Global feature space neural network for active computer vision

We advance new active computer vision algorithms based on the Feature space Trajectory (FST) representations of objects and a neural network processor for computation of distances in global feature space. Our algorithms classify rigid objects and estimate their pose from intensity images. They also indicate how to automatically reposition the sensor if the class or pose of an object is ambiguous from a given viewpoint and they incorporate data from multiple object views in the final object classification. An FST in a global eigenfeature space is used to represent 3D distorted views of an object. Assuming that an observed feature vector consists of Gaussian noise added to a point on the FST, we derive a probability density function for the observation conditioned on the class and pose of the object. Bayesian estimation and hypothesis testing theory are then used to derive approximations to the maximum a posterioriprobability pose estimate and the minimum probability of error classifier. Confidence measures for the class and pose estimates, derived using Bayes theory, determine when additional observations are required, as well as where the sensor should be positioned to provide the most useful information.     

Robust regression methods for computer vision: A review

Regression analysis (fitting a model to noisy data) is a basic technique in computer vision, Robust regression methods that remain reliable in the presence of various types of noise are therefore of considerable importance. We review several robust estimation techniques and describe in detail the least-median-of-squares (LMedS) method. The method yields the correct result even when half of the data is severely corrupted. Its efficiency in the presence of Gaussian noise can be improved by complementing it with a weighted least-squares-based procedure. The high time-complexity of the LMedS algorithm can be reduced by a Monte Carlo type speed-up technique. We discuss the relationship of LMedS with the RANSAC paradigm and its limitations in the presence of noise corrupting all the data, and we compare its performance with the class of robust M-estimators. References to published applications of robust techniques in computer vision are also given.     

Two trajectory tracking control methods for space hyper-redundant cable-driven robots considering model uncertainty

Multibody System Dynamics - Space hyper-redundant cable-driven robots (SHCDRs) have a slender body structure and high dexterity, which is very suitable for complex and limited unstructured space...     

Parallel programming for computer vision

Two Unix environments developed for programming parallel computers to handle image-processing and vision applications are described. Visx is a portable environment for the development of vision applications that has been used for many years on serial computers in research. Visx was adapted to run on a multiprocessor with modest parallelism by using functional decomposition and standard operating-system capabilities to exploit the parallel hardware. Paragon is a high-level environment for multiprocessor systems that has facilities for both functional decomposition and data partitioning. It provides primitives that will work efficiently on several parallel-processing systems. Paragon's primitives can be used to build special image-processing operations, allowing one's own programming environment to be grown naturally     

New computer vision based Snakes and Ladders algorithm for the safe trajectory of two axis CNC machines

Multi-axis machine production process optimization, automation and intelligence are the key codes of today’s scientific community. Rapid decision and intelligence are becoming more important for precise and safe virtual and real production. Multi-axis CNC production is a high speed machining process that demands less human intervention and high intelligence, to deal with any uncomfortable situation regarding collisions. Current CAM softwares as well as CNC machines are able to detect collisions but are unable to avoid these collisions automatically. This paper aims to make the CAD-CAM/CNC multi-axis safe trajectory generation process optimal, intelligent and automatic, using vision based image processing by the Snakes and Ladders game analogy. Applying the Snakes and Ladders analogy on machine virtual scene (trajectory preparation) and real scene (during production) images gives promising methodology for safe and efficient trajectory generation while avoiding collisions named Snakes and Ladders Analogy for Production Trajectory (SLAPT). Our Rectangular Enveloped Safe and Efficient Trajectory (RESET) algorithm, based on the same principle of the SLAPT methodology is also discussed in this paper. Results include some applications of algorithms on virtual and real machine scene images for the safe and optimized trajectory of tools. This paper focuses on intelligence and optimization of 2D non-functional transversal trajectories of 2-axis machines for production and preparation processes as an initial effort towards the complex safe trajectory generation process (mill-turn).     

Polymorphic-torus architecture for computer vision

A massively parallel fine-grained SIMD (single-instruction multi-data-stream) computer for machine vision computations is described. The architecture features a polymorphic-torus network which inserts an individually controllable switch into every node of the two-dimensional torus such that the network is dynamically reconfigurable to match the algorithm. Reconfiguration is accomplished by circuit switching and is achieved at fine-grained level. Using both the processor coordinate in the torus and the data for reconfiguration, the polymorphic-torus achieves solution time that is superior or equivalent to that of popular vision architectures such as mesh, tree, pyramid and hypercube for many vision algorithms discussed. Implementation of the architecture is given to illustrate its VLSI efficiency     

Joint space trajectory planning for flexible manipulators

A trajectory planning approach for controlling flexible manipulators is proposed. It is demonstrated that choosing actual joint angles as the generalized rigid coordinates is the key to applying the proposed approach. From the observation of the special structure of the input matrix, the concepts of motion-induced vibration and inverse dynamics under a specified motion history of the joints are formed naturally. Based on the above concepts, trajectory planning in joint space is proposed by using the optimization technique to determine the motion of joints along a specified path in joint space or work space and for general point-to-point motion. The motion for each joint is assumed to be in a class consisting of a fifth-order polynomial and a finite terms of Fourier series. This parameterization of motion allows the optimal trajectory planning to be formulated as a standard nonlinear programming problem, which avoids the necessity of solving a two-point-boundary-value problem and using dynamic programming. Setting the accelerations to zero at the initial and the final times is used to obtain smoother motion to reduce the spillover energy into unmodeled high-frequency dynamics. A penalty term on vibration energy contained in the performance index is used to minimize the vibration of the system modeled by lower frequency only. The final simulation results show the effectiveness of the proposed approach and the advantage for proper trajectory planning. © 2995 John Wiley & Sons, Inc.     

