Classification of hand postures against complex backgrounds using elastic graph matching

A system for person-independent classification of hand postures against complex backgrounds in video images is presented. The system employs elastic graph matching, which has already been successfully applied for object and face recognition. We use the bunch graph technique to model variance in hand posture appearance between different subjects and variance in backgrounds. Our system does not need a separate segmentation stage but closely integrates finding the object boundaries with posture classification.     

Stochastic models for recognition of occluded targets

Recognition of occluded objects in synthetic aperture radar (SAR) images is a significant problem for automatic target recognition. Stochastic models provide some attractive features for pattern matching and recognition under partial occlusion and noise. In this paper, we present a hidden Markov modeling based approach for recognizing objects in SAR images. We identify the peculiar characteristics of SAR sensors and using these characteristics we develop feature based multiple models for a given SAR image of an object. The models exploiting the relative geometry of feature locations or the amplitude of SAR radar return are based on sequentialization of scattering centers extracted from SAR images. In order to improve performance we integrate these models synergistically using their probabilistic estimates for recognition of a particular target at a specific azimuth. Experimental results are presented using both synthetic and real SAR images.     

Accelerating feature-vector matching using multiple-tree and sub-vector methods

We propose two methods to accelerate the matching of an unknown object with known objects, all of which are expressed as feature vectors. The acceleration becomes necessary when the population of known objects is large and a great deal of time would be required to match all of them. Our proposed methods are multiple decision trees and sub-vector matching, both of which use a learning procedure to estimate the optimal values of certain parameters. Online matching with a combination of the two methods is then performed, whereby candidates are matched rapidly without sacrificing the test accuracy. The process is demonstrated by experiments in which we apply the proposed methods to handwriting recognition and language identification. The speed-up factor of our approach is dramatic compared with an alternative approach that eliminates candidates in a deterministic fashion.     

A probabilistic matching algorithm for computer vision

A model-based vision system attempts to find correspondences between features of an object model and features detected in an image for purposes of recognition, localization, or inspection. In this paper we pose the relational matching problem as a special case of the pattern complex recognition problem and propose a probabilistic model to describe the images of an object. This Bayesian approach allows us to make explicit statements of how an image is formed from a model, and hence define a natural matching cost that can be used to guide a heuristic search in finding the best observation mapping. Furthermore, we show that even though the nature of the feature matching problem is exponential, the use of the proposed algorithm keeps the size of the problem under control, by efficiently reducing the search space.     

Unsupervised Learning for Graph Matching

Graph matching is an essential problem in computer vision that has been successfully applied to 2D and 3D feature matching and object recognition. Despite its importance, little has been published on learning the parameters that control graph matching, even though learning has been shown to be vital for improving the matching rate. In this paper we show how to perform parameter learning in an unsupervised fashion, that is when no correct correspondences between graphs are given during training. Our experiments reveal that unsupervised learning compares favorably to the supervised case, both in terms of efficiency and quality, while avoiding the tedious manual labeling of ground truth correspondences. We verify experimentally that our learning method can improve the performance of several state-of-the art graph matching algorithms. We also show that a similar method can be successfully applied to parameter learning for graphical models and demonstrate its effectiveness empirically.     

Robust object recognition with cortex-like mechanisms

We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex     

Recognition of occluded objects by reducing feature interactions

The main difficulty for the recognition of occluded objects lies in the fact that the original feature set is corrupted and no longer reliable to represent the object of interest. This corruption is caused by the interactions between features from different objects, denoted as feature interactions, which is a key issue addressed in our algorithm. In this paper, a local to global strategy is represented for the occlusion recognition problem, which combines the pairwise grouping and graph matching algorithms. Local appearance similarity serves as priors to reduce feature interactions, by which the performance of graph matching algorithms is improved in order to deal with the contaminated data set. With our formulation, a global decision on object recognition can be made based on locally gathered information. Experimental results show that the proposed framework can dramatically reduce incorrect matches and objects under severe occlusions can still be recognized.     

一种适用于室内服务机器人的实时物体识别系统

针对室内服务机器人在实际应用中的需求,提出一种结合三维点云分割和局部特征匹配的实时物体识别系统．该系统首先基于三维点云实现快速有效的物体检测,然后利用物体检测的结果定位物体在彩色图像中的区域,并采用基于SURF特征匹配的方法识别出物体的标识．实验结果表明,该系统可较好地满足室内服务机器人物体检测与识别的实时性和可靠性要求．     

Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition

Interpretation of images and videos containing humans interacting with different objects is a daunting task. It involves understanding scene/event, analyzing human movements, recognizing manipulable objects, and observing the effect of the human movement on those objects. While each of these perceptual tasks can be conducted independently, recognition rate improves when interactions between them are considered. Motivated by psychological studies of human perception, we present a Bayesian approach which integrates various perceptual tasks involved in understanding human-object interactions. Previous approaches to object and action recognition rely on static shape/appearance feature matching and motion analysis, respectively. Our approach goes beyond these traditional approaches and applies spatial and functional constraints on each of the perceptual elements for coherent semantic interpretation. Such constraints allow us to recognize objects and actions when the appearances are not discriminative enough. We also demonstrate the use of such constraints in recognition of actions from static images without using any motion information.     

