Stereo vision correspondence using a multichannel graph matching technique

A multichannel feature-based stereo vision technique is described in this paper where curve segments are used as the feature primitives in the matching process. Curve segments are extracted by tracking the zero-crossings of the left and right images. The generalized Hough transform of each curve and the curve length are used as a local feature vector in representing the distinctive characteristics of the curve segment. The feature vector of each curve segment in the left image is used as a constraint to find an instance of the same curve segment in the right image. The epipolar constraint on the centroids of the curve segment is used to limit the searching space in the right image.

A relational graph is formed from the left image by treating the centroids of the curve segments as the nodes of the graph. The local features of the curve segments are used to represent the local properties of the nodes, and the relationship between the nodes represents the structural properties of the objects in the scene. A similar graph is also formed from the right image curve segments. A graph isomorphism is then formed between the two graphs by using the epipolar constraint on the centroids, the local properties of the nodes, node assignment and the structural relationship (compatibility) between the nodes.     

Stereo correspondence with compact windows via minimum ratio cycle

One of the earliest and still widely used methods for dense stereo correspondence is based on matching windows of pixels. The main difficulty of this method is choosing a window of appropriate size and shape. Small windows may lack sufficient intensity variation for reliable matching, while large windows smooth out disparity discontinuities. We propose an algorithm to choose a window size and shape by optimizing over a large class of "compact" windows. The word compact is used informally to reflect the fact that the ratio of perimeter to area of our windows is small. We believe that this is the first area based method which efficiently constructs nonrectangular windows. Fast optimization over compact windows is achieved via the minimum ratio cycle algorithm for graphs. The algorithm has only a few parameters which are easy to fix.     

Context-based multi-target tracking with occlusion handling

Occlusion has long been a core challenge for multi-target tracking tasks. In this paper we present context-based tracking strategies and demonstrate those for two very different types of targets, namely vehicles and fruit flies, representing examples of different target categories (e.g. individually identifiable with relatively consistent trajectories versus nearly identical targets with highly irregular trajectories). Those two classes of targets are also recorded with either mobile or static camera systems, and they represent either long-term or high-frequency occlusion scenarios, respectively. Occlusions among rigid vehicles have various occlusion patterns because of the mobile recording platform and the dynamic traffic environment. In contrast, a high-density scene of fruit flies contains hundreds of targets where occlusion is relatively short, but the frequency of occlusions is very high. In this paper we propose tracking systems based on context information, and show that those are able to address both application scenarios of target tracking. The proposed strategy outperforms state-of-the-art methods in both cases. Experimental results also demonstrate the efficiency of the proposed systems for occlusion handling.     

Hierarchical image segmentation using a correspondence with a tree model

A new general image segmentation system is presented, based on the calculation of a tree representation of the original image in which image regions are assigned to tree nodes, followed by a correspondence process with a model tree, which embeds the a priori knowledge about the images. For this correspondence, an original algorithm is proposed, which performs the minimization of an error function that quantifies the difference between the input image tree and the model tree. We also present a new algorithm for automatically calculating the model tree from a set of manually segmented images. Results on synthetic and MR brain images are presented.     

Feature point correspondence in the presence of occlusion

Occlusion and poor feature point detection are two of the main difficulties in the use of multiple frames for establishing correspondence of feature points. A formulation of the correspondence problem as an optimization problem is used to handle these difficulties. Modifications to an existing iterative optimization procedure for solving the formulation of the correspondence problem are discussed. Experimental results are presented to show the merits of the formulation     

Contour-based object tracking with occlusion handling in video acquired using mobile cameras

We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame to frame by minimizing some energy functional evaluated in the contour vicinity defined by a band. Our approach has two major components related to the visual features and the object shape. Visual features (color, texture) are modeled by semiparametric models and are fused using independent opinion polling. Shape priors consist of shape level sets and are used to recover the missing object regions during occlusion. We demonstrate the performance of our method in real sequences with and without object occlusions.     

融合灰度和梯度的MRF模型的立体匹配

基于立体匹配的马尔科夫随机场（MRF）模型,构建MRF的全局能量函数的数据项和平滑项,提出一种融合灰度和梯度特征的数据项建立,利用改进的置信度传播方法得到视差图,通过MRF因果系统对其校正。通过Middlebury大学的立体视觉测试平台获得性能指标。实验表明,该方法提高了立体匹配的正确率。     

Implementing a hybrid simulation model for a Kanban-based material handling system

Plant floor material handling is a loose loop in most assembly plants. Simulation offers a quick, controllable and tunable approach for prototyping complex material handling processes in manufacturing environments. This paper proposes a hybrid simulation approach, using both discrete event and agent-based technologies, to model complex material handling processes in an assembly line. A prototype system is implemented using a commercial multi-paradigm modeling tool. In this prototype, JIT principles are applied to both the production and the material handling processes. The system performance is evaluated and system optimization directions are suggested. The proposed hybrid modeling approach facilitates the implementation of a responsive and adaptive environment in that various “what-if” scenarios can be simulated under different simulation configurations and real-time situations.     

Structural schema integration with full and partial correspondence using the dual model

The integration of views and schemas is an important part of database design and evolution and permits the sharing of data across complex applications. The view and schema integration methodologies used to date are driven purely by semantic considerations, and allow integration of objects only if that is valid from both semantic and structural view points. We discuss a new integration method called structural integration that has the advantage of being able to integrate objects that have structural similarities, even if they differ semantically. This is possible by using the object-oriented Dual Model which allows separate representation of structure and semantics. Structural integration has several advantages, including the identification of shared common structures that is important for sharing of data and methods.     

