基于几何特征的曲面物体识别

基于几何特征的曲面物体识别方法是通过从景物深度图象上提取景物表面的高斯曲率和平均曲率、曲率直方图,曲率的熵等几何信息,将景物用一个属性关系图ＡＲＧ来表示,并与模型库中的模型ＡＲＧ图进行优化匹配,从而来识别曲面景物。该方法主要是针对机器零部件等人造曲面物体的识别问题而设计的,其曲面几何特征的描述方法对二阶曲面比较有效,实验表明,应用该方法可成功地从深度图象中识别机器零部件等曲面物体,且有较好的识别结     

Partial shape recognition: a landmark-based approach

A method of recognizing partially occluded objects is presented in which each object is represented by a set of landmarks. Given a scene consisting of partially occluded objects, a model object in the scene is hypothesized by matching the landmarks of the model with those in the scene. A measure of similarity between two landmarks is needed to perform this matching. A local shape measure, sphericity, is introduced. It is shown that any invariant function under a similarity transformation is a function of the sphericity. To match landmarks between the model and the scene, a table of compatibility is constructed. A technique, known as hopping dynamic programming, is described to guide the landmark matching through the compatibility table. The location of the model in the scene is estimated with a least-squares fit among the matched landmarks. A heuristic measure is then computed to decide if the model is in the scene     

A flexible similarity measure for 3D shapes recognition

This paper is devoted to presenting a new strategy for 3D objects recognition using a flexible similarity measure based on the recent modeling wave (MW) topology in spherical models. MW topology allows us to establish an n-connectivity relationship in 3D objects modeling meshes. Using the complete object model, a study on considering different partial information of the model has been carried out to recognize an object. For this, we have introduced a new feature called cone-curvature (CC), which originates from the MW concept. CC gives an extended geometrical surroundings knowledge for every node of the mesh model and allows us to define a robust and adaptable similarity measure between objects for a specific model database. The defined similarity metric has been successfully tested in our lab using range data of a wide variety of 3D shapes. Finally, we show the applicability of our method presenting experimentation for recognition on noise and occlusion conditions in complex scenes.     

An analytical representation of conformal mapping for genus-zero implicit surfaces and its application to surface shape similarity assessment

This paper develops an analytical representation of conformal mapping for genus-zero implicit surfaces based on algebraic polynomial functions, and its application to surface shape similarity assessment. Generally, the conformal mapping often works as a tool of planar or spherical parameterization for triangle mesh surfaces. It is further exploited for implicit surface matching in this study. The method begins with discretizing one implicit surface by triangle mesh, where a discrete harmonic energy model related to both the mesh and the other implicit surface is established based on a polynomial-function mapping. Then both the zero-center constraint and the landmark constraints are added to the model to ensure the uniqueness of mapping result with the Möbius transformation. By searching optimal polynomial coefficients with the Lagrange–Newton method, the analytical representation of conformal mapping is obtained, which reveals all global and continuous one-to-one correspondent point pairs between two implicit surfaces. Finally, a shape similarity assessment index for (two) implicit surfaces is proposed through calculating the differences of all the shape index values among those corresponding points. The proposed analytical representation method of conformal mapping and the shape assessment index are both verified by the simulation cases for the closed genus-zero implicit surfaces. Experimental results show that the method is effective for genus-zero implicit surfaces, which will offer a new way for object retrieval and manufactured surface inspection.     

Structural pattern recognition using genetic algorithms with specialized operators

This paper presents a genetic algorithm (GA)-based optimization procedure for structural pattern recognition in a model-based recognition system using attributed relational graph (ARG) matching technique. The objective of our work is to improve the GA-based ARG matching procedures leading to a faster convergence rate and better quality mapping between a scene ARG and a set of given model ARGs. In this study, potential solutions are represented by integer strings indicating the mapping between scene and model vertices. The fitness of each solution string is computed by accumulating the similarity between the unary and binary attributes of the matched vertex pairs. We propose novel crossover and mutation operators, specifically for this problem. With these specialized genetic operators, the proposed algorithm converges to better quality solutions at a faster rate than the standard genetic algorithm (SGA). In addition, the proposed algorithm is also capable of recognizing multiple instances of any model object. An efficient pose-clustering algorithm is used to eliminate occasional wrong mappings and to determine the presence/pose of the model in the scene. We demonstrate the superior performance of our proposed algorithm using extensive experimental results.     

