Motion estimation and segmentation

In the general structure-from-motion (SFM) problem involving several moving objects in a scene, the essential first step is to segment moving objects independently. We attempt to deal with the problem of optical flow estimation and motion segmentation over a pair of images. We apply a mean field technique to determine optical flow and motion boundaries and present a deterministic algorithm. Since motion discontinuities represented by line process are embedded in the estimation of the optical flow, our algorithm provides accurate estimates of optical flow especially along motion boundaries and handles occlusion and multiple motions. We show that the proposed algorithm outperforms other well-known algorithms in terms of estimation accuracy and timing.     

On 3-D scene flow and structure recovery from multiview image sequences

Two novel systems computing dense three-dimensional (3-D) scene flow and structure from multiview image sequences are described in this paper. We do not assume rigidity of the scene motion, thus allowing for nonrigid motion in the scene. The first system, integrated model-based system (IMS), assumes that each small local image region is undergoing 3-D affine motion. Non-linear motion model fitting based on both optical flow constraints and stereo constraints is then carried out on each local region in order to simultaneously estimate 3-D motion correspondences and structure. The second system is based on extended gradient-based system (EGS), a natural extension of two-dimensional (2-D) optical flow computation. In this method, a new hierarchical rule-based stereo matching algorithm is first developed to estimate the initial disparity map. Different available constraints under a multiview camera setup are further investigated and utilized in the proposed motion estimation. We use image segmentation information to adopt and maintain the motion and depth discontinuities. Within the framework for EGS, we present two different formulations for 3-D scene flow and structure computation. One formulation assumes that initial disparity map is accurate, while the other does not. Experimental results on both synthetic and real imagery demonstrate the effectiveness of our 3-D motion and structure recovery schemes. Empirical comparison between IMS and EGS is also reported.     

Range map superresolution-inpainting,and reconstruction from sparse data

Range images often suffer from issues such as low resolution (LR) (for low-cost scanners) and presence of missing regions due to poor reflectivity, and occlusions. Another common problem (with high quality scanners) is that of long acquisition times. In this work, we propose two approaches to counter these shortcomings. Our first proposal which addresses the issues of low resolution as well as missing regions, is an integrated super-resolution (SR) and inpainting approach. We use multiple relatively-shifted LR range images, where the motion between the LR images serves as a cue for super-resolution. Our imaging model also accounts for missing regions to enable inpainting. Our framework models the high resolution (HR) range as a Markov random field (MRF), and uses inhomogeneous MRF priors to constrain the solution differently for inpainting and super-resolution. Our super-resolved and inpainted outputs show significant improvements over their LR/interpolated counterparts. Our second proposal addresses the issue of long acquisition times by facilitating reconstruction of range data from very sparse measurements. Our technique exploits a cue from segmentation of an optical image of the same scene, which constrains pixels in the same color segment to have similar range values. Our approach is able to reconstruct range images with as little as 10% data. We also study the performance of both the proposed approaches in a noisy scenario as well as in the presence of alignment errors.     

On the Spatial Statistics of Optical Flow

We present an analysis of the spatial and temporal statistics of “natural” optical flow fields and a novel flow algorithm that exploits their spatial statistics. Training flow fields are constructed using range images of natural scenes and 3D camera motions recovered from hand-held and car-mounted video sequences. A detailed analysis of optical flow statistics in natural scenes is presented and machine learning methods are developed to learn a Markov random field model of optical flow. The prior probability of a flow field is formulated as a Field-of-Experts model that captures the spatial statistics in overlapping patches and is trained using contrastive divergence. This new optical flow prior is compared with previous robust priors and is incorporated into a recent, accurate algorithm for dense optical flow computation. Experiments with natural and synthetic sequences illustrate how the learned optical flow prior quantitatively improves flow accuracy and how it captures the rich spatial structure found in natural scene motion.     

