Stereo matching using iterative reliable disparity map expansion in the color–spatial–disparity space

In this paper, we propose a new stereo matching algorithm using an iterated graph cuts and mean shift filtering technique. Our algorithm estimates the disparity map progressively through the following two steps. In the first step, with a previously estimated RDM (reliable disparity map) that consists of sparse ground control points, an updated dense disparity map is constructed through a RDM constrained energy minimization framework that can cope with occlusion. The graph cuts technique is employed for the solution of the proposed energy model. In the second step, more accurate and denser RDM is estimated through the disparity crosschecking technique and the mean shift filtering in the CSD (color–spatial–disparity) space. The proposed algorithm expands the reliable disparities in RDM repeatedly through the above two steps until it converges. Experimental results on the standard data set demonstrate that the proposed algorithm achieves comparable performance to the state-of-the-arts, and gives excellent results especially in the areas such as the disparity discontinuous boundaries and occluded regions, where the conventional methods usually suffer.     

3D objects recognition by optimal matching search of multinary relations graphs

A new method for 3D object optimal recognition from 2D single images is described. It introduces an optimization approach to inexact graph matching implemented by ordered search algorithm. The search is conducted on homomorphic or monomorphic trees constructed in a combinatorial state space. A min-max structure of the search guiding cost function combines error criteria based on hypothesized multinary geometrical relations with non-geometrical featural and contextual image information. The geometrical error criterion reflects the disparity of the estimated observation vectors derived from partial matches. These vectors are calculated by a novel “area ratio” method based on points or planar region primitives that are preferred for practical image segmentation. The experimental results demonstrate a significant reduction in the complexity of the matching problem (usually exponential), and low sensitivity to large image data errors.     

Stereo by incremental matching of contours

Contours made of sequences of adjacent edge points are used as primitives in stereo pair matching. Matching contour segments, rather than the traditional epipolar edge points, can greatly reduce possible ambiguity. This is done by reformulating point-matching constraints to apply to contour matching, and by introducing a unique incremental matching scheme. Best-matched contours are paired first, constraining through neighborhood support their neighboring contours. Examples of the proposed stereo matching scheme are shown, with very few errors, for aerial images of natural terrain     

Shape matching of two-dimensional objects

In this paper we present results in the areas of shape matching of nonoccluded and occluded two-dimensional objects. Shape matching is viewed as a ``segment matching' problem. Unlike the previous work, the technique is based on a stochastic labeling procedure which explicitly maximizes a criterion function based on the ambiguity and inconsistency of classification. To reduce the computation time, the technique is hierarchical and uses results obtained at low levels to speed up and improve the accuracy of results at higher levels. This basic technique has been extended to the situation where various objects partially occlude each other to form an apparent object and our interest is to find all the objects participating in the occlusion. In such a case several hierarchical processes are executed in parallel for every object participating in the occlusion and are coordinated in such a way that the same segment of the apparent object is not matched to the segments of different actual objects. These techniques have been applied to two-dimensional simple closed curves represented by polygons and the power of the techniques is demonstrated by the examples taken from synthetic, aerial, industrial and biological images where the matching is done after using the actual segmentation methods.     

Stereo matching with linear superposition of layers

In this paper, we address stereo matching in the presence of a class of non-Lambertian effects, where image formation can be modeled as the additive superposition of layers at different depths. The presence of such effects makes it impossible for traditional stereo vision algorithms to recover depths using direct color matching-based methods. We develop several techniques to estimate both depths and colors of the component layers. Depth hypotheses are enumerated in pairs, one from each layer, in a nested plane sweep. For each pair of depth hypotheses, matching is accomplished using spatial-temporal differencing. We then use graph cut optimization to solve for the depths of both layers. This is followed by an iterative color update algorithm which we proved to be convergent. Our algorithm recovers depth and color estimates for both synthetic and real image sequences.     

Contour analysis-based matching of ground objects in aerial images

An original approach to matching images is proposed based on the technique of comparison of the structure of contours. The technique for detecting contours is reinforced by combining the use of data from independent contours and contours that are the boundaries of regions. For this purpose, several assumptions and simple rules of general nature are formulated. Contours are identified based on local salient features of their one-dimensional representation. To avoid ambiguity in identifying contours, the technique of dynamic programming is harnessed. All computational procedures are invariant to image rotation. In conclusion the developed method is applied to the problem of matching image fragments in aerial images.     

