It is suggested that non-smooth or complex boundaries are processed by the visual system so as to obtain a simple abstract description, called contour texture, which contains much less information than that provided b...
详细信息
It is suggested that non-smooth or complex boundaries are processed by the visual system so as to obtain a simple abstract description, called contour texture, which contains much less information than that provided by the location of all points of the contour. A discussion is presented of what the nature of the contour texture of a curve is and its relation with two-dimensional texture, which the author contends should be thought of as a separate concept. Several applications are suggested, and an implemented filter-based scheme is presented.< >
A unified model for camera calibration is presented. The model does not assume any explicit form of imaging process and can perform linear back projection while considering all lens distortions. This model is well sui...
详细信息
A unified model for camera calibration is presented. The model does not assume any explicit form of imaging process and can perform linear back projection while considering all lens distortions. This model is well suited to stereo reconstruction. It has been shown that the original two-plane model, the linear and nonlinear pin hole model, can all be realized as special cases of this model. With the two-plane model, optimal orientation of the two reference planes can be found intuitively.< >
Current methods for registering image regions perform well for simple transformations or large image regions. The author presents a new method that is better able to handle small image regions as they deform with nonl...
详细信息
Current methods for registering image regions perform well for simple transformations or large image regions. The author presents a new method that is better able to handle small image regions as they deform with nonlinear transformations. He introduces difference decomposition, a novel approach to solving the registration problem. The method is a generalization of previous methods and can better handle nonlinear transforms. Although the methods are general, he focuses on projective transformations and introduces piecewise-projective transformations for modeling the motions of non-planar objects. He concludes with examples from a prototype implementation.
We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without...
详细信息
We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without the use of markers. The pose-recovery problem is formulated as a search problem and entails finding the pose parameters of a graphical human model whose synthesized appearance is most similar to the actual appearance of the real human in the multi-view images. The models used for this purpose are acquired from the images. We use a decomposition approach and a best-first technique to search through the high dimensional pose parameter space. A robust variant of chamfer matching is used as a fast similarity measure between synthesized and real edge images. We present initial tracking results from a large new Humans-in-Action (HIA) database containing more than 2500 frames in each of four orthogonal views. They contain subjects involved in a variety of activities, of various degrees of complexity, ranging from the more simple one-person hand waving to the challenging two-person close interaction in the Argentine Tango.
Recently applying artificial intelligence, machine learning and data mining techniques to intrusion detection system are increasing. But most of researches are focused on improving the performance of classifier. Selec...
详细信息
The findpath problem is the problem of moving an object to the desired position and orientation while avoiding obstacles. The authors present an approach to this problem using a potential-field representation of obsta...
详细信息
The findpath problem is the problem of moving an object to the desired position and orientation while avoiding obstacles. The authors present an approach to this problem using a potential-field representation of obstacles. A potential function similar to an electrostatic potential is assigned to each obstacle, and the topological structure of the free space is derived in the form of minimum potential valleys. A path specified by a subset of valley segments and associated object orientations, which minimizes a heuristic estimate of path length and the chance of collision, is selected as the initial guess of the solution. Then, the selected path as well as the orientation of the moving object along the path is modified to minimize a defined cost of the path. Findpath problems possessing three different levels of difficulty are identified. Path optimization is performed in up to three stages, according to the level of difficulty of the problem. These three stages are addressed by three separate algorithms which are automatically selected. The performance of the algorithms is illustrated.< >
A solution to the correspondence problem using constraint satisfaction is described. It uses a real-time line-fitting algorithm to detect changes in a point's motion parameters as they happen. A trajectory is hypo...
详细信息
A solution to the correspondence problem using constraint satisfaction is described. It uses a real-time line-fitting algorithm to detect changes in a point's motion parameters as they happen. A trajectory is hypothesized for a single point's motion. Since the event detected may be wrong, multiple trajectories are hypothesized for each point. A correspondence is drawn from the set of hypothesized trajectories. The algorithm is robust, working on noisy and non-rigid motion data, and does not use false precision.< >
A mathematical framework for the solution of statistical inference problems on a class of random sets is proposed. It is based on a new definition of expected pattern. The least-mean-difference estimator (restoration ...
详细信息
A mathematical framework for the solution of statistical inference problems on a class of random sets is proposed. It is based on a new definition of expected pattern. The least-mean-difference estimator (restoration filter) is proved, under certain conditions, to be equivalent to the minimization of the measure of size (area) of the set-difference between the original pattern and the expected pattern of the estimated (restored) pattern. Consequently, it is proved that, under certain conditions, if the estimator (restoration filter) is unbiased, then it is the least mean difference estimator (restoration filter).< >
A methodology for classifying syntactic patterns that performs a branch-and-bound search over a set of prototypes is proposed. The prototypes are first clustered hierarchically and the search is performed over the hie...
详细信息
A methodology for classifying syntactic patterns that performs a branch-and-bound search over a set of prototypes is proposed. The prototypes are first clustered hierarchically and the search is performed over the hierarchy. The proposed technique is applied to a patternrecognition system in which images are described by the sequence of features extracted from the chain codes of their contours. A rotationally invariant string distance measure is defined that compares two feature strings. The methodology discussed is compared to a nearest neighbor classifier that uses 12000 prototypes. The proposed technique decreases the time required to recognize a pattern by 93% and maintains a recognition rate of greater than 90%.< >
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion reconstruction. Learning progresses in...
详细信息
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion reconstruction. Learning progresses in alternative stages of self-training that optimize the probability of the image evidence: the recognition model is tunned using samples from the generative model and the generative model is optimized to produce inferences close to the ones predicted by the current recognition model. At equilibrium, the two models are consistent. During on-line inference, we scan the image at multiple locations and predict 3d human poses using the recognition model. But this implicitly includes one-shot generative consistency feedback. The framework provides a uniform treatment of human detection, 3d initialization and 3d recovery from transient failure. Our experimental results show that this procedure is promising for the automatic reconstruction of human motion in more natural scene settings with background clutter and occlusion.
暂无评论