A linguistic approach to 3-D object recognition

The principles of a 3-D object recognition system for combined intensity-image and depth-map understanding are discussed. The goal of such system is to be an inversion of image synthesis performed by 3-D computer graphics. A linguistic model for two system elements, the knowledge base and recognition strategy, being an extension of pattern recognition approaches, is outlined. It consists of a powerful object specification language and a simultaneous syntactic-semantic analysis in this language. The syntax is based on a node-controlled parallel structure grammar. Particular attention is paid to elements shared in common by several parts and to hidden line/surface problems. Both are embedded into the grammars derivation. The semantics is well-defined due to the attribution of the grammar.     

A Hidden Markov Model approach for appearance-based 3D object recognition

In this paper, a new appearance-based 3D object classification method is proposed based on the Hidden Markov Model (HMM) approach. Hidden Markov Models are a widely used methodology for sequential data modelling, of growing importance in the last years. In the proposed approach, each view is subdivided in regular, partially overlapped sub-images, and wavelet coefficients are computed for each window. These coefficients are then arranged in a sequential fashion to compose a sequence vector, which is used to train a HMM, paying particular attention to the model selection issue and to the training procedure initialization. A thorough experimental evaluation on a standard database has shown promising results, also in presence of image distortions and occlusions, the latter representing one of the most severe problems of the recognition methods. This analysis suggests that the proposed approach represents an interesting alternative to classic appearance-based methods to 3D object classification.     

Dense statistic versus sparse feature-based approach for 3D object recognition

In this article we introduce and compare two approaches towards automatic classification of 3D objects in 2D images. The first one is based on statistical modeling of wavelet features. It estimates probability density functions for all possible object classes considered in a particular recognition task. The second one uses sparse local features. For training, SURF features are extracted from the training images. During the recognition phase, features from the image are matched geometrically, providing the best fitting object for the query image. Experiments were performed for different training sets using more than 40 000 images with different backgrounds. Results show very good classification rates for both systems and point out special characteristics for each approach, which make them more suitable for different applications.     

3D free-form surface registration and object recognition

A new technique to recognise 3D free-form objects via registration is proposed. This technique attempts to register a free-form surface, represented by a set of % MathType!MTEF!2!1!+-% feaafeart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaaGOmamaala% aabaGaaGymaaqaaiaaikdaaaGaamiraaaa!38F8!\[2\frac{1}{2}D\] sensed data points, to the model surface, represented by another set of % MathType!MTEF!2!1!+-% feaafeart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaaGOmamaala% aabaGaaGymaaqaaiaaikdaaaGaamiraaaa!38F8!\[2\frac{1}{2}D\] model data points, without prior knowledge of correspondence or view points between the two point sets. With an initial assumption that the sensed surface be part of a more complete model surface, the algorithm begins by selecting three dispersed, reliable points on the sensed surface. To find the three corresponding model points, the method uses the principal curvatures and the Darboux frames to restrict the search over the model space. Invariably, many possible model 3-typles will be found. For each hypothesized model 3-tuple, the transformation to match the sensed 3-tuple to the model 3-tuple can be determined. A heuristic search is proposed to single out the optimal transformation in low order time. For realistic object recognition or registration, where the two range images are often extracted from different view points of the model, the earlier assumption that the sensed surface be part of a more complete model surface cannot be relied on. With this, the sensed 3-tuple must be chosen such that the three sensed points lie on the common region visible to both the sensed and model views. We propose an algorithm to select a minimal non-redundant set of 3-tuples such that at least one of the 3-tuples will lie on the overlap. Applying the previous algorithm to each 3-tuple within this set, the optimal transformation can be determined. Experiments using data obtained from a range finder have indicated fast registration for relatively complex test cases. If the optimal registrations between the sensed data (candidate) and each of a set of model data are found, then, for 3D object recognition purposes, the minimal best fit error can be used as the decision rule.     

基于路径轮廓的三维目标识别

骨架能更有效地反映出目标的拓扑结构和细节变化, 因而在三维目标识别中得到广泛应用, 但存在的基于骨架的识别方法均要求骨架端点位于轮廓曲线上, 并且识别精度受骨架端点排序的影响。针对该问题, 提出了一种新的基于路径轮廓的三维目标识别算法。该算法首先定义了一种新的特征点——骨切点, 并根据骨切点在轮廓曲线上的顺序关系, 对骨架端点进行排序; 然后利用路径轮廓对目标轮廓进行分割; 再构造一种新的局部不变特征, 并结合hash表以识别三维目标。实验结果表明, 该算法对存在部分遮挡或缺损的三维目标仍有较好的识别效果。     

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     

Support vector machines for 3D object recognition

Support vector machines (SVMs) have been recently proposed as a new technique for pattern recognition. Intuitively, given a set of points which belong to either of two classes, a linear SVM finds the hyperplane leaving the largest possible fraction of points of the same class on the same side, while maximizing the distance of either class from the hyperplane. The hyperplane is determined by a subset of the points of the two classes, named support vectors, and has a number of interesting theoretical properties. In this paper, we use linear SVMs for 3D object recognition. We illustrate the potential of SVMs on a database of 7200 images of 100 different objects. The proposed system does not require feature extraction and performs recognition on images regarded as points of a space of high dimension without estimating pose. The excellent recognition rates achieved in all the performed experiments indicate that SVMs are well-suited for aspect-based recognition     