Detecting salient motion by accumulating directionally-consistentflow

Motion detection can play an important role in many vision tasks. Yet image motion can arise from “uninteresting” events as well as interesting ones. In this paper, salient motion is defined as motion that is likely to result from a typical surveillance target (e.g., a person or vehicle traveling with a sense of direction through a scene) as opposed to other distracting motions (e.g., the scintillation of specularities on water, the oscillation of vegetation in the wind). We propose an algorithm for detecting this salient motion that is based on intermediate-stage vision integration of optical flow. Empirical results are presented that illustrate the applicability of the proposed methods to real-world video. Unlike many motion detection schemes, no knowledge about expected object size or shape is necessary for rejecting the distracting motion     

Multi-View Scene Capture by Surfel Sampling: From Video Streams to Non-Rigid 3D Motion,Shape and Reflectance

In this paper we study the problem of recovering the 3D shape, reflectance, and non-rigid motion properties of a dynamic 3D scene. Because these properties are completely unknown and because the scene's shape and motion may be non-smooth, our approach uses multiple views to build a piecewise-continuous geometric and radiometric representation of the scene's trace in space-time. A basic primitive of this representation is the dynamic surfel, which (1) encodes the instantaneous local shape, reflectance, and motion of a small and bounded region in the scene, and (2) enables accurate prediction of the region's dynamic appearance under known illumination conditions. We show that complete surfel-based reconstructions can be created by repeatedly applying an algorithm called Surfel Sampling that combines sampling and parameter estimation to fit a single surfel to a small, bounded region of space-time. Experimental results with the Phong reflectancemodel and complex real scenes (clothing, shiny objects, skin) illustrate our method's ability to explain pixels and pixel variations in terms of their underlying causes—shape, reflectance, motion, illumination, and visibility.     

Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score

We present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences. Our method minimizes the prediction error of the shape and motion estimates. Both problems then translate into a generic image registration task. The latter is entrusted to a global measure of image similarity, chosen depending on imaging conditions and scene properties. Rather than integrating a matching measure computed independently at each surface point, our approach computes a global image-based matching score between the input images and the predicted images. The matching process fully handles projective distortion and partial occlusions. Neighborhood as well as global intensity information can be exploited to improve the robustness to appearance changes due to non-Lambertian materials and illumination changes, without any approximation of shape, motion or visibility. Moreover, our approach results in a simpler, more flexible, and more efficient implementation than in existing methods. The computation time on large datasets does not exceed thirty minutes on a standard workstation. Finally, our method is compliant with a hardware implementation with graphics processor units. Our stereovision algorithm yields very good results on a variety of datasets including specularities and translucency. We have successfully tested our motion estimation algorithm on a very challenging multi-view video sequence of a non-rigid scene. Electronic supplementary material Electronic supplementary material is available for this article at and accessible for authorised users.     

Scene segmentation from visual motion using global optimization

This paper presents results from computer experiments with an algorithm to perform scene disposition and motion segmentation from visual motion or optic flow. The maximum a posteriori (MAP) criterion is used to formulate what the best segmentation or interpretation of the scene should be, where the scene is assumed to be made up of some fixed number of moving planar surface patches. The Bayesian approach requires, first, specification of prior expectations for the optic flow field, which here is modeled as spatial and temporal Markov random fields; and, secondly, a way of measuring how well the segmentation predicts the measured flow field. The Markov random fields incorporate the physical constraints that objects and their images are probably spatially continuous, and that their images are likely to move quite smoothly across the image plane. To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used. The search for the globally optimal segmentation is performed using simulated annealing.     

Shape from Specular Reflection and Optical Flow

Inferring scene geometry from a sequence of camera images is one of the central problems in computer vision. While the overwhelming majority of related research focuses on diffuse surface models, there are cases when this is not a viable assumption: in many industrial applications, one has to deal with metal or coated surfaces exhibiting a strong specular behavior. We propose a novel and generalized constrained gradient descent method to determine the shape of a purely specular object from the reflection of a calibrated scene and additional data required to find a unique solution. This data is exemplarily provided by optical flow measurements obtained by small scale motion of the specular object, with camera and scene remaining stationary. We present a non-approximative general forward model to predict the optical flow of specular surfaces, covering rigid body motion as well as elastic deformation, and allowing for a characterization of problematic points. We demonstrate the applicability of our method by numerical experiments on synthetic and real data.     

Three-dimensional scene flow

Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only the normal flow can be computed directly from the image measurements, without some form of smoothing or regularization. In this paper, we begin by showing that the same fundamental limitation applies to scene flow; however, many cameras are used to image the scene. There are then two choices when computing scene flow: 1) perform the regularization in the images or 2) perform the regularization on the surface of the object in the scene. In this paper, we choose to compute scene flow using regularization in the images. We describe three algorithms, the first two for computing scene flow from optical flows and the third for constraining scene structure from the inconsistencies in multiple optical flows.     

