Multi-scale 2D tracking of articulated objects using hierarchical spring systems

This paper presents a flexible framework to build a target-specific, part-based representation for arbitrary articulated or rigid objects. The aim is to successfully track the target object in 2D, through multiple scales and occlusions. This is realized by employing a hierarchical, iterative optimization process on the proposed representation of structure and appearance. Therefore, each rigid part of an object is described by a hierarchical spring system represented by an attributed graph pyramid. Hierarchical spring systems encode the spatial relationships of the features (attributes of the graph pyramid) describing the parts and enforce them by spring-like behavior during tracking. Articulation points connecting the parts of the object allow to transfer position information from reliable to ambiguous parts. Tracking is done in an iterative process by combining the hypotheses of simple trackers with the hypotheses extracted from the hierarchical spring systems.     

Reprint of: Multi-scale 2D tracking of articulated objects using hierarchical spring systems

This paper presents a flexible framework to build a target-specific, part-based representation for arbitrary articulated or rigid objects. The aim is to successfully track the target object in 2D, through multiple scales and occlusions. This is realized by employing a hierarchical, iterative optimization process on the proposed representation of structure and appearance. Therefore, each rigid part of an object is described by a hierarchical spring system represented by an attributed graph pyramid. Hierarchical spring systems encode the spatial relationships of the features (attributes of the graph pyramid) describing the parts and enforce them by spring-like behavior during tracking. Articulation points connecting the parts of the object allow to transfer position information from reliable to ambiguous parts. Tracking is done in an iterative process by combining the hypotheses of simple trackers with the hypotheses extracted from the hierarchical spring systems.     

Model-Based Recognition of 3D Curves From One View

It is well known that there are no geometric invariants of a projection from 3D to 2D. However, given some modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions should be sufficiently strong to enable us to find such invariants, but not stronger than necessary. In this paper we find such modeling assumptions for general 3D curves under affine projection. We show, for example, that if one of the two affine curvatures is known along the 3D curve, the other can be found from the curve's 2D image. We can also derive the point correspondence between the curve and its image. We also deal with point sets and direction vectors.     

A Framework for Reconstruction based Recognition of Partially Occluded Repeated Objects

In this paper we propose a reconstruction based recognition scheme for objects with repeated components, using a single image of such a configuration, in which one of the repeated components may be partially occluded. In our strategy we reconstruct each of the components with respect to the same frame and use these to compute invariants.We propose a new mathematical framework for the projective reconstruction of affinely repeated objects. This uses the repetition explicitly and hence is able to handle substantial occlusion of one of the components. We then apply this framework to the reconstruction of a pair of repeated quadrics. The image information required for the reconstruction are the outline conic of one of the quadrics and correspondence between any four points which are images of points in general position on the quadric and its repetition. Projective invariants computed using the reconstructed quadrics have been used for recognition. The recognition strategy has been applied to images of monuments with multi-dome architecture. Experiments have established the discriminatory ability of the invariants.     

Localization of primitives using adaptive projections

An application of an active method in order to compute highly accurate 3D localization of point features from few projections is presented. The angle of projection of the image is controlled by the system and directed to extract 3D information from the environment in a manner leading to accurate location in less computation.This model is relevant for tomographic reconstruction, for feature based stereo and for model based robot registration.     

Dynamic characteristics and stability criterion of rotary galloping gait with an articulated passive spine joint

Based on the simplified planar quadruped model with a passive spine joint, this paper focuses on studying the effect of the spine joint on the dynamic performance and the stability of the rotary galloping gait. The stable, periodic, and symmetric rotary galloping gait is achieved by the particle swarm optimization method without any parameter symmetry for leg motion and without any limitation for spine motion. By analyzing the symmetric pattern of the rotary galloping gait, the stability criterion is derived: the closer to zero is the pitching angle at peak time of the center of mass, the better is the stability of the galloping gait. Then, we study the effect of rear leg touchdown angle and spine stiffness on the stability. Moreover, the unstable rotary galloping gait can be stabilized by adjusting one or more of the touchdown angle, spine stiffness, and leg stiffness. Furthermore, the effect of the spine stiffness on the key kinematic and kinetic properties is also studied for different initial values and mechanical parameters. The presented stability criterion and the achieved dynamic performance analysis results will be instructive for the design and control of the quadruped robot.     

基于黎曼流形的平面目标识别

平面目标识别中的几何形变可用射影变换群描述. 与紧致李群SO(n, R)不同, 正则化的射影变换群, 即非紧致李群SL(n, R)上由黎曼度量决定的黎曼指数映射不同于由单参数子群决定的李群指数映射. 基于黎曼流形优化算法得到取值于特殊线性群SL(3, R)的样本的内蕴均值和协方差矩阵, 并依此构建李群正态分布. 利用此先验知识, 根据贝叶斯定理进行简单背景下的平面目标的识别实验. 结果表明, 利用射影变换群的统计特性可有效提高平面目标识别的成功率.     

Appearance-based recognition of 3-D objects by cluttered background and occlusions

In this article we present a new appearance-based approach for the classification and the localization of 3-D objects in complex scenes. A main problem for object recognition is that the size and the appearance of the objects in the image vary for 3-D transformations. For this reason, we model the region of the object in the image as well as the object features themselves as functions of these transformations. We integrate the model into a statistical framework, and so we can deal with noise and illumination changes. To handle heterogeneous background and occlusions, we introduce a background model and an assignment function. Thus, the object recognition system becomes robust, and a reliable distinction, which features belong to the object and which to the background, is possible. Experiments on three large data sets that contain rotations orthogonal to the image plane and scaling with together more than 100 000 images show that the approach is well suited for this task.     