The illumination-invariant recognition of 3D objects using localcolor invariants

Traditional approaches to three dimensional object recognition exploit the relationship between three dimensional object geometry and two dimensional image geometry. The capability of object recognition systems can be improved by also incorporating information about the color of object surfaces. Using physical models for image formation, the authors derive invariants of local color pixel distributions that are independent of viewpoint and the configuration, intensity, and spectral content of the scene illumination. These invariants capture information about the distribution of spectral reflectance which is intrinsic to a surface and thereby provide substantial discriminatory power for identifying a wide range of surfaces including many textured surfaces. These invariants can be computed efficiently from color image regions without requiring any form of segmentation. The authors have implemented an object recognition system that indexes into a database of models using the invariants and that uses associated geometric information for hypothesis verification and pose estimation. The approach to recognition is based on the computation of local invariants and is therefore relatively insensitive to occlusion. The authors present several examples demonstrating the system's ability to recognize model objects in cluttered scenes independent of object configuration and scene illumination. The discriminatory power of the invariants has been demonstrated by the system's ability to process a large set of regions over complex scenes without generating false hypotheses     

Model construction and shape recognition from occluding contours

A technique is presented for recognizing a 3D object (a model in an image library) from a single 2D silhouette using information such as corners (points with high positive curvatures) and occluding contours, rather than straight line segments. The silhouette is assumed to be a parallel projection of the object. Each model is stored as a set of the principal quadtrees, from which the volume/surface octree of the model is generated. Feature points (i.e. corners) are extracted to guide the recognition process. Four-point correspondences between the 2D feature points of the observed object and 3D feature points of each model are hypothesized, and then verified by applying a variety of constraints to their associated viewing parameters. The result of the hypothesis and verification process is further validated by 2D contour matching. This approach allows for a method of handling both planar and curved objects in a uniform manner, and provides a solution to the recognition of multiple objects with occlusion as demonstrated by the experimental results     

Non-rigid 3D shape tracking from multiview video

We present a fast and efficient non-rigid shape tracking method for modeling dynamic 3D objects from multiview video. Starting from an initial mesh representation, the shape of a dynamic object is tracked over time, both in geometry and topology, based on multiview silhouette and 3D scene flow information. The mesh representation of each frame is obtained by deforming the mesh representation of the previous frame towards the optimal surface defined by the time-varying multiview silhouette information with the aid of 3D scene flow vectors. The whole time-varying shape is then represented as a mesh sequence which can efficiently be encoded in terms of restructuring and topological operations, and small-scale vertex displacements along with the initial model. The proposed method has the ability to deal with dynamic objects that may undergo non-rigid transformations and topological changes. The time-varying mesh representations of such non-rigid shapes, which are not necessarily of fixed connectivity, can successfully be tracked thanks to restructuring and topological operations employed in our deformation scheme. We demonstrate the performance of the proposed method both on real and synthetic sequences.     

Invariant-Based Recognition of Complex Curved 3D Objects from Image Contours

This paper addresses the problem of recognizing three-dimensional objects bounded by smooth curved surfaces from image contours found in a single photograph. The proposed approach is based on a viewpoint-invariant relationship between object geometry and certain image features under weak perspective projection. The image features themselves are viewpoint-dependent. Concretely, the set of all possible silhouette bitangents, along with the contour points sharing the same tangent direction, is the projection of a one-dimensional set of surface points where each point lies on the occluding contour for a five-parameter family of viewpoints. These image features form a one-parameter family of equivalence classes, and it is shown that each class can be characterized by a set of numerical attributes that remain constant across the corresponding five-dimensional set of viewpoints. This is the basis for describing objects by “invariant” curves embedded in high-dimensional spaces. Modeling is achieved by moving an object in front of a camera and does not require knowing the object-to-camera transformation; nor does it involve implicit or explicit three-dimensional shape reconstruction. At recognition time, attributes computed from a single image are used to index the model database, and both qualitative and quantitative verification procedures eliminate potential false matches. The approach has been implemented and examples are presented.     

