CVGIP: Image Understanding最新文献

We describe a system for obtaining a "generic" parts-based 3D object representation. We use range image data as the input, obtaining a 3D object representation based on 12 geon-like 3D part primitives as the output. The 3D parts-based representation consists of parts detected in the image and their identities. Unlike previous work, we do not make simplifying assumptions such as the availability of perfect line drawings, perfect segmentation, or manual segmentation.We propose a novel method of specifying "generic" 3D parts, i.e., by means of surface adjacency graphs (SAGs). Using the SAGs, we derive an extremely compact multi-view representation of the part primitives, consisting of a total of only 74 views for all 12 primitives. Based on the multi-view representation of parts, we present a method of performing part segmentation from range images, given a good surface segmentation. This method for partsegmentation is more general than common approaches based on Hoffman and Richards′ "principle of transversality." We present two approaches for identifying the parts as one of the 12 3D part primitives. The first approach applies statistical pattern classification methods using parameters estimated by superquadric fitting. Five features derived from the estimated superquadric parameters are used to distinguish between the 12 part primitives. Classification error rates are estimated for k-nearest-neighbor and binary tree classifiers, for real as well as for synthetic range images. The second approach for part identification draws inferences from the distribution of angles between surface normals and the principal axis of a part.We show that intensity data can be used to recover from some misclassifications yielded by the purely range-based methods of part identification. A simple test is applied to check the concavity or convexity of the part silhouette in the intensity image. This serves as a reliable test of whether the part axis is straight orcurved.Results of part segmentation and identification are presented for real range images of several multi-part objects. Our system successfully performs part segmentation and identifies the parts.

Recently, the assumed goal of computer vision, reconstructing a representation of the scene, has been critcized as unproductive and impractical. Critics have suggested that the reconstructive approach should be supplanted by a new purposive approach that emphasizes functionality and task driven perception at the cost of general vision. In response to these arguments, we claim that the recovery paradigm central to the reconstructive approach is viable, and, moreover, provides a promising framework for understanding and modeling general purpose vision in humans and machines. An examination of the goals of vision from an evolutionary perspective and a case study involving the recovery of optic flow support this hypothesis. In particular, while we acknowledge that there are instances where the purposive approach may be appropriate, these are insufficient for implementing the wide range of visual tasks exhibited by humans (the kind of flexible vision system presumed to be an end-goal of artificial intelligence). Furthermore, there are instances, such as recent work on the estimation of optic flow, where the recovery paradigm may yield useful and robust results. Thus, contrary to certain claims, the purposive approach does not obviate the need for recovery and reconstruction of flexible representations of the world.

This paper describes a novel method for the estimation of point correspondences on a surface undergoing conformal nonrigid motion based on changes in its Gaussian curvature. The use of Gaussian curvature in nonrigid motion analysis is justified by its invariancy towards rigid motion and the type of surface parameterization. Input to the algorithm is the set of 3D points before and after the motion. We deal with a restricted class of nonrigid motion called conformal motion. In conformal motion, the stretching is equal in all directions, but different at different points. Small motion assumption is utilized to hypothesize all possible point correspondences. Curvature changes are then computed for each hypothesis. Finally, the error between computed curvature changes and the one predicted by the conformal motion assumption is calculated. The hypothesis with the smallest error gives point correspondences between consecutive time frames. The algorithm requires calculation of the Gaussian curvature at points on surface before and after the motion. It also requires computation of the coefficients of the first fundamental form at points on surface before the motion. Estimation of point correspondences and stretching can also be refined so as to reduce the error introduced by sampling. Simulations are performed on an ellipsoidal data to illustrate performance and accuracy of derived algorithms. Then, the proposed algorithm is applied to volumetric CT data of the left ventricle (LV) of a dog′s heart. Stretching of the LV wall during its expansion and contraction phases is depicted along with the estimated point correspondences. Stretching comparisons are made between the normal and abnormal LV.

In Tarr and Black′s paper it is stated that computer vision research should be based on reconstruction, as it offers the most promising framework for achieving insight into human visual cognition. It is further stated that it is in agreement with evolution. The competing school, the purposive, is considered too specific and relevant mainly for construction of robotic related systems with a limited functionality. In this paper it is argued that the two schools should not be viewed as competing, but rather as complementary. The reconstruction approach is used for research in vision functionalities, which may be combined into operational systems through a purposive analysis from a global point of view. Such a combined approach to vision is necessary for addressing critical issues such as continuous operation and achievement of specific visual tasks, while maintaining the generality needed to obtain insight into visual cognition.