基于图像的场景信息的估计与处理研究
文献类型:学位论文
作者 | 王颢星 |
学位类别 | 工学博士 |
答辩日期 | 2014-05-29 |
授予单位 | 中国科学院大学 |
授予地点 | 中国科学院自动化研究所 |
导师 | 张晓鹏 |
关键词 | 明暗图 反照率图 保边平滑处理 一致性分割 颜色纠正 shading image reflectance image edge-preserving smoothing consistent segmentation color correction |
其他题名 | On the Image based Scene Information Estimation and Processing |
学位专业 | 模式识别与智能系统 |
中文摘要 | 物体表面的颜色是由物体的形状、材质、光照环境以及观察者的位置等因素决定的。提取、处理、分析这些蕴藏在图像中的基本信息在计算机视觉与计算机图形学相关领域存在广阔的应用,是计算机视觉与计算机图形学研究的基本问题。本文围绕基于图像的形状、反照率、明暗信息以及颜色信息的提取与处理展开相关研究,研究的主要内容包括: 第一,本文提出一种基于单张图像与粗略几何数据的反照率、明暗图(shading image)的估计方法。本文方法利用形状约束、反照率约束与光照参数先验约束减少问题求解的不确定性。针对相关研究中出现的形状信息估计不准确的问题,本文方法通过使用粗略的几何观察数据以提高最终的形状评估结果的准确性。本文问题的能量函数的最终形式是非线性最小二乘问题,我们使用了适合求解大规模问题的Sparse Levenberg-Marquardt方法与由粗到精的优化策略对该问题进行求解,取得了较为稳定的估计结果。 第二,本文针对包含噪声的深度图数据提出了一种使用二阶平滑先验的保持边缘平滑处理方法。本文方法通过使用二阶平滑先验避免相关方法中出现的阶梯状平滑偏差。针对使用二阶平滑先验导致的边缘处过分平滑的问题,本文方法使用了离散0-1变量锋利地保持不连续区域。针对本文方法的连续变量与不连续变量的混合优化问题,我们使用了一种快速解法获取问题的近似解。我们在实验部分展示了本文方法在深度图像与普通图像保边平滑处理应用中的有效性。 第三,本文针对具有粗匹配关系的图像提出一种基于一致性分割的局部颜色纠正方法。本文方法通过一致性分割减弱图像匹配误差对颜色纠正造成的影响,通过使用与双边滤波近似的颜色影响权重避免分割块边缘处的不自然的颜色过渡效果。在实验部分,我们展示了本文方法的一致性分割结果与颜色纠正结果。 最后,对本文进行总结并指出进一步需要展开的工作。 |
英文摘要 | The observed colors of the object are influenced by many factors of the physical world, including the shape and material of the object, the illumination, the position of the viewer, etc. Estimating and processing the shape, color, reflectance and shading the observed image are a fundamental problem in computer vision and computer graphics. In this thesis, we proposed a model for intrinsic decomposition and discussed two related topics. The main contributions of this thesis are as follows: 1. We proposed an intrinsic decomposition method which used the single image and noisy shape observation data as the input data. This method can decompose the input data into the refined shape data, reflectance image and the shading image. As this problem is underconstrained, the shape smoothness constraint, reflectance smoothness constraint and the illumination prior are used to alleviate the ambiguity of the decomposition. Compared to the related work, our method can achieve more accurate shape estimation result by using the shape observation data. Our problem is a nonlinear least squares problem and solve it using sparse Levenberg-Marquardt algorithm and the coarse-to-fine optimization strategy. 2. We proposed an edge-preserving smoothing method for the depth map. This method uses the second order smoothness prior to avoid the staircase effect which exists in recent methods. It uses the binary line process variables to overcome the over-smoothing problem caused by the high order smoothness prior. Therefore, the salient edges can be sharply preserved. As the binary variables make the original problem hard to solve, a practical optimization strategy is used to achieve the approximate solution. We demonstrate the effectiveness of our method in the applications such as depth map smoothing, cartoon image denoising, non-photorealistic rendering and image detail magnification. 3. We proposed a consistent segmentation based local color correction method for coarsely registered images. A consistent segmentation method is proposed to alleviate the negative effect rising from inaccurate registration. The region confidences and the bilateral-filter-like color influence maps are used to improve the color correction result. The experiment shows the proposed method achieves improved color correction results compared with related work. Finally, the research results are summarized, and the future work is discussed. |
语种 | 中文 |
其他标识符 | 201018014628013 |
源URL | [http://ir.ia.ac.cn/handle/173211/6646] ![]() |
专题 | 毕业生_博士学位论文 |
推荐引用方式 GB/T 7714 | 王颢星. 基于图像的场景信息的估计与处理研究[D]. 中国科学院自动化研究所. 中国科学院大学. 2014. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。