Determination of Horizontal Motion through Optical Flow Computations

For intelligent/autonomous subsea vehicles,reliable short-range horizontal positioning is difficult to achieve,particularly over flat bottom topography.A potential solution proposed in this paper utilized a passive optical sensing method to estimate the vehicle displacement using the bottom surface texture.The suggested optical flow method does not require any feature correspondences in images and it is robust in allowing brightness changes between image frames.Fundamentally,this method is similar to correlation methods attempting to match images and compute the motion disparity.However,in correlation methods,searching a neighbor region blindly for best match is lengthy.Main contributions of this paper come from the analysis showing that optical flow computation based on the general model cannot avoid errors except for null motion although the sign of optical flow keeps correct,and from the development of an iterative shifting method based on the error characteristics to accurately determine motions.Advantages of the proposed method are verified by real image experiments.     

A super-resolution method with EWA

This paper introduces a practical algorithm for super-resolution,the process of reconstructing a high-resolution image from low-resolution input ones.The emphasis of the work is to super-resolve frames from real-world image/video sequences which may contain significant object occlusion or scene changes.As the quality of super-resolved images highly relies on the correctness of image alignment between consecutive frames,the robust optical flow method is used to accurately estimate motion between the image pair.An efficient and reliable scheme is devised to detect and discard incorrect matchings which may degrade the output quality.The usage of elliptical weighted average (EWA) filter is also introduced to model the point spread function (PSF) of acquisition system in order to improve accuracy of the model.A number of complex video sequences are tested to demonstrate the applicability and reliability of the proposed algorithm.     

Fast adaptive wavelet for remote sensing image compression

Remote sensing images are hard to achieve high compression ratio because of their rich texture. By analyzing the influence of wavelet properties on image compression, this paper proposes wavelet construction rules and builds a new biorthogonal wavelet construction model with parameters. The model parameters are optimized by using genetic algorithm and adopting energy compaction as the optimization object function. In addition, in order to resolve the computation complexity problem of online construction, according to the image classification rule proposed in this paper we construct wavelets for different classes of images and implement the fast adaptive wavelet selection algorithm （FAWS）. Experimental results show wavelet bases of FAWS gain better compression performance than Daubechies9/7.     

高精度图像测量与对准系统的算法研究

In this paper a new high accuracy image measurement and registration system design is proposed, in which edges of image in pixel are detected by improved Canny operator, edge points are recorded by an auto-tracing algorithm, edges in sub-pixel are located by spatial moment-based operator. The object parameters are calculated by means of Least Squares and the accuracy is improved by a proposed algorithm. Finally an automatic detection,recognition and measurement algorithm is proposed. The simulation experiment on a standard circle shows the properties of validity, feasibility about the design and algorithm proposed.     

Spatially Adaptive Image Restoration Using Fuzzy Punctual Kriging

We present a general formulation based on punctual kriging and fuzzy concepts for image restoration in spatial domain. Gray-level images degraded with Gaussian white noise have been considered. Based on the pixel local neighborhood, fuzzy logic has been employed intelligently to avoid unnecessary estimation of a pixel. The intensity estimation of the selected pixels is then carried out by employing punctual kriging in conjunction with the method of Lagrange multipliers and estimates of local semi-variances. Application of such a hybrid technique performing both selection and intensity estimation of a pixel demonstrates substantial improvement in the image quality as compared to the adaptive Wiener filter and existing fuzzykriging approaches. It has been found that these filters achieve noise reduction without loss of structural detail information, as indicated by their higher structure similarity indices, peak signal to noise ratios and the new variogram based quality measures.     

A neural paradigm for time-varying motion segmentation

This paper proposes a new neural algorithm to perform the segmentation of an observed scene into regions corresponding to different moving objects by analyzing a time-varying images sequence.The method consists of a classification step,where the motion of small patches is characterized through an optimization approach,and a segmentation step merging meighboring patches characterized by the same motion.Classification of motion is performed without optical flow computation,but considering only the spatial and temporal image gradients into an appropriate energy function minimized with a Hopfield-like neural network giving as output directly the 3D motion parameter estimates.Network convergence is accelerated by integrating the quantitative estimation of motion parameters with a qualitative estimate of dominant motion using the geometric theory of differential equations.     

