A system is described for real-time motion tracking of 3-D objects, including those with variable internal parameters. Unlike most previous work on model-based motion tracking, this system provides for the integrated ...
详细信息
ISBN:
(纸本)0818620579
A system is described for real-time motion tracking of 3-D objects, including those with variable internal parameters. Unlike most previous work on model-based motion tracking, this system provides for the integrated treatment of matching and measurement errors during motion tracking. These two sources of error have very different distributions and must be handled by separate computational mechanisms. These errors can be treated in an integrated way by using the computation of variance in predicted feature measurements to greatly decrease the amount of search required for subsequent matching. In return, the search process is used to eliminate the need to treat outliers during the analysis of measurement errors. The resulting system can robustly track models with many degrees of freedom while running on relatively inexpensive hardware. These same techniques can be used to speed verification during model-based recognition, and they point the way to merging of systems for recognition and motion tracking.
The authors adopted a model-based approach, where the shape of the object is defined in terms of several mini-templates. The mini-templates are abstract descriptions of simple geometric features like arcs and corners....
详细信息
ISBN:
(纸本)0818620579
The authors adopted a model-based approach, where the shape of the object is defined in terms of several mini-templates. The mini-templates are abstract descriptions of simple geometric features like arcs and corners. Relationships between mini-templates are not rigid. Rather, they are represented by springs that allow deformation of a template in terms of its size and orientation. Cost functionals are determined empirically. The authors expect their system to generate candidate regions in a given photograph associated with a rank of its goodness.
An iterative algorithm is presented that simultaneously recovers the actual shape and the actual reflectance from the pseudo estimates. The recovery algorithm works on Lambertian surfaces of arbitrary shape with possi...
详细信息
ISBN:
(纸本)0818620579
An iterative algorithm is presented that simultaneously recovers the actual shape and the actual reflectance from the pseudo estimates. The recovery algorithm works on Lambertian surfaces of arbitrary shape with possibly varying and unknown reflectance. The general behavior of the algorithm and its convergence properties are discussed. Both simulation and experimental results are included to demonstrate the accuracy and stability of the algorithm.
An examination is made of the problem of predicting when a model surface patch on a three-dimensional object is totally back-facing, and hence need not be searched for during object recognition. Examining every point ...
详细信息
ISBN:
(纸本)0818620579
An examination is made of the problem of predicting when a model surface patch on a three-dimensional object is totally back-facing, and hence need not be searched for during object recognition. Examining every point on the surface patch is inelegant and impractical, yet difficulties arise with curved surface patches. The authors conclude that visibility can be determined from an analysis of the surface orientation at the patch boundary for a wide class of model surface patch types (i.e. those having constant principal curvature signs), under orthographic projection.
A procedure is presented for recognizing an object from its range data. A set of object surface data points are segmented into triangular patches using a small number of knot points. These knot points are placed by th...
详细信息
ISBN:
(纸本)081861966X
A procedure is presented for recognizing an object from its range data. A set of object surface data points are segmented into triangular patches using a small number of knot points. These knot points are placed by the local adjustment technique. For the resulting triangulated surface model, high-level edge lines are extracted using unit normal vectors of the triangular patches. This set of high-level primitives is used to construct a graph structure for each object. Experimental results are presented for a set of objects with salient features.
This work introduces an approach to build a qualitative description of scenes along a route, which is used in route recognition by a mobile robot. The description consists of a series of landmarks autonomously selecte...
详细信息
ISBN:
(纸本)0818620579
This work introduces an approach to build a qualitative description of scenes along a route, which is used in route recognition by a mobile robot. The description consists of a series of landmarks autonomously selected by the robot from a panoramic view, which has been generated as a visual memory of scenes along routes. The basic idea to bridge the quantitative panoramic view to qualitative landmarks is to examine the 'distinctiveness' of patterns in the image and select landmarks from unique patterns that are remarkable by which to navigate.
The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute o...
详细信息
ISBN:
(纸本)0818690275
The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute of an object, called a footprint, for the purpose of hashing. The recognition strategy is to match the given contour curve against all model objects and select the best matching. The recognition procedures are divided into reading each object picture, retrieving a footprint, building a model objects database, finding break points, and matching. Associated techniques, such as border tracking with chain code, setting a footprint hashing table, and connecting an orientational linked list, are also discussed.
The authors present the formulation of an improved neural architecture, a modified adaptive resonance theory (ART), for the enhancement of binary images in the presence of noise. The two-layer ART model developed by G...
详细信息
ISBN:
(纸本)0818620846
The authors present the formulation of an improved neural architecture, a modified adaptive resonance theory (ART), for the enhancement of binary images in the presence of noise. The two-layer ART model developed by G. A. Carpenter and S. Grossberg (1987) is further incorporated into a four-layer network. The operation and performance of ART1 in classifying binary input patterns is first investigated. Based on ART1, a noise filtering architecture is devised whereby preestablished recognition categories are used as region or contour detection exemplars in order to fill in the gaps and smooth the contours of a noisy binary image without any prior knowledge of the image itself.
An algorithm is described which produces the extraction of an object's contours in a binary image while storing only two raster lines at a time during processing. The major data structure used is a block adjacency...
详细信息
ISBN:
(纸本)0818690275
An algorithm is described which produces the extraction of an object's contours in a binary image while storing only two raster lines at a time during processing. The major data structure used is a block adjacency graph which occupies much less space (typically one hundredth) than the original image. Because this algorithm has very low costs of memory space and processing time, it is a powerful tool for processing large-size engineering drawings. Applications of the method to the recognition of some loop-structure logical symbols are described.
The recognition of unknown shapes by maximum-likelihood methods is considered. The contour of a shape is represented by its centroidal profile, and it is fitted by a circular autoregressive model. Two different shape ...
详细信息
ISBN:
(纸本)0818690275
The recognition of unknown shapes by maximum-likelihood methods is considered. The contour of a shape is represented by its centroidal profile, and it is fitted by a circular autoregressive model. Two different shape recognition problems are considered: the decision on the similarity of two unknown shapes and the classification of an unknown shape as one of many known shapes. Maximum-likelihood decision rules for these two cases are derived. The decision rules are invariant to translation, rotation, and size change after normalizing the estimates. The developed algorithms are used to classify eight classes of machine parts and eight classes of aircraft shapes. For each class, 60-80 samples are generated by rotating and dilating the original shape. In the experiment, more than 98% of the machine parts are classified correctly, and more than 97% of the aircraft shapes are correctly classified. This result is better than the results of previous model-based approaches.
暂无评论