Integrating correspondence analysis with Grey relational model to implement a user-driven STP product strategy for smart glasses

To enhance customer retention and customer acquisition, product differentiation, product configuration and product recommendation are of importance to help firms implement segmentation–targeting–positioning strategies. In reality, however, user perceptions of product features are usually vague and diverse by individuals. Consequently, for a manufacturer, learning an efficient way to balance the trade-offs between satisfying customer needs and optimizing product varieties has become much more challenging than before. In order to overcome the aforementioned difficulty, this paper presents a novel framework to assist firms in determining the optimal product varieties of smart glasses with consideration of diverse requirements of three distinct segments (i.e. home entertainment, medical healthcare, and industry service). In particular, correspondence analysis is employed to indicate which product attributes best characterize a specific segment for achieving product differentiation. Then, by means of Grey relational model, the top three priorities with regard to three segments are systematically identified for conducting product configuration. Lastly, Bayes theorem is utilized to assign a potential buyer to his/her most similar segment for accomplishing unsupervised product recommendation.     

Feature correspondence in a non-overlapping camera network

Person re-identification across multiple cameras is difficult due to viewpoint and illumination variations. Most traditional research focuses on developing invariant features that are unaffected by these variations. However, thus far, there has been no feature developed that is completely invariant, and it is possible that a fully invariant feature may not exist. Therefore, we do not seek to develop these ideal features in this paper. We instead propose a framework for learning a gallery of persons who appear in the camera network frequently. The gallery contains appearance models of these persons from each camera and viewpoint. Given the camera identity, viewpoint identity, person identity, the model is decided. Since these appearance models are specific to each camera and viewpoint, the problems of viewpoint variations and illumination variations between cameras are explicitly solved, and re-identification becomes a ranking problem. Experiments demonstrate that our framework provides significant improvement in addressing the re-identification problem.     

Construction of a key-dependent message secure symmetric encryption scheme in the ideal cipher model

Key-dependent message (KDM) security is an important security issue that has attracted much research in recent years. In this paper, we present a new construction of the symmetric encryption scheme in the the ideal cipher model (ICM); we prove that our scheme is KDM secure against active attacks with respect to arbitrary polynomialtime challenge functions. Our main idea is to introduce a universal hash function (UHF) h as a random value for each encryption, and then use s = h(sk) as the key of the ideal cipher F, where sk is the private key of our symmetric encryption scheme. Although many other schemes that are secure against KDM attacks have already been proposed, in both the ideal standard models, the much more significance of our paper is the simplicity in which we implement KDM security against active attacks.     

Construction of a key-dependent message secure symmetric encryption scheme in the ideal cipher model

Key-dependent message （KDM） security is an important security issue that has attracted much research in recent years. In this paper, we present a new construction of the symmetric encryption scheme in the the ideal cipher model （ICM）; we prove that our scheme is KDM secure against active attacks with respect to arbitrary polynomialtime challenge functions. Our main idea is to introduce a universal hash function （UHF） h as a random value for each encrypfion, and then use s = h（sk） as the key of the ideal cipher F, where sk is the private key of our symmetric encryption scheme. Although many other schemes that are secure against KDM attacks have already been proposed, in both the ideal standard models, the much more significance of our paper is the simplicity in which we implement KDM security against active attacks.     

An Evolutionary-Based Stereo Matching Method with a Multilevel Searching Strategy

Stereo matching is one of the fundamental problems in computer vision. It consists in identifying features in two or more stereo images that are generated by the same physical feature in the three-dimensional space. This paper presents an evolutionary approach with a multilevel searching strategy for matching edges extracted from two stereo images. The matching problem is turned into an optimization task, which is performed by means of a genetic algorithm with a new encoding scheme. For an effective exploitation of the genetic stereo matching algorithm for real-time obstacle detection, a multilevel searching strategy is proposed to match the edges at different levels by considering their gradient magnitudes. Experimental results and comparative analysis are presented to demonstrate the effectiveness of the proposed method for real-time obstacle detection in front of a moving vehicle using linear stereo vision.     

Evolutionary model trees for handling continuous classes in machine learning

Model trees are a particular case of decision trees employed to solve regression problems. They have the advantage of presenting an interpretable output, helping the end-user to get more confidence in the prediction and providing the basis for the end-user to have new insight about the data, confirming or rejecting hypotheses previously formed. Moreover, model trees present an acceptable level of predictive performance in comparison to most techniques used for solving regression problems. Since generating the optimal model tree is an NP-Complete problem, traditional model tree induction algorithms make use of a greedy top-down divide-and-conquer strategy, which may not converge to the global optimal solution. In this paper, we propose a novel algorithm based on the use of the evolutionary algorithms paradigm as an alternate heuristic to generate model trees in order to improve the convergence to globally near-optimal solutions. We call our new approach evolutionary model tree induction (E-Motion). We test its predictive performance using public UCI data sets, and we compare the results to traditional greedy regression/model trees induction algorithms, as well as to other evolutionary approaches. Results show that our method presents a good trade-off between predictive performance and model comprehensibility, which may be crucial in many machine learning applications.     

The gradient with respect to a symmetric matrix

The well-known formulas for gradient matrices can be applied only when the elements of the matrix are independent [1],[2]. In this note, the author derives gradient formulas for two important types of element dependency: symmetry and skew symmetry. Application is made to the sensitivity analysis of optimal estimation systems.