Recognition Using Region Correspondences

Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estimation. This is the problem of using a correspondence between some portions of an object model and some portions of an image to determine whether the image contains an instance of the object, and, in case it does, to determine the transformation that relates the model to the image. The current approaches to this problem are divided into methods that use global properties of the object (e.g., centroid and moments of inertia) and methods that use local properties of the object (e.g., corners and line segments). Global properties are sensitive to occlusion and, specifically, to self occlusion. Local properties are difficult to locate reliably, and their matching involves intensive computation.We present a novel method for recognition that uses region information. In our approach the model and the image are divided into regions. Given a match between subsets of regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3-D objects undergoing affine and projective transformations. The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls. Like the global methods, our approach makes use of region information that reflects the true shape of the object. But like local methods, our approach can handle occlusion.     

Estimating pose of articulated objects using low-level motion

In this work a method is presented to track and estimate pose of articulated objects using the motion of a sparse set of moving features. This is achieved by using a bottom-up generative approach based on the Pictorial Structures representation [1]. However, unlike previous approaches that rely on appearance, our method is entirely dependent on motion. Initial low-level part detection is based on how a region moves as opposed to its appearance. This work is best described as Pictorial Structures using motion. A standard feature tracker is used to automatically extract a sparse set of features. These features typically contain many tracking errors, however, the presented approach is able to overcome both this and their sparsity. The proposed method is applied to two problems: 2D pose estimation of articulated objects walking side onto the camera and 3D pose estimation of humans walking and jogging at arbitrary orientations to the camera. In each domain quantitative results are reported that improve on state of the art. The motivation of this work is to illustrate the information present in low-level motion that can be exploited for the task of pose estimation.     

基于少量特征点的多模态人脸识别

针对二维人脸识别对姿态和光照变化较为敏感的问题,提出了一种基于少量特征点的多模态人脸识别方法。在训练阶段,对三维人脸数据进行二次处理和数据挖掘,为建立完备的特征模板奠定了基础;提出了一种简洁高效的样本聚类方法,克服了特征提取过程中的非线性问题;通过局部特征分析(Local Feature Analysis,LFA)实现了特征点"局部"与"全局"信息的融合。实验证明该方法在具有较高执行效率的同时,对人脸图像的姿态和光照变化具有理想的鲁棒性,在WHU-3D小规模人脸数据库上取得了98.06%的识别率。     

Modeling and computing ternary projective relations between regions

Current spatial database systems offer limited querying capabilities beyond binary topological relations. This paper introduces a model for projective relations between regions to support other qualitative spatial queries. The relations are ternary because they are based on the collinearity invariant of three points under projective geometry. The model is built on a partition of the plane into separate zones that are obtained from projective properties of two reference objects: then, by considering the empty/nonempty intersections of a primary object with these zones, the model is able to distinguish between 34 different projective relations. Then, the paper proposes original algorithms for computing the relations under the assumption that regions of the plane are stored as vector polygons in a spatial database. These algorithms run in optimal O(nlogn) time.     

Dynamic obstacle identification based on global and local features for a driver assistance system

This paper proposes a novel dynamic obstacle recognition system combining global feature with local feature to identify vehicles, pedestrians and unknown backgrounds for a driver assistance system. The proposed system consists of two main procedures: a dynamic obstacle detection model to localize an area containing a moving obstacle, and an obstacle identification model, which is a hybrid of global and local information, for recognizing an obstacle with and without occlusion. A dynamic saliency map is used for localizing an area containing a moving obstacle. For the global feature analysis, we propose a modified GIST using orientation features with MAX pooling, which is robust to translation and size variations of an object. Although the global features are a compact way to represent an object and provide a good accuracy for non-occluded objects, they are sensitive to image translation and occlusion. Thus, a local feature-based identification model is also proposed and combined with the global feature. As such, for the obstacle identification problem, the proposed system mainly follows the global feature-based object identification. If the global feature-based model identifies a candidate area as background, the system verifies the area again using the local feature-based model. As a result, the proposed system is able to provide information on both the appearance of obstacles and the class of an obstacle. Experimental results show that the proposed model can successfully detect obstacle candidates and robustly identify obstacles with and without occlusion.     