Indexing without invariants in 3D object recognition

We present a method of indexing 3D objects from single 2D images. The method does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. This makes hypothesis recovery more efficient in high-dimensional spaces, which are necessary to achieve specificity in large model databases. Search efficiency is maintained in these regimes by the use of best-bin first search. Neighbors recovered from the index are used to generate probability estimates, local within the feature space, which are then used to rank hypotheses for verification. On average, the ranking process greatly reduces the number of verifications required. Our approach is general in that it can be applied to any real-valued feature vector. In addition, it is straightforward to add to our index information from real images regarding the true probability distributions of the feature groupings used for indexing     

An evolutionary approach to the extraction of object construction trees from 3D point clouds

In order to extract a construction tree from a finite set of points sampled on the surface of an object, we present an evolutionary algorithm that evolves set-theoretic expressions made of primitives fitted to the input point-set and modeling operations. To keep relatively simple trees, we use a penalty term in the objective function optimized by the evolutionary algorithm. We show with experiments successes but also limitations of this approach.     

3D object recognition using invariants of 2D projection curves

This paper presents a new method for recognizing 3D objects based on the comparison of invariants of their 2D projection curves. We show that Euclidean equivalent 3D surfaces imply affine equivalent 2D projection curves that are obtained from the projection of cross-section curves of the surfaces onto the coordinate planes. Planes used to extract cross-section curves are chosen to be orthogonal to the principal axes of the defining surfaces. Projection curves are represented using implicit polynomial equations. Affine algebraic and geometric invariants of projection curves are constructed and compared under a variety of distance measures. Results are verified by several experiments with objects from different classes and within the same class.     

Efficient 3D object recognition using foveated point clouds

Recent hardware technologies have enabled acquisition of 3D point clouds from real world scenes in real time. A variety of interactive applications with the 3D world can be developed on top of this new technological scenario. However, a main problem that still remains is that most processing techniques for such 3D point clouds are computationally intensive, requiring optimized approaches to handle such images, especially when real time performance is required. As a possible solution, we propose the use of a 3D moving fovea based on a multiresolution technique that processes parts of the acquired scene using multiple levels of resolution. Such approach can be used to identify objects in point clouds with efficient timing. Experiments show that the use of the moving fovea shows a seven fold performance gain in processing time while keeping 91.6% of true recognition rate in comparison with state-of-the-art 3D object recognition methods.     

A unified approach to moving object detection in 2D and 3D scenes

The detection of moving objects is important in many tasks. Previous approaches to this problem can be broadly divided into two classes: 2D algorithms which apply when the scene can be approximated by a flat surface and/or when the camera is only undergoing rotations and zooms, and 3D algorithms which work well only when significant depth variations are present in the scene and the camera is translating. We describe a unified approach to handling moving object detection in both 2D and 3D scenes, with a strategy to gracefully bridge the gap between those two extremes. Our approach is based on a stratification of the moving object detection problem into scenarios which gradually increase in their complexity. We present a set of techniques that match the above stratification. These techniques progressively increase in their complexity, ranging from 2D techniques to more complex 3D techniques. Moreover, the computations required for the solution to the problem at one complexity level become the initial processing step for the solution at the next complexity level. We illustrate these techniques using examples from real-image sequences     

Isolated 3D object recognition through next view planning

In many cases, a single view of an object may not contain sufficient features to recognize it unambiguously. This paper presents a new online recognition scheme based on next view planning for the identification of an isolated 3D object using simple features. The scheme uses a probabilistic reasoning framework for recognition and planning. Our knowledge representation scheme encodes feature based information about objects as well as the uncertainty in the recognition process. This is used both in the probability calculations as well as in planning the next view. Results clearly demonstrate the effectiveness of our strategy for a reasonably complex experimental set     

Robust affine structure matching for 3D object recognition

We consider model-based object localization based on local geometric feature matching between the model and the image data. The method is based on geometric constraint analysis, working in transformation space. We present a formal method which guarantees finding all feasible matchings in polynomial time. From there we develop more computationally feasible algorithms based on conservative approximations of the formal method. Additionally, our formalism relates object localization, affine model indexing, and structure from multiple views to one another     

BONSAI: 3D object recognition using constrained search

BONSAI, a model-based 3D object recognition system, is described. It identifies and localizes 3D objects in range images of one or more parts that have been designed on a computer-aided-design (CAD) system. Recognition is performed via constrained search of the interpretation tree, using unary and binary constraints (derived automatically from the CAD models) to prune the search space. Attention is focused on the recognition procedure, but the model-building, image acquisition, and segmentation procedures are also outlined. Experiments with over 200 images demonstrate that the constrained search approach to 3D object recognition has an accuracy comparable to that of previous systems