Owen Robert Mitchell

Weighted selection of image features for resolved rate visual feedback control

The authors develop methodologies for the automatic selection of image features to be used to visually control the relative position and orientation (pose) between the end-effector of an eye-in-hand robot and a workpiece. A resolved motion rate control scheme is used to update the robots pose based on the position of three features in the cameras image. The selection of these three features depends on a blend of image recognition and control criteria. The image recognition criteria include feature robustness, completeness, cost of feature extraction, and feature uniqueness. The control criteria include system observability, controllability, and sensitivity. A weighted criteria function is used to select the combination of image features that provides the best control of the end-effector of a general six-degrees-of-freedom manipulator. Both computer simulations and laboratory experiments on a PUMA robot arm were conducted to verify the performance of the feature-selection criteria. >

Threshold decomposition of gray-scale morphology into binary morphology

Recently, a superposition property called threshold decomposition and another property called stacking were introduced and shown to apply successfully to gray-scale morphological operations. This property allows gray-scale signals to be decomposed into multiple binary signals. The signals are processed in parallel, and the results are combined to produce the desired gray-scale result. The authors present the threshold decomposition architecture and the stacking property that allows the implementation of this architecture. Gray-scale operations are decomposed into binary operations. This decomposition allows gray-scale morphological operations to be implemented using only logic gates in VLSI architectures that can significantly improve speed as well as give theoretical insight into the operations. >

Precision edge contrast and orientation estimation

The contrast and orientation estimation accuracy of several edge operators that have been proposed in the literature is examined both for the noiseless case and in the presence of additive Gaussian noise. The test image is an ideal step edge that has been sampled with a square-aperture grid. The effects of subpixel translations and rotations of the edge on the performance of the operators are studied. It is shown that the effect of subpixel translations of an edge can generate more error than moderate noise levels. Methods with improved results are presented for Sobel angle estimates and the Nevatia-Babu operator, and theoretical noise performance evaluations are also provided. An edge operator based on two-dimensional spatial moments is presented. All methods are compared according to worst-case and RMS error in an ideal noiseless situation and RMS error under various noise levels. >

Partial shape recognition using dynamic programming

A partial-shape-recognition technique utilizing local features described by Fourier descriptors is introduced. A dynamic programming formulation for shape matching is developed, and a method for comparison of match quality is discussed. This technique is shown to recognize unknown contours that may be occluded or that may overlap other objects. Precise scale information is not required, and the unknown objects may appear at any orientation with respect to the camera. The segment-matching dynamic programming method is contrasted with other sequence-comparison techniques that utilize dynamic programming. Experimental results are discussed that indicate that partial contours can be recognized with reasonable accuracy. >

Analysis of three-dimensional movement using Fourier descriptors

Recent improvements in Fourier descriptor (FD) shape analysis enable rapid identification of three-dimensional objects using FD feature vectors derived from their boundaries. In three-dimensional shape analysis, it is essential to preserve all information to achieve good performance. In the real-time situation it is, of course, equally important to use a computationally efficient method. The method of three-dimensional shape analysis using normalized Fourier descriptors is information preserving, yet is as fast as previous suboptimum methods. In addition, the feature vector has a linear property, allowing to interpolate between library projections and effectively define a continuum of library projections rather than a finite set. This method is applied to the analysis of sequential data varying in resolution and orientation relative to the camera. Computational considerations are discussed, and it is seen that real-time implementation of the method is feasible.

Three-Dimensional Shape Analysis Using Local Shape Descriptors

The three-dimensional shape analysis problem is a very demanding test of shape analysis algorithms. Previous approaches to the problem have employed global features such as moments and Fourier descriptors. Global features lack the capacity for solving the partial shape recognition problem, in which only part of the unknown shape is available. Previous approaches to local shape analysis have employed structural (syntactic) methods, but these methods have so far failed to solve the three-dimensional problem. This paper describes a hybrid structural/statistical local shape analysis algorithm which is applied to the three-dimensional problem.

Model-based visual feedback control for a hand-eye coordinated robotic system

The integration of a single camera into a robotic system to control the relative position and orientation between the robots end-effector and a moving part in real time is discussed. Only monocular vision techniques are considered because of current limitations in the speed of computer vision analysis. The approach uses geometric models of both the part and the camera, as well as the extracted image features, to generate the appropriate robot control signals for tracking. Part and camera models are also used during the teaching stage to predict important image features that appear during task completion.<<ETX>>

Detection and sub-pixel location of photogrammetric targets in digital images☆

Abstract Data consist of aerial digital images with ground targets in the form of crosses of different dimensions and orientations. Location and recognition of the targets relies on Fourier descriptors and on two-dimensional moments. Further processing employs least squares adjustment of the target shape in order to precisely determine the position ( X and Y ) and orientation θ of each cross to a fraction of a pixel accuracy. Results are given from tests with synthetic crosses on a real terrain digital data base. Accuracies achieved have reached to within 0.03–0.05 pixel. Digital image compression has shown to cause cross targets to shift in location by as much as 0.5 pixel.

Cerebral processing of spatial and verbal-analytic tasks: An EEG study

Abstract Cerebral processing was investigated as a function of cognitive task and spatial ability. EEGs were recorded while 38 subjects, ages 16–18, performed four tasks. The production requirement of the tasks varied along a spatial-analytic continuum while the perceptual requirement was held constant for three of the tasks and was nil for the fourth. Task related alpha power ratio differences were observed, supporting the hypothesis that hemispheric processing is a function of the task processing demands and not just related to the perceptual requirements.

Image segmentation using a local extrema texture measure

Abstract An image segmentation technique is proposed which uses a texture measure that counts the number of local extrema in a window centered at each picture point. Four gray level pictures are derived, each of which represents a texture or gray level property of the original image. These intermediate pictures are used to derive the number of segments in which to divide the original image. The segmentation is then performed by assigning each pixel in the original image to a region by using a four-dimensional distance measure on the intermediate pictures, comparing each location to each selected segment. This process is then repeated in a hierarchical structure using decreasing window sizes so that smaller regions within the larger ones are defined. The computations required are amenable to real-time video implementation using state-of-the-art devices.