3D shape recovery from image focus using kernel regression in eigenspace

Shape from focus (SFF) is one of the optical passive methods for three dimensional (3D) shape recovery of an object from its two dimensional (2D) images. The focus measure plays important role in SFF algorithms. Mostly, conventional focus measures are based on gradient, so their performance is restricted under noisy conditions. Moreover, SFF methods also suffer from loss of focus information due to discreteness. This paper introduces a new SFF method based on principal component analysis (PCA) and kernel regression. The focus values are computed through PCA by considering a sequence of small 3D neighborhood for each object point. We apply unsupervised regression through Nadaraya and Watson Estimate (NWE) on depth values to get a refined 3D shape of the object. It reduces the effect of noise within a small surface area as well as approximates the accurate 3D shape by exploiting the depth dependencies in the neighborhood. Performance of the proposed scheme is investigated in the presence of different types of noises and textured areas. Experimental results demonstrate effectiveness of the proposed approach.     

Optimal depth estimation by combining focus measures using genetic programming

Three-dimensional (3D) shape reconstruction is a fundamental problem in machine vision applications. Shape From Focus (SFF) is one of the passive optical methods for 3D shape recovery that uses degree of focus as a cue to estimate 3D shape. In this approach, usually a single focus measure operator is applied to measure the focus quality of each pixel in the image sequence. However, the applicability of a single focus measure is limited to estimate accurately the depth map for diverse type of real objects. To address this problem, we develop Optimal Composite Depth (OCD) function through genetic programming (GP) for accurate depth estimation. The OCD function is constructed by optimally combining the primary information extracted using one/or more focus measures. The genetically developed composite function is then used to compute the optimal depth map of objects. The performance of the developed nonlinear function is investigated using both the synthetic and the real world image sequences. Experimental results demonstrate that the proposed estimator is more useful in computing accurate depth maps as compared to the existing SFF methods. Moreover, it is found that the heterogeneous function is more effective than homogeneous function.     

基于场景对象注意与深度图融合的深度估计

现有单目深度估计算法主要从单幅图像中获取立体信息,存在相邻深度边缘细节模糊、明显的对象缺失问题。提出一种基于场景对象注意机制与加权深度图融合的单目深度估计算法。通过特征矩阵相乘的方式计算特征图任意两个位置之间的相似特征向量,以快速捕获长距离依赖关系,增强用于估计相似深度区域的上下文信息,从而解决自然场景中对象深度信息不完整的问题。基于多尺度特征图融合的优点,设计加权深度图融合模块,为具有不同深度信息的多视觉粒度的深度图赋予不同的权值并进行融合,融合后的深度图包含深度信息和丰富的场景对象信息,有效地解决细节模糊问题。在KITTI数据集上的实验结果表明,该算法对目标图像预估时σ<1.25的准确率为0.879,绝对相对误差、平方相对误差和对数均方根误差分别为0.110、0.765和0.185,预测得到的深度图具有更加完整的场景对象轮廓和精确的深度信息。     

融合双目多维感知特征的立体视频显著性检测

目的 立体视频能提供身临其境的逼真感而越来越受到人们的喜爱,而视觉显著性检测可以自动预测、定位和挖掘重要视觉信息,可以帮助机器对海量多媒体信息进行有效筛选。为了提高立体视频中的显著区域检测性能,提出了一种融合双目多维感知特性的立体视频显著性检测模型。方法 从立体视频的空域、深度以及时域3个不同维度出发进行显著性计算。首先,基于图像的空间特征利用贝叶斯模型计算2D图像显著图;接着,根据双目感知特征获取立体视频图像的深度显著图;然后,利用Lucas-Kanade光流法计算帧间局部区域的运动特征,获取时域显著图;最后,将3种不同维度的显著图采用一种基于全局-区域差异度大小的融合方法进行相互融合,获得最终的立体视频显著区域分布模型。结果 在不同类型的立体视频序列中的实验结果表明,本文模型获得了80%的准确率和72%的召回率,且保持了相对较低的计算复杂度,优于现有的显著性检测模型。结论 本文的显著性检测模型能有效地获取立体视频中的显著区域,可应用于立体视频/图像编码、立体视频/图像质量评价等领域。     

Optimizing image focus for 3D shape recovery through genetic algorithm

Three-dimensional information of objects is advantageous and widely used in multimedia systems and applications. Shape form focus (SFF) is a passive optical technique that reconstructs 3D shape of an object using a sequence of images with varying focus settings. In this paper, we propose an optimization of the focus measure. First, Wiener filter is applied for noise reduction from the image sequence. At the second stage, genetic algorithm (GA) is applied for focus measure optimization. GA finds the maximum focus measurement under a fitness criterion. Finally, 3D shape of the object is determined by maximizing focus measure along the optical direction. The proposed method is tested with image sequences of simulated and real objects. The performance of the proposed technique is analyzed through statistical criteria such as root mean square error (RMSE) and correlation. Comparative analysis shows the effectiveness of the proposed method.     