Super-Resolution Reconstruction of Image Sequence Using Multiple Motion Estimation Fusion

Super-resolution reconstruction algorithm produces a high-resolution image from a low-resolution image sequence. The accuracy and the stability of the motion estimation (ME) are essential for the whole restoration. In this paper, a new super-resolution reconstruction algorithm is developed using a robust ME method, which fuses multiple estimated motion vectors within the sequence. The new algorithm has two major improvements compared with the previous research. First, instead of only two frames, the whole sequence is used to obtain a more accurate and stable estimation of the motion vector of each frame; second, the reliability of the ME is quantitatively measured and introduced into the cost function of the reconstruction algorithm. The algorithm is applied to both synthetic and real sequences, and the results are presented in the paper.     

3D Image Synthesis for B-Reps Objects

This paper presents a new algorithm for generating 3D images of B-reps objects with trimmed surface boundaries.The 3D image is a discrete voxel-map representation within a Cubic Frame Buffer (CFB).The definition of 3D images for curve,surface and solid object are introduced which imply the connectivity and fidelity requirements.Adaptive Forward Differencing matrix (AFD-matrix) for 1D-3D manifolds in 3D space is developed.By setting rules to update the AFD-matrix,the forward difference direction and stepwise can be adjusted.Finally,an efficient algorithm is presented based on the AFD-matrix concept for converting the object in 3D space to 3D image in 3D discrete space.     

Blind Deblurring Based on L0Norm from Salient Edges简

Motion deblurring is a basic problem in the field of image processing and analysis. This paper proposes a new method of single image blind deblurring which can be significant to kernel estimation and non-blind deconvolution. Experiments show that the details of the image destroy the structure of the kernel, especially when the blur kernel is large. So we extract the image structure with salient edges by the method based on RTV. In addition, the traditional method for motion blur kernel estimation based on sparse priors is conducive to gain a sparse blur kernel. But these priors do not ensure the continuity of blur kernel and sometimes induce noisy estimated results. Therefore we propose the kernel refinement method based on L0 to overcome the above shortcomings. In terms of non-blind deconvolution we adopt the L1/L2 regularization term. Compared with the traditional method, the method based on L1/L2 norm has better adaptability to image structure, and the constructed energy functional can better describe the sharp image. For this model, an effective algorithm is presented based on alternating minimization algorithm.     

Preserving global features of fluid animation from a single image using video examples

We synthesize animations from a single image by transferring fluid motion of a video example globally.Given a target image of a fluid scene,an alpha matte is required to extract the fluid region.Our method needs to adjust a user-specified video example for producing the fluid motion suitable for the extracted fluid region.Employing the fluid video database,the flow field of the target image is obtained by warping the optical flow of a video frame that has a visually similar scene to the target image according to their scene correspondences,which assigns fluid orientation and speed automatically.Results show that our method is successful in preserving large fluid features in the synthesized animations.In comparison to existing approaches,it is both possible and useful to utilize our method to create flow animations with higher quality.     

基于TVGA正则化的室内运动模糊图像恢复

针对室内环境下相机曝光时间长,被摄目标相对相机运动会产生图像模糊的问题,以室内服务移动机器人为研究背景,提出了一种基于Topkis-Veinott梯度法(TVGA)正则化运动的模糊图像恢复方法。此算法首先采用方向导数法估计出运动模糊方向,同时将图像运动模糊方向旋转至水平轴;然后采用自相关函数平均法确定运动模糊长度,并算出运动模糊点扩展函数(PSF);最后采用改进的TVGA最优化正则参数,进而恢复原始图像。与经典的Wiener法和两种正则化恢复方法进行的比较结果表明,用TVGA法正则化恢复的图像效果较好,不仅较接近原始图像,且易于实现。     

倒谱和快速全变差去卷积的运动模糊图像复原

物体和成像系统之间的相对运动导致图像产生运动模糊,降低了图像质量,为了获得更加理想的复原图像,提出一种基于倒谱和快速全变差去卷积相结合的运动模糊图像复原算法。利用倒谱法对运动模糊图像的点扩散函数参数（模糊角度和模糊尺度）进行辩识,采用快速全变差去卷积法对模糊图像进行复原,采用多幅图像进行仿真实验测试算法的性能。仿真结果表明,相对于经典图像复原算法,该算法复原图像的主观视觉效果以及客观评价指标均更优,具有一定的实际利用价值。     

基于Radon变换的运动模糊图像恢复

提出了一种快速自然运动模糊图像恢复算法,采用一种新的基于Radon变换算法来确定模糊核函数;在确定模糊核函数后,对于模糊图像的恢复采用了一种改进的基于l1范数和l2范数混合保真项的变分图像恢复算法。实验结果表明,与Fergus的算法和Levinss的算法比较,所提算法对于一类线性运动占主要因素的强噪声模糊图像的恢复具有更快的速度和良好的恢复效果。     