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     

Symbolic signatures for deformable shapes

Recognizing classes of objects from their shape is an unsolved problem in machine vision that entails the ability of a computer system to represent and generalize complex geometrical information on the basis of a finite amount of prior data. A practical approach to this problem is particularly difficult to implement, not only because the shape variability of relevant object classes is generally large, but also because standard sensing devices used to capture the real world only provide a partial view of a scene, so there is partial information pertaining to the objects of interest. In this work, we develop an algorithmic framework for recognizing classes of deformable shapes from range data. The basic idea of our component-based approach is to generalize existing surface representations that have proven effective in recognizing specific 3D objects to the problem of object classes using our newly introduced symbolic-signature representation that is robust to deformations, as opposed to a numeric representation that is often tied to a specific shape. Based on this approach, we present a system that is capable of recognizing and classifying a variety of object shape classes from range data. We demonstrate our system in a series of large-scale experiments that were motivated by specific applications in scene analysis and medical diagnosis.     

Efficient data structures for model-based 3-D object recognitionand localization from range images

An effective method of surface characterization of 3D objects using surface curvature properties and an efficient approach to recognizing and localizing multiple 3D free-form objects (free-form object recognition and localization) are presented. The approach is surface based and is therefore not sensitive to noise and occlusion, forms hypothesis by local analysis of surface shapes, does not depend on the visibility of complete objects, and uses information from a CAD database in recognition and localization. A knowledge representation scheme for describing free-form surfaces is described. The data structure and procedures are well designed, so that the knowledge leads the system to intelligent behavior. Knowledge about surface shapes is abstracted from CAD models to direct the search in verification of vision hypotheses. The knowledge representation used eases processes of knowledge acquisition, information retrieval, modification of knowledge base, and reasoning for solution     

Structural indexing: efficient 3-D object recognition

The authors present an approach for the recognition of multiple 3-D object models from three 3-D scene data. The approach uses two different types of primitives for matching: small surface patches, where differential properties can be reliably computed, and lines corresponding to depth or orientation discontinuities. These are represented by splashes and 3-D curves, respectively. It is shown how both of these primitives can be encoded by a set of super segments, consisting of connected linear segments. These super segments are entered into a table and provide the essential mechanism for fast retrieval and matching. The issues of robustness and stability of the features are addressed in detail. The acquisition of the 3-D models is performed automatically by computing splashes in highly structured areas of the objects and by using boundary and surface edges for the generation of 3-D curves. The authors present results with the current system (3-D object recognition based on super segments) and discuss further extensions     

Object representation and recognition in shape spaces

In this paper, we describe a shape space based approach for invariant object representation and recognition. In this approach, an object and all its similarity transformed versions are identified with a single point in a high-dimensional manifold called the shape space. Object recognition is achieved by measuring the geodesic distance between an observed object and a model in the shape space. This approach produced promising results in 2D object recognition experiments: it is invariant to similarity transformations and is relatively insensitive to noise and occlusion. Potentially, it can also be used for 3D object recognition.     

Depth estimation from image structure

In the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured. The interpretation of shading, edges, and junctions may provide a 3D model of the scene but it will not provide information about the actual "scale" of the space. One possible source of information for absolute depth estimation is the image size of known objects. However, object recognition, under unconstrained conditions, remains difficult and unreliable for current computational approaches. We propose a source of information for absolute depth estimation based on the whole scene structure that does not rely on specific objects. We demonstrate that, by recognizing the properties of the structures present in the image, we can infer the scale of the scene and, therefore, its absolute mean depth. We illustrate the interest in computing the mean depth of the scene with application to scene recognition and object detection     

3D modeling of multiple-object scenes from sets of images

This paper proposes a new approach for multi-object 3D scene modeling. Scenes with multiple objects are characterized by object occlusions under several views, complex illumination conditions due to multiple reflections and shadows, as well as a variety of object shapes and surface properties. These factors raise huge challenges when attempting to model real 3D multi-object scene by using existing approaches which are designed mainly for single object modeling. The proposed method relies on the initialization provided by a rough 3D model of the scene estimated from the given set of multi-view images. The contributions described in this paper consists of two new methods for identifying and correcting errors in the reconstructed 3D scene. The first approach corrects the location of 3D patches from the scene after detecting the disparity between pairs of their projections into images. The second approach is called shape-from-contours and identifies discrepancies between projections of 3D objects and their corresponding contours, segmented from images. Both unsupervised and supervised segmentations are used to define the contours of objects.