Fast intra prediction algorithm based on texture analysis for 3D-HEVC encoders

The advances in display technologies and the growing popularity of 3D video systems have attracted more consumers for 3D viewing experiences, and, consequently, the demand for storage and transmission of 3D video content is increasing. To cope with this demand, a 3D video extension of high-efficiency video coding (HEVC) standard is being developed and near the final standardization stage. The upcoming 3D-HEVC standard is expected to provide higher encoding efficiency than its predecessors, supporting multiple views with high resolution, at a cost of considerable increase in computational complexity, which can be an obstacle to its use in real-time applications. This article proposes a novel complexity reduction algorithm developed to optimize the 3D-HEVC intra mode decision targeting real-time video processing for consumer devices with limited computational power, such as 3D camcorders and smartphones equipped with multiple cameras and depth acquisition capabilities. The proposed algorithm analyzes the texture frames and depth maps to estimate the orientation of edges present in the prediction unit data, speeding up the intra prediction process and reducing the 3D-HEVC encoding processing time. Experimental results demonstrate that the proposed algorithm can save 26 % in computational complexity on average with negligible loss of encoding efficiency. This solution contributes to make more feasible the compression of 3D videos targeting real-time applications in power-constrained devices.     

结合暗通道原理和双边滤波的遥感图像增强

目的 在遥感应用如目视解译等任务中,需要提高遥感影像的视觉质量,为此提出一种基于暗通道原理和双边滤波的遥感图像增强算法。方法 由于暗通道模型的softmatting过程计算复杂性高,故使用双边滤波估计大气光幕,进而获得优化透射图,代替He算法中softmatting过程,提高了计算效率。针对将暗通道原理应用于遥感图像增强时所产生的色彩失真现象,提出透射图的改进算法,提高景深图像的取值,同时约束其最大值不大于1。最后,基于景深图像和暗通道原理获得增强后的遥感图像。结果 实验结果表明,本文算法能够有效地增加图像的对比度。与基于双边滤波单尺度Retinex图像增强、四尺度Retinex增强、直方图均衡化及MSRCR增强的结果进行了比较,实验结果验证了算法的有效性。结论 本文模型能够使处理后的遥感图像更符合视觉特性,以便于目视解译与分析。该算法适用于遥感图像的可视化增强。     

采用空间聚类和平面或连通的彩色图像分割

提出了一种RGB空间聚类和平面区域生长相结合的彩色图像分割方法。聚类时采用重心和空间棋盘距离进行计算,主要为加法、减法运算;区域生长时提出了一种用或连通代替八邻域来判断连通性的新方法,主要为简单的二进制位运算。总体计算复杂度低,从而有效而且快速地实现了彩色图像的目标分割。     

Consideration of illumination effects and optimization of window size for accurate calculation of depth map for 3D shape recovery

Obtaining an accurate and precise depth map is the ultimate goal for 3D shape recovery. For depth map estimation, one of the most vital parts is the initial selection of the focus measure and processing the images with the selected focus measure. Although, many focus measures have been proposed in the literature but not much attention has been paid to the factors affecting those focus measures as well as the manner the images are processed with those focus measures. In this paper, for accurate calculation of depth map, we consider the effects of illumination on the depth map as well as the selection of the window size for application of the focus measures. The resulting depth map can further be used in techniques and algorithms leading to recovery of three-dimensional structure of the object which is required in many high-level vision applications. It is shown that the illumination effects can directly result in incorrect estimation of depth map if proper window size is not selected during focus measure computation. Further, it is shown that the images need some kind of pre-processing to enhance the dark regions and shadows in the image. For this purpose, an adaptive enhancement algorithm is proposed for pre-processing. In this paper, we prove that without such pre-processing for image enhancement and without the use of proper window size for the estimation of depth maps, it is not possible to obtain the accurate depth map.     

超分辨率图像复原中的快速L-曲线估计

讨论了从一组低采样降质的视频图像重建超分辨率图像中未知参数的估计问题．使用L-Curve标准来估计正则化参数，然而，L-Curve的计算代价十分昂贵．它需要计算正则化近似解和残差的范式．为此提出一种基于Lanczos算法和Gauss积分理论的算法，在超分辨率图像重建中的参数估计中可以减少L-Curve的计算代价．