A new nonlinear feature extraction method is presented for classification and pose estimation of objects from single views. The feature extraction method is called the maximum representation and discrimination feature...
详细信息
ISBN:
(纸本)081942983X
A new nonlinear feature extraction method is presented for classification and pose estimation of objects from single views. The feature extraction method is called the maximum representation and discrimination feature (MRDF) method. The nonlinear MRDF transformations to use are obtained in closed form, and offer significant advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We consider MRDFs on image data, provide a new a-stage nonlinear MRDF solution, and show it specializes to well-known linear and nonlinear image processing transforms under certain conditions. We show the use of the MRDF in estimating the class and pose of images of rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show new results with better classification and pose estimation accuracy than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.
One approach to stereo matching is to use different local features to find correspondences. The selection of an optimum feature set is the content of this paper. An operational software tool based on the principle of ...
详细信息
ISBN:
(纸本)081942983X
One approach to stereo matching is to use different local features to find correspondences. The selection of an optimum feature set is the content of this paper. An operational software tool based on the principle of comparing feature vectors is used for stereo matching. A relatively large set of different local features is sought for optimum combinations of 6-10 of them. This is done by a genetic process that uses an intrinsic quality criterion that evaluates the correctness of each individual match. The convergence of the genetic feature selection process is demonstrated on a real stereo pair of a tunnel surface. Four areas were used for individual optimization. After several hundred generations for each of the areas, it is shown that the identified feature sets result in a considerably better stereo matching result than the currently used features, which were the result of an initial manual choice. The experiments described in this paper use a "super-set" of 145 features for every pixel, which are created by filtering the image with convolution kernels (averaging, Gaussian filters, bandpass, highpass), median filters and Gabor kernels. From these 145 filters, the genetic feature selection process selects an optimal set of operators. Using the selected filters results in a 15% improvement of the matching accuracy and robustness.
robots operating in an unstructured environment need high level modeling of their operational space in order to plan a path from an initial position to a desired goal. A fuzzy approach to evaluate each unit region on ...
详细信息
robots operating in an unstructured environment need high level modeling of their operational space in order to plan a path from an initial position to a desired goal. A fuzzy approach to evaluate each unit region on a grid map by a certain value of transition cost is proposed. The method employs fuzzy granulation of information on various terrain features and their combination based on a fuzzy neural network.
A strategy for identifying, measuring, and duplicating machined parts using an endpoint open loop (EOL) position based, visual servo robot is presented. The procedure is demonstrated using the representative, commerci...
详细信息
A strategy for identifying, measuring, and duplicating machined parts using an endpoint open loop (EOL) position based, visual servo robot is presented. The procedure is demonstrated using the representative, commercially important, problem of duplicating keys for automobiles. The tasks completed for this application are: identify the blank type of the original;measure the unique cut pattern;correct deviations;and grind the duplicate.
robots relying on vision as a primary sensor frequently need to track common objects such as people, cars, and tools in order to successfully perform autonomous navigation or grasping tasks. These objects may comprise...
详细信息
robots relying on vision as a primary sensor frequently need to track common objects such as people, cars, and tools in order to successfully perform autonomous navigation or grasping tasks. These objects may comprise many visual parts and attributes, yet image-based tracking algorithms are often keyed to only one of a target's identifying characteristics. In this paper, we present a framework for sharing information among disparate state estimation processes operating on the same underlying visual object. Well-known techniques for joint probabilistic data association are adapted to yield increased robustness when multiple trackers attuned to different visual cues are deployed simultaneously. We also formulate a measure of tracker confidence, based on distinctiveness and occlusion probability, which permits the deactivation of trackers before erroneous state estimates adversely affect the ensemble. We will discuss experiments using color-region, and snake-based tracking in tandem that demonstrate the efficacy of this approach.
Three-dimensional multilayer phase gratings (nuclear layers in the human retina) of oscillating cells positioned in the image plane of a monocular optical imaging system transform tight double cones by diffraction and...
