决定。由此,可以有效地解决目标短时间遮挡及跟踪环境光照变化问题。在大量跟踪场景中实验表明,提出的算法在跟踪精度上要优于主流跟踪算法。 2. 提出了基于局部梯度模自适应插值边缘指导的单幅图像超分辨率算法。局部梯度模自适应插值本质上是利用梯度场的局部信息来自适应的锐化梯度。首先,利用局部梯度模自适应插值从低分辨率图像中直接估计锐化的高分辨率梯度。而后,将估计的高分辨率梯度作为(边缘保持的)梯度约束用于基于重建的超分辨率算法。大量实验表明,较主流的超分辨率方法,提出的算法在定性和定量两方面取得了令人满意的结果。同时,在时间上较其他基于梯度的算法提高了近3倍,较基于学习的算法提高近10倍。 3. 在贝叶斯估计框架下,提出了两个基于局部模型的水平集医学图像分割算法。首先,提出了一种新的局部序模型。该模型可以加强局部前景和背景聚类中心的约束,从而使分割的全局一致性得以保持。对比实验表明,提出的方法可以解决局部二值拟合(Local Binary Fitting; LBF)模型初始化敏感和存在明显分割错误的问题。其次,将图像生成模型引入图像分割,由此,可将分割和偏置矫正在统一的模型下求解。进一步,为使分割过程更加稳定,提出了一种新的图像指导的正则。该正则通过局部学习(局部线性回归)将图像的相似性传递到水平集函数上。实验表明,较主流算法,提出的算法在分割精度和偏置校正方面均有改进。 4. 提出了基于自适应阈值局部二值模式(Local Binary Pattern; LBP)的背景建模算法。首先,提出了一种新的自适应阈值局部二值模式。在计算阈值时,首先将图像内所有像素分为两类,即:边缘像素和纹理像素,而后,对两类像素分别使用不同的阈值计算策略,从而实现自适应阈值选取。其次,基于朴素贝叶斯技术,将自适应阈值局部二值模式应用于背景建模。实验表明,提出的背景建模算法能适用于大量复杂的场景,尤其是光照变化的场景;并且,相对于主流算法,提出的算法运算复杂度更低。
Other AbstractWith the development of computer hardware and software, and the gradually maturity of related disciplines, such as pattern recognition, image processing and computer graphics, the development of computer vision is also in full swing, and becomes the current research focus. In recent year, a large number of computer vision problems have been proposed and deeply studied by researches. For many vision problems, due to their complexities, it is difficulty to utilize a global model to represent them. Hence, it is more flexibly and effectively to address vision problems by considering them locally, that is, introducing local perception. In this thesis, we apply the localization idea to some vision problems, and correspondingly propose some local perception based algorithms. The main contributions of the thesis are listed as follows: 1. We propose a local background-aware visual tracking algorithm. First, the proposed tracking algorithm treats local background as the context, and introduces it into target representation. As a result, we propose a target description, i.e. the local background weighted histogram (LBWH). The LBWH enhances the discrimination between target and background, so that highlights the foreground in the target region. Hence, the proposed tracking algorithm can effectively tackle the difficulties of the similarity between target and background as well as the variability of the potential background. Second, we propose a forward-backward mean-shift (FBMS) algorithm is proposed by incorporating a forward-backward evaluation scheme, in which the tracking result is determined by the forward-backward error. Therefore, the proposed algorithm can effectively solve short-time partial occlusion and illumination variation problems. Extensive experiments on various scenarios have demonstrated that our tracking algorithm outperforms the state-of-the-art approaches in tracking accuracy. 2.We propose an edge-directed single image super-resolution method based on a local gradient magnitude adaptive self-interpolation (LGMASI) algorithm. Essentially, the LGMASI algorithm utilizes the local gradient information to adaptively sharpen the gradient. An adaptive self-interpolation algorithm is first applied to estimate a sharp high-resolution gradient field directly from the input low-resolution image. The obtained high-resolution gradient is then regarded as a gradient constraint or an edge-preserving constraint to reconstruct the high-resolution image. Exte...
shelfnumXWLW1873
Other Identifier201018014628060
Language中文
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/6521
Collection毕业生_博士学位论文
Recommended Citation
GB/T 7714
汪凌峰. 基于局部感知的若干视觉问题研究[D]. 中国科学院自动化研究所. 中国科学院大学,2013.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20101801462806(9138KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[汪凌峰]'s Articles
Baidu academic
Similar articles in Baidu academic
[汪凌峰]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[汪凌峰]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.