Reconstruction of three-dimensional objects through matching oftheir parts

The problem of re-assembling an object from its parts or fragments has never been addressed with a unified computational approach, which depends on the pure geometric form of the parts and not on application-specific features. We propose a method for the automatic reconstruction of a model based on the geometry of its parts, which may be computer-generated models or range-scanned models. The matching process can benefit from any other external constraint imposed by the specific application     

Relaxation algorithm for shape matching of two-dimensional objects

This paper describes a relaxation algorithm without a parameter for shape matching of partially occluded two-dimensional objects. This technique is based on a relaxation labelling process of Rosenfeld et al. for reducing or eliminating the ambiguity. The shapes are represented by polygonal approximation. The proposed relaxation method is used to find acceptable line segment pairs of polygons.     

Representation and shape matching of 3-d objects

A three-dimensional scene analysis system for the shape matching of real world 3-D objects is presented. Various issues related to representation and modeling of 3-D objects are addressed. A new method for the approximation of 3-D objects by a set of planar faces is discussed. The major advantage of this method is that it is applicable to a complete object and not restricted to single range view which was the limitation of the previous work in 3-D scene analysis. The method is a sequential region growing algorithm. It is not applied to range images, but rather to a set of 3-D points. The 3-D model of an object is obtained by combining the object points from a sequence of range data images corresponding to various views of the object, applying the necessary transformations and then approximating the surface by polygons. A stochastic labeling technique is used to do the shape matching of 3-D objects. The technique matches the faces of an unknown view against the faces of the model. It explicitly maximizes a criterion function based on the ambiguity and inconsistency of classification. It is hierarchical and uses results obtained at low levels to speed up and improve the accuracy of results at higher levels. The objective here is to match the individual views of the object taken from any vantage point. Details of the algorithm are presented and the results are shown on several unknown views of a complicated automobile casting.     

Stereo vision for robotic applications in the presence of non-ideal lighting conditions

Many robotic and machine-vision applications rely on the accurate results of stereo correspondence algorithms. However, difficult environmental conditions, such as differentiations in illumination depending on the viewpoint, heavily affect the stereo algorithms’ performance. This work proposes a new illumination-invariant dissimilarity measure in order to substitute the established intensity-based ones. The proposed measure can be adopted by almost any of the existing stereo algorithms, enhancing it with its robust features. The performance of the dissimilarity measure is validated through experimentation with a new adaptive support weight (ASW) stereo correspondence algorithm. Experimental results for a variety of lighting conditions are gathered and compared to those of intensity-based algorithms. The algorithm using the proposed dissimilarity measure outperforms all the other examined algorithms, exhibiting tolerance to illumination differentiations and robust behavior.     

基于SIFT和Daisy相结合的立体匹配算法

立体匹配是计算机视觉领域最活跃的研究课题之一,针对传统SIFT描述符在图像存在多个相似区域时易造成误匹配和Daisy的匹配效率会因200维的描述符而降低的问题,提出一种SIFT和Daisy相结合的立体匹配算法。该方法利用SIFT算法生成关键特征点,利用Daisy描述符自身具有的良好的旋转不变性,对特征点进行描述,利用特征描述符欧氏距离的最近邻匹配和种子区域增长得到视差图。实验结果表明,该方法匹配精度高,速度快,在部分遮挡、视点变化引起的图像变形等问题上有更好的表现。     

Using intermediate objects to improve the efficiency of visual search

When using a mobile camera to search for a target object, it is often important to maximize the efficiency of the search. We consider a method for increasing efficiency by searching only those subregions that are especially likely to contain the object. These subregions are identified via spatial relationships. Searches that use this method repeatedly find an “intermediate” object that commonly participates in a spatial relationship with the target object, and then look for the target in the restricted region specified by this relationship. Intuitively, such searches, calledindirect searches, seem likely to provide efficiency increases when the intermediate objects can be recognized at low resolutions and hence can be found with little extra overhead, and when they significantly restrict the area that must be searched for the target. But what is the magnitude of this increase, and upon what other factors does efficiency depend? Although the idea of exploiting spatial relationships has been used in vision systems before, few have quantitatively examined these questions. We present a mathematical model of search efficiency that identifies the factors affecting efficiency and can be used to predict their effects. The model predicts that, in typical situations, indirect search provides up to an 8-fold increase in efficiency. Besides being useful as an analysis tool, the model is also suitable for use in an online system for selecting intermediate objects.     