林业运动模糊图像复原的融合正则化方法

林业机器人在林业环境中进行作业时,很容易因为滑动、地面障碍物的碰撞等原因发生小幅的无规律运动导致机器人相机采集的图像发生运动模糊,对后续图像信息提取造成很大的影响。针对这一问题,提出了林业运动模糊图像复原的融合正则化方法。先建立包含[L1/L2]范数正则项的代价函数,求解运动模糊核。再通过图像梯度先验正则项及稀疏正则项构建代价函数,对清晰图像求解。引入的[L1/L2]范数正则项及图像梯度先验正则项对稀疏表示正则项容易产生块效应的问题进行了弥补,因而获得了令人满意的效果。对人工合成的运动模糊图像和自然条件下真实运动模糊图像进行的实验验证了该算法的有效性。     

基于广义规范化稀疏模型的图像盲去模糊算法

针对基于规范化稀疏先验的图像盲去模糊方法估计精度低、计算速度慢、参数选择敏感等问题,提出一种Tikhonov正则增强的广义规范化稀疏模型,且将其作为中间清晰图像和运动模糊核的共同先验约束。随后,利用算子分裂、交替方向乘子法以及快速傅立叶变换,最小化关于中间清晰图像与运动模糊核的目标函数,导出一种快速图像盲去模糊算法。在标准测试集以及实际彩色模糊图像上的实验结果验证了提出方法的有效性和鲁棒性。此外,在同等条件下与近期文献中的盲去模糊方法进行比较,显示了本文方法在估计精度和估计效率上的双重优势。     

基于边缘模糊频谱特征的散焦参数估计方法

退化图像复原的关键在于点扩散函数(PSF)的准确估计,针对散焦模糊图像点扩散函数参数未知的情况,提出一种基于图像边缘模糊频谱特征的参数估计方法。首先分析基本边缘经模糊退化后的频谱特征,进而构建了自然图像的边缘模型作为参考图像,通过在连续的散焦值范围内计算与待测模糊图像频谱的最大相似性,以获取散焦参数估计值。实验结果表明,所提方法能够适用于大尺度模糊图像的参数估计问题,且具有较强的抗噪性能。     

基于多尺度网络的运动模糊图像复原算法

动态场景的非均匀盲去模糊一直是图像复原领域中的一个难题。针对目前的模糊图像复原算法不能很好地解决多样性模糊源的问题,提出了一种端到端的基于多尺度网络的运动模糊图像复原算法。所提算法使用修剪过的残差块作为基本单元,且在每一级尺度上都采用相同的非对称编解码网络。为了更好地提取输入图像特征,在编码端使用引入注意力机制的残差模块,还加入了空间金字塔池化层。编码端和解码端中间的循环单元可以获取图像的空间信息,从而利用图像空间的连续性来进行非均匀运动模糊图像的复原。测试结果显示,在GoPro数据集上所提算法的峰值信噪比（PSNR）达到33.69 dB,结构相似性（SSIM）达到0.953 7,且能够更好地复原模糊图像的细节信息,而在Blur数据集上所提算法的PSNR为31.47 dB,SSIM为0.904 7。实验结果表明,与尺度递归网络和深度层次化多patch网络相比,所提算法取得了更优的模糊图像复原效果。     

航空图像运动模糊的快速恢复

根据运动模糊图像的特点,建立了原始图像与模糊图像之间的关系,采用了一种快速图像复原的算法,实现了对图像的快速恢复,得到较好的效果。     

基于频域的运动模糊参数估计

运动模糊图像复原的关键之一是模糊核函数的估计,即降质图像的模糊方向和距离变化的估计。已经有多种方法用于模糊核函数的估计,通过对运动模糊图像频谱的研究,提出了一种基于形态学的模糊运动方向计算方法,并根据模糊图像频谱的黑色条纹周期出现的规律,采用投影法计算极值点,从而获取模糊运动距离。实验结果表明该算法简单有效,得到的运动模糊参数较准确。     

Recognition of camera-captured low-quality characters using motion blur information

Camera-based character recognition has gained attention with the growing use of camera-equipped portable devices. One of the most challenging problems in recognizing characters with hand-held cameras is that captured images undergo motion blur due to the vibration of the hand. Since it is difficult to remove the motion blur from small characters via image restoration, we propose a recognition method without de-blurring. The proposed method includes a generative learning method in the training step to simulate blurred images by controlling blur parameters. The method consists of two steps. The first step recognizes the blurred characters based on the subspace method, and the second one reclassifies structurally similar characters using blur parameters estimated from the camera motion. We have experimentally proved that the effective use of motion blur improves the recognition accuracy of camera-captured characters.