A CAD Model Based System for Object Recognition

3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.     

HEGM: A hierarchical elastic graph matching for hand gesture recognition

A hierarchical scheme for elastic graph matching applied to hand gesture recognition is proposed. The proposed algorithm exploits the relative discriminatory capabilities of visual features scattered on the images, assigning the corresponding weights to each feature. A boosting algorithm is used to determine the structure of the hierarchy of a given graph. The graph is expressed by annotating the nodes of interest over the target object to form a bunch graph. Three annotation techniques, manual, semi-automatic, and automatic annotation are used to determine the position of the nodes. The scheme and the annotation approaches are applied to explore the hand gesture recognition performance. A number of filter banks are applied to hand gestures images to investigate the effect of using different feature representation approaches. Experimental results show that the hierarchical elastic graph matching (HEGM) approach classified the hand posture with a gesture recognition accuracy of 99.85% when visual features were extracted by utilizing the Histogram of Oriented Gradient (HOG) representation. The results also provide the performance measures from the aspect of recognition accuracy to matching benefits, node positions correlation and consistency on three annotation approaches, showing that the semi-automatic annotation method is more efficient and accurate than the other two methods.     

A Neural Network Approach to Planar-Object Recognition in 3D Space

Most existing 2D object recognition algorithms are not perspective (or projective) invariant, and hence are not suitable for many real-world applications. By contrast, one of the primary goals of this research is to develop a flat object matching system that can identify and localise an object, even when seen from different viewpoints in 3D space. In addition, we also strive to achieve good scale invariance and robustness against partial occlusion as in any practical 2D object recognition system. The proposed system uses multi-view model representations and objects are recognised by self-organised dynamic link matching. The merit of this approach is that it offers a compact framework for concurrent assessments of multiple match hypotheses by promoting competitions and/or co-operations among several local mappings of model and test image feature correspondences. Our experiments show that the system is very successful in recognising object to perspective distortion, even in rather cluttered scenes. Receiveed: 29 May 1998?,Received in revised form: 12 October 1998?Accepted: 26 October 1998     

Distant Collision Response in Rigid Body Simulations

We use a finite element model to predict the vibration response of objects in a rigid body simulation, such that rigid objects are augmented to provide a plausible elastic collision response between distant objects due to vibration. We start with a generalized eigenvalue decomposition of the elastic model to precompute a response to an impact at any point on an elastic object with fixed boundary conditions. Then, given a collision between objects, we generate an approximate response impulse to distribute to other objects already in contact with the colliding bodies. This can lead to distant impacts causing an object to slip, or a delicate stack of objects to fall. We also use a geodesic distance based spatial attenuation approximation for travelling waves in objects to respond to an impact at one contact with an impulse at other locations. This response ultimately allows a long distance relationship between contacts, both across a single object being struck, but also traversing the contact graph of a larger collection of objects. We qualitatively validate our approach with a ground truth simulation, and demonstrate a number of scenarios where a long distance relationship between contacts is valuable.     

A neural network approach to CSG-based 3-D object recognition

Describes the recognition subsystem of a computer vision system based on constructive solid geometry (CSG) representation scheme. Instead of using the conventional CSG trees to represent objects, the proposed system uses an equivalent representation scheme-precedence graphs-for object representation. Each node in the graph represents a primitive volume and each are between two nodes represents the relation between them. Object recognition is achieved by matching the scene precedence graph to the model precedence graph. A constraint satisfaction network is proposed to implement the matching process. The energy function associated with the network is used to enforce the matching constraints including match validity, primitive similarity, precedence graph preservation, and geometric structure preservation. The energy level is at its minimum only when the optimal match is reached. Experimental results on several range images are presented to demonstrate the proposed approach     

Probabilistic Models of Appearance for 3-D Object Recognition

We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses probability distributions to describe the range of possible variation in the object's appearance. These distributions are organized on two levels. Large variations are handled by partitioning training images into clusters corresponding to distinctly different views of the object. Within each cluster, smaller variations are represented by distributions characterizing uncertainty in the presence, position, and measurements of various discrete features of appearance. Many types of features are used, ranging in abstraction from edge segments to perceptual groupings and regions. A matching procedure uses the feature uncertainty information to guide the search for a match between model and image. Hypothesized feature pairings are used to estimate a viewpoint transformation taking account of feature uncertainty. These methods have been implemented in an object recognition system, OLIVER. Experiments show that OLIVER is capable of learning to recognize complex objects in cluttered images, while acquiring models that represent those objects using relatively few views.