Learning search heuristics for finding objects in structured environments

We consider the problem of efficiently finding an object with a mobile robot in an initially unknown, structured environment. The overall goal is to allow the robot to improve upon a standard exploration technique by utilizing background knowledge from previously seen, similar environments. We present two conceptually different approaches. Whereas the first method, which is the focus of this article, is a reactive search technique that decides where to search next only based on local information about the objects in the robot’s vicinity, the second algorithm is a more global and inference-based approach that explicitly reasons about the location of the target object given all observations made so far. While the model underlying the first approach can be learned from data of optimal search paths, we learn the model of the second method from object arrangements of example environments. Our application scenario is the search for a product in a supermarket. We present simulation and real-world experiments in which we compare our strategies to alternative methods and also to the performance of humans.     

A generalization of template matching for recognition of real objects

Pattern-recognition methods are discussed under the general headings of feature extraction and template matching. Problems arising from these methods are of two types: those arising in the process of recognition and those arising when making measurements on objects after recognition. It is indicated how template matching can avoid these latter types of problems and how a generalization of the normal notion of template can surmount problems of the first type. Such a generalized template matching procedure for recognizing cells in a microscope slide is discussed. The generalized template, in this case, makes use of the fact that the cells seem “bubble-like”. It expands a “bubble” template and detects matches between this and the visual data.     

Development of rescue manipulator to search narrow space for victims

Recently, disasters such as earthquakes and so on occur at various places, and rescue operation using robots has attracted much attention. In this paper, we propose a new rescue robot with duplex mechanism that is realized by connecting two manipulators in parallel. We have demonstrated the validity and effectiveness of the proposed system by developing a prototype system. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Optimal search path for service in the presence of disruptions

We consider the following basic search path problem: a customer residing at a node of a network needs to obtain service from one of the facilities; facility locations are known and fixed. Facilities may become inoperational with certain probability; the state of the facility only becomes known when the facility is visited. Customer travel stops when the first operational facility is found. The objective is to minimize the expected total travel distance.     

Sequential Monte Carlo for Bayesian matching of objects with occlusions

We consider the problem of locating instances of a known object in a novel scene by matching the fiducial features of the object. The appearance of the features and the shape of the object are modeled separately and combined in a Bayesian framework. In this paper, we present a novel matching scheme based on sequential Monte Carlo, in which the features are matched sequentially, utilizing the information about the locations of previously matched features to constrain the task. The particle representation of hypotheses about the object position allow matching in multimodal and cluttered environments, where batch algorithms may have convergence difficulties. The proposed method requires no initialization or predetermined matching order, as the sequence can be started from any feature. We also utilize a Bayesian model to deal with features that are not detected due to occlusions or abnormal appearance. In our experiments, the proposed matching system shows promising results, with performance equal to batch approaches when the target distribution is unimodal, while surpassing traditional methods under multimodal conditions. Using the occlusion model, the object can be localized from only a few visible features, with the nonvisible parts predicted from the conditional prior model.     

An algorithm for projective point matching in the presence of spurious points

Point matching is the task of finding correspondences between two sets of points such that the two sets of points are aligned with each other. Pure point matching uses only the location of the points to constrain the problem. This is a problem with broad practical applications, but it has only been well studied when the geometric transformation relating the two point sets is of a relatively low order. Here we present a heuristic local search algorithm that can find correspondences between point sets in two dimensions that are related by a projective transform. Point matching is a harder problem when spurious points appear in the sets to be matched. We present a heuristic algorithm which minimizes the effects of spurious points.     

The search for complex problem-solving strategies in the presence of stressors

OBJECTIVE: The present research tests the effects of time pressure and noise on open-mindedness to discover new problem-solving strategies. BACKGROUND: We are primarily interested in transfer of skill from one phase to the next. More specifically, this study investigates whether the presence of stressors makes participants adhere to the sustained use of complex rules. METHOD: Participants learned to apply a complex rule in the first phase of a category learning task. In the second phase, this rule became dysfunctional and participants had to search for a new categorization rule in order to assign the stimuli to the correct classes. Two experiments were set up to investigate this issue. RESULTS: Participants were found to have difficulty discovering a complex Phase 2 rule in the presence of stressors, whereas the discovery of a simple rule was not hindered by the presence of stressors. CONCLUSION: In the discussion, it is argued that the present results are compatible with previous research on stressors showing that time pressure and noise induce the application of simple strategies. The innovative finding here is that this simplification also occurs in individuals who are accustomed to using complex solutions. APPLICATION: The implications of the present results for emergency response training are elaborated upon.