遮挡情况下刚体位姿估计的自适应无迹卡尔曼分布式融合

针对视觉目标位姿估计系统中常出现的因为特征点遮挡而造成系统估计结果不准确的问题,本文提出了一种利用自适应无迹卡尔曼滤波(AUKF)作为局部滤波器的分布式融合估计方法.通过引入改进的Sage-Husa噪声估计器自适应过程噪声.根据特征点识别量将遮挡情况分为部分遮挡和严重遮挡,对部分遮挡子系统根据先验信息修复缺失观测点后进行局部滤波估计,严重遮挡子系统不参与融合,利用当前时刻整体估计结果对其进行初始化.通过仿真获取了区分遮挡情况的阈值,实验结果表明所提方法能够提升系统在遮挡情况下的估计精度与鲁棒性.     

基于共面圆的距离传感器与相机的相对位姿标定

近年来, 距离传感器与摄像机的组合系统标定在无人车环境感知中得到了广泛的研究与应用, 其中基于平面特征的方法简单易行而被广泛采用. 然而, 目前多数方法基于点匹配进行, 易错且鲁棒性较低. 本文提出了一种基于共面圆的距离传感器与相机的组合系统相对位姿估计方法. 该方法使用含有两个共面圆的标定板, 可以获取相机与标定板间的位姿, 以及距离传感器与标定板间的位姿. 此外, 移动标定板获取多组数据, 根据计算得到两个共面圆的圆心在距离传感器和相机下的坐标, 优化重投影误差与3D对应点之间的误差, 得到距离传感器与相机之间的位姿关系. 该方法不需要进行特征点的匹配, 利用射影不变性来获取相机与三维距离传感器的位姿. 仿真实验与真实数据实验结果表明, 本方法对噪声有较强的鲁棒性, 得到了精确的结果.     

Robust face alignment and tracking by combining local search and global fitting

When a face in an image is considerably occluded, existing local search and global fitting methods often cannot find the facial features due to failures in the local facial feature detectors or the fitting limitations of appearance modeling. To solve these problems, we propose a new face alignment method that combines the local search and global fitting methods, where local misalignments in the local search method are restricted by holistic appearance fitting in the global fitting method and the divergent or shrinking alignments in the global fitting method are avoided by the restricting local movements in the local search method. The proposed alignment method consists of two stages: the initialization stage detects the face, estimates the facial pose and obtains the initial facial features by locating a pose-specific mean shape on the detected face; the optimization stage then obtains the facial features by updating the parameter set from the combined Hessian matrix and the combined gradient vector. We also extend the proposed face alignment to face tracking by adding a template image that is warped from the facial features obtained in the previous frame. In the experiments, the proposed method yields more accurate and stable face alignment or tracking under heavy occlusion and pose variation than the existing methods.     

Multiple people tracking and pose estimation with occlusion estimation

Simultaneously tracking poses of multiple people is a difficult problem because of inter-person occlusions and self occlusions. This paper presents an approach that circumvents this problem by performing tracking based on observations from multiple wide-baseline cameras. The proposed global occlusion estimation approach can deal with severe inter-person occlusions in one or more views by exploiting information from other views. Image features from non-occluded views are given more weight than image features from occluded views. Self occlusion is handled by local occlusion estimation. The local occlusion estimation is used to update the image likelihood function by sorting body parts as a function of distance to the cameras. The combination of the global and the local occlusion estimation leads to accurate tracking results at much lower computational costs. We evaluate the performance of our approach on a pose estimation data set in which inter-person and self occlusions are present. The results of our experiments show that our approach is able to robustly track multiple people during large movement with severe inter-person occlusions and self occlusions, whilst maintaining near real-time performance.     

Outlier correction from uncalibrated image sequence using the Triangulation method

We propose a robust algorithm for estimating the projective reconstruction from image features using the RANSAC-based Triangulation method. In this method, we select input points randomly, separate the input points into inliers and outliers by computing their reprojection error, and correct the outliers so that they can become inliers. The reprojection error and correcting outliers are computed using the Triangulation method. After correcting the outliers, we can reliably recover projective motion and structure using the projective factorization method. Experimental results showed that errors can be reduced significantly compared to the previous research as a result of robustly estimated projective reconstruction.     

Real-time markerless tracking for augmented reality: the virtual visual servoing framework

Tracking is a very important research subject in a real-time augmented reality context. The main requirements for trackers are high accuracy and little latency at a reasonable cost. In order to address these issues, a real-time, robust, and efficient 3D model-based tracking algorithm is proposed for a "video see through" monocular vision system. The tracking of objects in the scene amounts to calculating the pose between the camera and the objects. Virtual objects can then be projected into the scene using the pose. In this paper, nonlinear pose estimation is formulated by means of a virtual visual servoing approach. In this context, the derivation of point-to-curves interaction matrices are given for different 3D geometrical primitives including straight lines, circles, cylinders, and spheres. A local moving edges tracker is used in order to provide real-time tracking of points normal to the object contours. Robustness is obtained by integrating an M-estimator into the visual control law via an iteratively reweighted least squares implementation. This approach is then extended to address the 3D model-free augmented reality problem. The method presented in this paper has been validated on several complex image sequences including outdoor environments. Results show the method to be robust to occlusion, changes in illumination, and mistracking.     