Estimating optical flow in segmented images using variable-orderparametric models with local deformations

This paper presents a new model for estimating optical flow based on the motion of planar regions plus local deformations. The approach exploits brightness information to organize and constrain the interpretation of the motion by using segmented regions of piecewise smooth brightness to hypothesize planar regions in the scene. Parametric flow models are estimated in these regions in a two step process which first computes a coarse fit and then estimates the appropriate parametrization of the motion of the region. The initial fit is refined using a generalization of the standard area-based regression approaches. Since the assumption of planarity is likely to be violated, we allow local deformations from the planar assumption in the same spirit as physically-based approaches which model shape using coarse parametric models plus local deformations. This parametric plus deformation model exploits the strong constraints of parametric approaches while retaining the adaptive nature of regularization approaches. Experimental results on a variety of images model produces accurate flow estimates while the incorporation of brightness segmentation boundaries     

室内动态环境下基于网格分割与双地图耦合的RGB-D SLAM算法

为解决室内动态环境下现有RGB-D SLAM（同步定位与地图创建）系统定位精度低、建图效果差的问题,提出一种基于网格分割与双地图耦合的RGB-D SLAM算法。基于单应运动补偿与双向补偿光流法,根据几何连通性与深度图像聚类结果实现网格化运动分割,同时保证算法的快速性。利用静态区域内的特征点最小化重投影误差对相机进行位置估计。结合相机位姿、RGB-D图像、网格化运动分割图像,同时构建场景的稀疏点云地图和静态八叉树地图并进行耦合,在关键帧上使用基于网格分割和八叉树地图光线遍历的方法筛选静态地图点,更新稀疏点云地图,保障定位精度。公开数据集和实际动态场景中的实验结果都表明,本文算法能够有效提升室内动态场景中的相机位姿估计精度,实现场景静态八叉树地图的实时构建和更新。此外,本文算法能够实时运行在标准CPU硬件平台上,无需GPU等额外计算资源。     

The Shape Boltzmann Machine: A Strong Model of Object Shape

A good model of object shape is essential in applications such as segmentation, detection, inpainting and graphics. For example, when performing segmentation, local constraints on the shapes can help where object boundaries are noisy or unclear, and global constraints can resolve ambiguities where background clutter looks similar to parts of the objects. In general, the stronger the model of shape, the more performance is improved. In this paper, we use a type of deep Boltzmann machine (Salakhutdinov and Hinton, International Conference on Artificial Intelligence and Statistics, 2009) that we call a Shape Boltzmann Machine (SBM) for the task of modeling foreground/background (binary) and parts-based (categorical) shape images. We show that the SBM characterizes a strong model of shape, in that samples from the model look realistic and it can generalize to generate samples that differ from training examples. We find that the SBM learns distributions that are qualitatively and quantitatively better than existing models for this task.     

A Stochastic Approach for Blurred Image Restoration and Optical Flow Computation on Field Image Sequence

The blur in target images caused by camera vibration due to robot motion or hand shaking and by object(s) moving in the background scene is different to deal with in the computer vision system.In this paper,the authors study the relation model between motion and blur in the case of object motion existing in video image sequence,and work on a practical computation algorithm for both motion analysis and blut image restoration.Combining the general optical flow and stochastic process,the paper presents and approach by which the motion velocity can be calculated from blurred images.On the other hand,the blurred image can also be restored using the obtained motion information.For solving a problem with small motion limitation on the general optical flow computation,a multiresolution optical flow algoritm based on MAP estimation is proposed. For restoring the blurred image ,an iteration algorithm and the obtained motion velocity are used.The experiment shows that the proposed approach for both motion velocity computation and blurred image restoration works well.     

Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images

We address the problem of estimating the shape and appearance of a scene made of smooth Lambertian surfaces with piecewise smooth albedo. We allow the scene to have self-occlusions and multiple connected components. This class of surfaces is often used as an approximation of scenes populated by man-made objects. We assume we are given a number of images taken from different vantage points. Mathematically this problem can be posed as an extension of Mumford and Shah’s approach to static image segmentation to the segmentation of a function defined on a deforming surface. We propose an iterative procedure to minimize a global cost functional that combines geometric priors on both the shape of the scene and the boundary between smooth albedo regions. We carry out the numerical implementation in the level set framework.     