An invariant observer for a chemostat model

In this paper, we tackle the problem of designing an invariant observer for a chemostat model with adjustable and robust convergence. The main idea of the paper is to build a new class of observers for chemostat model using hidden symmetries. The effectiveness of the proposed observer is shown through simulations.     

An improved generalized Hough transform for the recognition of overlapping objects

The generalized Hough transform (GHT) is a powerful method for recognizing arbitrary shapes as long as the correct match accounts for both much of the model and much of the sensory object. For moderate levels of occlusion, however, the GHT can hypothesize many false solutions. In this paper, we present an improved two-stage GHT procedure for the recognition of overlapping objects. Each boundary point in the image is described by three features including the concavity, radius and normal direction of the curve segment in the neighborhood of the point. The first stage of the voting process determines the rotational angle of the sensory object with respect to the model by matching those points that have the same concavity and radii. The second stage then determines the centroid of the sensory object by matching those points that have the same concavity, radii and rotational angles. The three point features remove the false contribution of votes in the vote generation phase. Experimental results have shown that the proposed algorithm works well for complex objects under severely overlapping conditions.     

Curve and Surface Duals and the Recognition of Curved 3D Objects from their Silhouettes

This article addresses the problem of recognizing a solid bounded by a smooth surface in a single image. The proposed approach is based on a new representation for two- and three-dimensional shapes, called their signature, that exploits the close relationship between the dual of a surface and the dual of its silhouette in weak-perspective images. Objects are modeled by rotating them in front of a camera without any knowledge of or constraints on their motion. The signatures of their silhouettes are concatenated into a single object signature. To recognize an object from novel viewpoint other than those used during modeling, the signature of the contours extracted from a test photograph is matched to the signatures of all modeled objects signatures. This approach has been implemented, and recognition examples are presented.     

基于多视角距离图象的三维物体建模及其在识别中的应用

模型的表示和构建是基于距离图象三维物体识别技术中的关键模块之一.针对已有方法存在的若干问题,提出一个新的综合多个视角距离图象的三维物体模型表示策略和增量式的模型习得算法,并将该模型表示用于三维物体识别中.实验结果验证了算法的有效性.     

Local association based recognition of two-dimensional objects

A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.     

Object recognition and articulated object learning by accumulative Hopfield matching

In this paper, a novel object recognition method based on attributed relational graph matching is proposed, which is called accumulative Hopfield matching. We first divide the scene graph into many sub-graphs, and a modified Hopfield network is then constructed to obtain the sub-graph isomorphism between each sub-scene graph and model graph. The final result is deduced by accumulating the solutions of all small sub-networks. Comparing to the traditional Hopfield network, the proposed system has the advantage of finding homomorphic mappings between two graphs. Furthermore, the system can be applied for articulated object recognition and visual model learning, which is considered as a difficult topic till now. The proposed method has been evaluated with real images.     

Isochronous sets of invariant control systems

Let G be a connected Lie group with Lie algebra g and Σ=(G,D) a controllable invariant control system. A subset A⊂G is said to be isochronous if there exists a uniform time T_A>0 such that any two arbitrary elements in A can be connected by a positive orbit of Σ at exact time T_A. In this paper, we search for classes of Lie groups G such that any Σ has the following property: there exists an increasing sequence of open neighborhoods (V_n)_n≥0 of the identity in G such that the group can be decomposed in isochronous rings W_n=V_n+1−V_n. We characterize this property in algebraic terms and we show that three classes of Lie groups satisfy this property: completely solvable simply connected Lie groups, semisimple Lie groups and reductive Lie groups.     

Invariants of Families of Coplanar Conics and Their Applications to Object Recognition

This paper presents mutual invariants of families ofcoplanar conics. These invariants are compared with the use ofinvariants of two conics and a case is presented where the proposedinvariants have a greater discriminating power than the previouslyused invariants. The use of invariants for two conics is extended toany number of coplanar conics. A lambda-matrix is associated witheach family of coplanar conics. The use of lambda-matrices isextended from the single variable polynomial to multi-variablepolynomials. The Segre characteristic and other invariants of thelambda-matrix are used as invariants of the family of conics.     

不变矩稳定性及基于多级特征模型的目标识别研究

从成像过程和实际应用角度研究影响目标不变矩稳定性的各种因素,包括有限观测区域、高斯模糊和离散化处理以及在这些因素影响下不变矩的变化规律和误差．理论分析和实验还证明各不变矩自身的稳定特性不仅与阶数而且与其次数有关．这些研究和分析表明建立多尺度目标特征模型的必要性,可为不变矩在实际成像识别系统中正确有效地应用提供重要的理论和实验依据．     

二维连续形变物体的计算机识别技术研究

在对包括连续形变物体等在内的基本概念给出严格定义的基础上(为使该文自封闭),首先对物体的刚性相似问题进行了深入研究,提出了新的不变量理论,即长度相似不变量和方向相似不变量,进一步揭示出物体拓扑相似与物体刚性相似之间所存在的内在联系,最后研究了物体连续形变与物体拓扑相似之间的内在联系,并以定理形式给出了物体连续形变的充要条件——成为该文识别算法的理论依据;另外,拓扑同胚以及相似不变量等概念在算法的研究过程中起着较为重要的作用．