详细信息
ISBN:
(纸本)081942983X
Three-dimensional multilayer phase gratings (nuclear layers in the human retina) of oscillating cells positioned in the image plane of a monocular optical imaging system transform tight double cones by diffraction and pulsation (quantization) into the reciprocal space behind the grating (Fourier-space in the Fresnel-nearfield). This effect we call OPTORETINA not only guarantees the transformation of the physical stimuli parameters (intensity/wavelength) in the visible spectrum into three chromatically tuned adaptive RGB-color channels (diffraction orders with Brightness-Hue-Saturation aspects) and of object. distances in 3D-space into spatial frequencies or temporal phase differences in reciprocal space (the MULTIDIST grating optical sensors developed at CORRSYS). The 3D-grating, acting as a spatiotemporal frequency and spectral filter, contributes to image pre-processing in Fourier-space. it allows patchwise Fourier-analysis in the Fresnel-nearfield based on weighted Patterson maps of centrosymmetric hexagonal multilayer gratings. Spectral/temporal modulation and spatial frequency analysis seem to be orthogonal to each other as in audition. The OPTORETINA with its cellular diffractive 3D-gratings and their power spectra illustrates a specific part of cortical 4D-spatiotemporal processing. A cortical modulator becomes relevant for temporal coincidence detection and spectral/spatiotemporal correlation in complex image processing, relating multimodal stimulus parameters to internal timing.
An algorithm consisting of an artificial neural network and phase only match filter (POMF) method to tracking an object in a series of satellite images with variant intensity level is proposed. The notable adaptive re...
详细信息
An algorithm consisting of an artificial neural network and phase only match filter (POMF) method to tracking an object in a series of satellite images with variant intensity level is proposed. The notable adaptive resonance theory (ART) neural network is used as a high frequency noise filter for the POMF. The algorithm is examined by means of several satellite images. From the experimental results, the proposed method demonstrates that the performance of POMF can be successfully improved by reducing the high frequent noise of the background in the satellite images.
Scene segmentation is a pre-processing step for many vision systems. We are concerned with segmentation as a precursor to 3-D scene modeling. Segmentation of a scene for this purpose usually involves dividing an image...
详细信息
ISBN:
(纸本)081942983X
Scene segmentation is a pre-processing step for many vision systems. We are concerned with segmentation as a precursor to 3-D scene modeling. Segmentation of a scene for this purpose usually involves dividing an image into areas that are relatively uniform in some value (e.g. intensity, range, or curvature). This single segmented image represents the analogous segmented scene. This paper presents a segmentation method that uses features to indicate boundaries or edges between regions. We incorporate features from multiple image types to obtain an more accurate segmentation of objects or object parts in the scene. Multiple features are not only combined directly to improve segmentation results, but they are also used to guide a smoothing operation. This smoothing technique preserves features representing edges while smoothing noise in the images. The segmentation method is based on applying a watershed algorithm to a fuzzy feature map. A fuzzy feature map being any image containing fuzzy values representing degree of membership in a particular feature class. The first step in obtaining the fuzzy feature map involves smoothing noise from the image pair. We apply an anisotropic diffusion algorithm to both images. This algorithm smooths noise in the images while preserving changes in range, intensity, and surface normal. We create three fuzzy feature maps from the smoothed range and intensity image pair: gradient of the range image, gradient of the intensity image, sind gradient of the surface normal of the range image. We fuse these fuzzy feature maps to create a fuzzy feature map of edges. This map includes both step and crease edges. Where step edges are defined as discontinuities in range and crease edges are discontinuities in surface normal of range. We derive a segmentation from this fuzzy edge map by application of a morphological watershed algorithm. We present results from analysis of real images.
This paper addresses a method for implementation of some basic geometric transformation, namely rotation and scale, on 1D parallel SIMD computers. Solutions to solve many implementation details such as 2D image scanni...
详细信息
This paper addresses a method for implementation of some basic geometric transformation, namely rotation and scale, on 1D parallel SIMD computers. Solutions to solve many implementation details such as 2D image scanning with 1D machine, the floating point arithmetic simulation and an approximation of the transformed pixel spatial co-ordinates are proposed. The proposed approach tolerates up to ±15° rotation and up to ±50% continue scale changes between images. Those transformations can be used for construction of robust matching primitives useful for robot applications. The evaluation of the proposed method, on SYMPATI2, a French 1D parallel computer (designed by CEA,LETI) is reported.
Linear models are a popular tool to characterize the performance of active vision systems. They cannot, however, capture the nonlinear limits of the system performance that arise out of the physical limitations of the...
详细信息
Linear models are a popular tool to characterize the performance of active vision systems. They cannot, however, capture the nonlinear limits of the system performance that arise out of the physical limitations of the real system. We examine how the finite field of view and the limited motor torque impose bounds on the linear operation of an active vision system in a fixation task. We derive the bounds by analyzing a real active vision system and measuring its response to repeatable and controllable target motions generated by a robot arm. The knowledge of the operational bounds can guide us in deciding which aspects of the active vision system to improve for better overall performance.
暂无评论