Revised definition of optical flow: integration of radiometric andgeometric cues for dynamic scene analysis

Optical flow has been commonly defined as the apparent motion of image brightness patterns in an image sequence. In this paper, we propose a revised definition to overcome shortcomings in interpreting optical flow merely as a geometric transformation field. The new definition is a complete representation of geometric and radiometric variations in dynamic imagery. We argue that this is more consistent with the common interpretation of optical flow induced by various scene events. This leads to a general framework for the investigation of problems in dynamic scene analysis, based on the integration and unified treatment of both geometric and radiometric cues in time-varying imagery. We discuss selected models, including the generalized dynamic image model, for the estimation of optical flow. We show how various 3D scene information are encoded in, and thus may be extracted from, the geometric and radiometric components of optical flow. We provide selected examples based on experiments with real images     

Vision and Rain

The visual effects of rain are complex. Rain produces sharp intensity changes in images and videos that can severely impair the performance of outdoor vision systems. In this paper, we provide a comprehensive analysis of the visual effects of rain and the various factors that affect it. Based on this analysis, we develop efficient algorithms for handling rain in computer vision as well as for photorealistic rendering of rain in computer graphics. We first develop a photometric model that describes the intensities produced by individual rain streaks and a dynamic model that captures the spatio-temporal properties of rain. Together, these models describe the complete visual appearance of rain. Using these models, we develop a simple and effective post-processing algorithm for detection and removal of rain from videos. We show that our algorithm can distinguish rain from complex motion of scene objects and other time-varying textures. We then extend our analysis by studying how various factors such as camera parameters, rain properties and scene brightness affect the appearance of rain. We show that the unique physical properties of rain—its small size, high velocity and spatial distribution—makes its visibility depend strongly on camera parameters. This dependence is used to reduce the visibility of rain during image acquisition by judiciously selecting camera parameters. Conversely, camera parameters can also be chosen to enhance the visibility of rain. This ability can be used to develop an inexpensive and portable camera-based rain gauge that provides instantaneous rain-rate measurements. Finally, we develop a rain streak appearance model that accounts for the rapid shape distortions (i.e. oscillations) that a raindrop undergoes as it falls. We show that modeling these distortions allows us to faithfully render the complex intensity patterns that are visible in the case of raindrops that are close to the camera.     

基于超像素和光流引导的正射影像拼接方法

影像拼接是生成大规模数字正射影像的关键技术之一,但现有的影像拼接方法在进行多个影像拼接时存在拼接线穿过明显地物导致的鬼影现象。光流是观察者和场景间相对运动引起的影像边缘等的相对运动,其中,大光流对应影像间的变化区域,可用于检测正射影像间的明显地面区域。提出一种基于光流引导的新型影像拼接方法,通过超像素的密集光流提取影像中明显的地物信息,以避免接缝穿过明显的地面物体。采用由粗到细的接缝线优化策略,并在超像素级别上利用Dijkstra算法进行最佳拼接区域检测,从而提高接缝线检测的效率。在此基础上,结合归一化互相关成本函数在像素级别上进行拼接线的像素级优化,获得最优的接缝线。实验结果表明,该方法从主观视觉上能够生成高质量的接缝线,在保证拼接效率的情况下,SSIM质量评价指标较Dijkstra方法、图割方法以及商业软件OrthoVista得到明显提高。     

Estimation of 3D Surface Shape and Smooth Radiance from 2D Images: A Level Set Approach

We cast the problem of shape reconstruction of a scene as the global region segmentation of a collection of calibrated images. We assume that the scene is composed of a number of smooth surfaces and a background, both of which support smooth Lambertian radiance functions. We formulate the problem in a variational framework, where the solution (both the shape and radiance of the scene) is a minimizer of a global cost functional which combines a geometric prior on shape, a smoothness prior on radiance and a data fitness score. We estimate the shape and radiance via an alternating minimization: The radiance is computed as the solutions of partial differential equations defined on the surface and the background. The shape is estimated using a gradient descent flow, which is implemented using the level set method. Our algorithm works for scenes with smooth radiances as well as fine homogeneous textures, which are known challenges to traditional stereo algorithms based on local correspondence.