this paper presents a generalised technique for parallelising embedded computer vision and patternrecognition applications and shows how it has been applied to the recognition of handwritten postcodes on envelopes. T...
详细信息
this paper presents a generalised technique for parallelising embedded computer vision and patternrecognition applications and shows how it has been applied to the recognition of handwritten postcodes on envelopes. the technique is based upon the utilisation of pipelines of processor farms (PPF), and is applicable to any embedded system with continuous input/output data streams. the postcode recogniser combines temporal multiplexing and data parallelism to achieve a speedup of 21.4 compared withthe original sequential application, using a total of 52 transputers.
A simple vision method to determine the 3-D location and shape parameters of a cone by using structured light is presented. the key concept in the proposed method is to convert the complex curved stripe pattern to an ...
详细信息
ISBN:
(纸本)0818662654
A simple vision method to determine the 3-D location and shape parameters of a cone by using structured light is presented. the key concept in the proposed method is to convert the complex curved stripe pattern to an equivalent, but simpler, linear stripe pattern. the conic surface patch lying between the two visible silhouette edges is replaced by the plane defined by the two silhouette edges that cuts the cone. the appropriate geometric models are given to compute the cone axis and shape parameters representing the height of the cone and the radius of the cone base.
We describe a novel and general approach for the detection of facial features such as the eyes. the approach is based on biologically motivated processing and classification schemes. the processing involves retinal sa...
详细信息
We describe a novel and general approach for the detection of facial features such as the eyes. the approach is based on biologically motivated processing and classification schemes. the processing involves retinal sampling along P-type lattices and micro saccades, while classification is done using the self-organizing feature map (SOFM). the optimal set of eye templates is found by an enhanced SOFM approach using cross-validation training. Experimental results are presented to prove the feasibility of our approach.
A new method for videoconferencing using the concept of spatially varying sensing is introduced. Various techniques are discussed for combining information obtained from multiple points-of-interest (foveae) in an imag...
详细信息
A new method for videoconferencing using the concept of spatially varying sensing is introduced. Various techniques are discussed for combining information obtained from multiple points-of-interest (foveae) in an image. A fovea can be used to follow a moving object of interest as well. A fast videoconferencing prototype for desktop computers is also described.
We present a simple yet powerful method to perform point-to-point matching between two images. the method uses an evidence measure, whose value for a given displacement reflects boththe similarity between two locatio...
详细信息
We present a simple yet powerful method to perform point-to-point matching between two images. the method uses an evidence measure, whose value for a given displacement reflects boththe similarity between two locations and the confidence in a correct match. the measure is based on the gradient fields of the images, and can be computed quickly and in parallel. Accumulating the evidence measure for different displacements allows (1) stable computation, of correspondences without smoothing across motion boundaries, and (2) detection of dominant motions. the method works well both on highly textured images and on images containing regions of uniform intensities, and can be used for a variety of applications, including stereo, motion, and object tracking.
Nonmetric multidimensional scaling (MDS) is a family of algorithms that allow one to derive a quantitative representation of data from a set of qualitative measurements which must satisfy certain simple constraints. A...
详细信息
Nonmetric multidimensional scaling (MDS) is a family of algorithms that allow one to derive a quantitative representation of data from a set of qualitative measurements which must satisfy certain simple constraints. As a tool for vision, MDS combines the advantages of both qualitative and classical approaches, by relying, on the one hand, on an ordinal-scale input representation, and by supporting, on the other hand, the extraction of metric information. the present paper illustrates an application of MDS to the recovery of depth from the rank order of binocular disparity differences for a set of points. Our results indicate that multidimensional scaling constitutes a promising approach to the integration of biological and computational insights into the problem of depth perception.
Partitioning a set of data points which are characterized by their mutual dissimilarities instead of an explicit coordinate representation is a difficult, NP-hard combinatorial optimization problem. the authors formul...
详细信息
Partitioning a set of data points which are characterized by their mutual dissimilarities instead of an explicit coordinate representation is a difficult, NP-hard combinatorial optimization problem. the authors formulate this optimization problem of a pairwise clustering cost function in the maximum entropy framework using a variational principle to derive corresponding data partitionings in a d-dimensional Euclidian space. this approximation solves the embedding problem and the grouping of these data into clusters simultaneously and in a selfconsistent fashion.
Regularization looks for an interpolating function which is close to the data and also "smooth". this function is obtained by minimizing an error functional which is the weighted sum of a "fidelity term...
详细信息
Regularization looks for an interpolating function which is close to the data and also "smooth". this function is obtained by minimizing an error functional which is the weighted sum of a "fidelity term" and a "smoothness term". However, using only one set of weights does not guarantee that this function will be the MAP estimate. One has to consider all possible weights in order to find the MAP function. Also, using only one combination of weights makes the algorithm very sensitive to the data. the solution suggested here is through the Bayesian approach: a probability distribution over all weights is constructed and all weights are considered when reconstructing the function or computingthe expectation of a linear functional on the function space.
In this paper, we identify the computational requirements for structural pattern analysis, particularly for the operations of spatial grouping and matching. We describe two such algorithms that are in wide use here at...
详细信息
In this paper, we identify the computational requirements for structural pattern analysis, particularly for the operations of spatial grouping and matching. We describe two such algorithms that are in wide use here at USC and discuss approaches to reducing their execution times via parallel implementation. We provide brief descriptions and results of two research projects geared generally, toward the parallel implementation of computer vision systems and specifically, towards these algorithms.
this paper presents a hierarchical motion estimation method considering both a large spatial and temporal support. the problem of motion estimation is formulated as a time-varying parameter estimation problem. the mai...
详细信息
this paper presents a hierarchical motion estimation method considering both a large spatial and temporal support. the problem of motion estimation is formulated as a time-varying parameter estimation problem. the main advantage of the proposed algorithm is its ability to constrain the computation of the flow field spatially and temporally at the same time, by defining each motion parameter as a linear combination of some orthogonal time functions. the number of time basis varies according to the complexity of the movement and is determined automatically by means of a multiresolution approach and of statistical tests. We also present two different applications which underline the validity of the chosen approach.
暂无评论