CAGD-based computer vision

The authors explore the connection between CAGD (computer-aided geometric design) and computer vision. A method for the automatic generation of recognition strategies based on the 3-D geometric properties of shape has been devised and implemented. It uses a novel technique to quantify the following properties of features which compose models used in computer vision: robustness, completeness, consistency, cost, and uniqueness. By utilizing this information, the automatic synthesis of a specialized recognition scheme, called a strategy tree, is accomplished. Strategy trees describe, in a systematic and robust manner, the search process used for recognition and localization of particular objects in the given scene. The consist of selected 3-D features which satisfy system constraints and corroborating evidence subtrees which are used in the formation of hypotheses. Verification techniques, used to substantiate or refute these hypotheses are explored. Experiments utilizing 3-D data are presented     

Convergent matching for model-based computer vision

We consider matching in model-based computer vision as a converging discrete iteration and give a basis for examining the convergence as the movement of the working point in a lattice. Because the matching is non-deterministic we discuss convergence in terms of completing sub-problems within a time slot. This form of low-level scheduling avoids effectively unlimited trials of sub-graphs, a phenomenon that we call the NP-trap. We define high-level scheduling as the need to test each reference class at least once and thereafter focus attention on the most promising candidates. Examples show the bounding of matching time with a time slot and focusing of attention guided by a figure of merit.     

Computer vision for interactive computer graphics

Vision can be a powerful interface device for computers because of its potential for sensing body position, head orientation, direction of gaze, pointing commands, and gestures. Such unencumbered interaction can make computers easier to use. We describe vision algorithms for interactive graphics and present vision-controlled graphics applications using these algorithms. Some applications employ an artificial retina chip for image detection or preprocessing     

Object-based visual attention for computer vision

In this paper, a novel model of object-based visual attention extending Duncan's Integrated Competition Hypothesis [Phil. Trans. R. Soc. London B 353 (1998) 1307-1317] is presented. In contrast to the attention mechanisms used in most previous machine vision systems which drive attention based on the spatial location hypothesis, the mechanisms which direct visual attention in our system are object-driven as well as feature-driven. The competition to gain visual attention occurs not only within an object but also between objects. For this purpose, two new mechanisms in the proposed model are described and analyzed in detail. The first mechanism computes the visual salience of objects and groupings; the second one implements the hierarchical selectivity of attentional shifts. The results of the new approach on synthetic and natural images are reported.     

3-D model building for computer vision

This paper presents a Computer-Aided Geometric Design (CAGD) based approach for building 3-D models. A new method is given which allows the points on the surface of the designed object to be sampled at the desired resolution. The resulting data structure includes 3-D coordinates of the points, surface normals and neighborhood information.     

A probabilistic matching algorithm for computer vision

A model-based vision system attempts to find correspondences between features of an object model and features detected in an image for purposes of recognition, localization, or inspection. In this paper we pose the relational matching problem as a special case of the pattern complex recognition problem and propose a probabilistic model to describe the images of an object. This Bayesian approach allows us to make explicit statements of how an image is formed from a model, and hence define a natural matching cost that can be used to guide a heuristic search in finding the best observation mapping. Furthermore, we show that even though the nature of the feature matching problem is exponential, the use of the proposed algorithm keeps the size of the problem under control, by efficiently reducing the search space.     

Elements of early vision for computer graphics

Visually based techniques in computer graphics have blossomed. Important advances in perceptually driven rendering, realistic image display, high-fidelity visualization, and appearance-preserving geometric simplification have all been realized by applying knowledge of the limitations and capabilities of human visual processing. Much of this work is grounded in the physiology and psychophysics of early vision, which focuses on how visual mechanisms transduce and code the patterns of light arriving at the eye. The article surveys some of the fundamental findings in the study of early vision including basic visual anatomy and physiology, optical properties of the eye, light sensitivity and visual adaptation, and spatial vision     

A software environment for parallel computer vision

A software environment tailored to computer vision and image processing (CVIP) that focuses on how information about the CVIP problem domain can make the high-performance algorithms and the sophisticated algorithm techniques being designed by algorithm experts more readily available to CVIP researchers is presented. The environment consists of three principle components: DISC, Cloner, and Graph Matcher. DISC (dynamic intelligent scheduling and control) supports experimentation at the CVIP task level by creating a dynamic schedule from a user's specification of the algorithms that constitute a complex task. Cloner is aimed at the algorithm development process and is an interactive system that helps a user design new parallel algorithms by building on and modifying existing library algorithms. Graph Matcher performs the critical step of mapping new algorithms onto the target parallel architecture. Initial implementations of DISC and Graph Matcher have been completed, and work on Cloner is in progress