Integrated Matching and Segmentation of Multiple Features in Two Views

We present an integrated method to match multiple features including points, regions, and lines in two perspective images, and simultaneously segment them such that all features in each segment have the same 3D motion. The method uses local affine (first-order) approximation of the displacement field under the assumption of locally rigid motion. Each distinct motion is represented in the image plane by a distinct set of values for six displacement parameters. To compute the values of these parameters, the 6D space is split into two 3D spaces, and each is exhaustively searched coarse-to-fine. This yields two results simultaneously, correspondences between features and segmentation of features into subsets corresponding to locally rigid patches of moving objects. Since matching is based on the 2D approximation of 3D motion, problems due to motion or object boundaries and occlusion can be avoided. Large motion is also handled in a manner unlike the methods based on flow field. Integrated use of the multiple features not only gives a larger number of features (overconstrained system) but also reduces the number of candidate matches for the features, thus making matching less ambiguous. Experimental results are presented for four pairs of real images.     

结合全局与局部信息的点云目标识别模型库构建

目的 点云目标识别流程分为离线与在线阶段。离线阶段基于待识别目标的CAD模型构建一个模型库,在线基于近邻查找完成识别。本文针对离线阶段,提出一种新的模型库构建方法。方法 首先将CAD模型置于一个二十面体中心,使用多个虚拟相机获取CAD模型在不同视角下的点云;然后将每个不同视角下的点云进行主成分分析并基于主成分分析的结果从多个选定的方向将点云切分为多个子部分,这些子部分包含点云的全局及局部信息;接着对每个子部分使用聚类算法获取其最大聚类,去除离群点;最后结合多种方式删减一些冗余聚类,减小模型库规模。结果 在多个公开数据集上使用多种点云描述子进行对比实验,识别结果表明,相对于传统的模型库构建方法,基于本文方法进行识别正确率更高,在某些点云描述子上的识别正确率提升达到10%以上。结论 通过将CAD模型在不同视角下点云的全局与局部信息都加入模型库中,本文提出的模型库构建方法可有效提高点云目标识别正确率,改善了场景目标发生遮挡时,近邻查找识别精度不高的问题。     

多物体遮挡情况下的视觉跟踪算法

针对视频监控中多运动物体间的遮挡问题,提出一种结合全局特征匹配与局部特征匹配的目标跟踪算法.该算法采用基于直方图和基于分块的方法共同表达目标的灰度特征.遮挡发生前实时进行遮挡预判,遮挡时采用基于块分类的方法跟踪目标,遮挡结束后通过直方图匹配重新定位目标.实验结果表明了该方法的有效性和优越性.     

On Rational Geometry of Conic Sections

Simple geometric objects and transformations appear in representations and algorithms of geometric facilities in computer applications such as modelling, robotics, or graphics. Usually, these applications only support objects and transformations fully describable by rational parameters, and a computer display of points of the objects at least implicitly requires points with rational coordinates. In this setting we investigate some basic questions of the geometry of rational conic sections, when the geometry is defined by the group of rational projective transformations, the group of rational affine transformations, or the group of rational rigid transformations. Some results follow classical results, while others turn out to be quite different. In particular, we obtain a complete classification scheme for nondegenerate rational conics for rational affine geometry and a constructive method for production of a minimal set of representatives of all equivalence classes.     

Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts

This paper presents a novel vision-based global localization that uses hybrid maps of objects and spatial layouts. We model indoor environments with a stereo camera using the following visual cues: local invariant features for object recognition and their 3D positions for object pose estimation. We also use the depth information at the horizontal centerline of image where the optical axis passes through, which is similar to the data from a 2D laser range finder. This allows us to build our topological node that is composed of a horizontal depth map and an object location map. The horizontal depth map describes the explicit spatial layout of each local space and provides metric information to compute the spatial relationships between adjacent spaces, while the object location map contains the pose information of objects found in each local space and the visual features for object recognition. Based on this map representation, we suggest a coarse-to-fine strategy for global localization. The coarse pose is estimated by means of object recognition and SVD-based point cloud fitting, and then is refined by stochastic scan matching. Experimental results show that our approaches can be used for an effective vision-based map representation as well as for global localization methods.