The development of an autonomous mobile robot is a central problem in artificial intelligence and robotics. A vision system can be used to recognize naturally occurring landmarks located in known positions. The proble...
详细信息
ISBN:
(纸本)0819413232
The development of an autonomous mobile robot is a central problem in artificial intelligence and robotics. A vision system can be used to recognize naturally occurring landmarks located in known positions. The problem considered here is that of finding the location and orientation of a mobile robot using a 3-D image taken by a CCD camera located on the robot. The naturally occurring landmarks that we use are the corners of the room extracted by an edge detection algorithm from a 2-D image of the indoor scene. Then, the location and orientation of the vehicle are calculated by perspective information of the landmarks in the scene of the room where the robot moves.
Markov random field techniques for region labeling have become prevalent in image processing research since the seminal work of Geman and Geman in the early 1 980's. Their use in actual working systems, however, h...
详细信息
ISBN:
(纸本)0819416282
Markov random field techniques for region labeling have become prevalent in image processing research since the seminal work of Geman and Geman in the early 1 980's. Their use in actual working systems, however, has been hampered by a number ofdifficult problems. Perhaps the most intractable of the problems has been the convergence rate of the algorithm. In this paper, we present a technique that introduces stable points in the labeling array of the random field. The stable points are determined by using a simple statistical pixel classifier together with a confidencemeasure at each pixel. The most confident (top 1% )pixellabels are selected and these labels are used to initiate the evolution of the random field. The stable points introduce pockets of "certainty" in the evolution of the process. The labeling is locally stable and even small numbers of stable points vastly decrease convergence rates of the algorithm.
In previously published papers we have presented an object representation known as a core that represents an object at measurement scales (tolerances) relative to the local size of the object. Such object-relevant sca...
详细信息
ISBN:
(纸本)081941462X
In previously published papers we have presented an object representation known as a core that represents an object at measurement scales (tolerances) relative to the local size of the object. Such object-relevant scale allows one to be more sensitive to such detail (and, of course, the effects of noise, blurring, and other image degradation) for smaller objects while being less sensitive to such detail (and image degradation) for larger objects. This produces a more robust mechanism that is able to trade off between sensitivity to noise and loss of detail by considering the properties of the object involved. This paper, after briefly reviewing the definition and computation of cores, studies this relationship between noise and object size and shows that the algorithms for computing cores do indeed produce more stable results for larger objects by automatically selecting correspondingly larger, less noise-sensitive scales.
We have developed and field tested a real-time robust diagnostic system, which uses hierarchical, multiple-aspect models of plants. The models include the functional structure, timed failure propagation graphs, physic...
详细信息
ISBN:
(纸本)0819415480
We have developed and field tested a real-time robust diagnostic system, which uses hierarchical, multiple-aspect models of plants. The models include the functional structure, timed failure propagation graphs, physical component structure, and component failure modes. The diagnostic reasoning applies structural and temporal constraints for the generation and validation of fault hypotheses using the `predictor-corrector' principle. The diagnosis is generated in real time, amid an evolving alarm scenario, and uses progressive deepening control strategy. The robust diagnostic system has been tested and demonstrated using ECLSS models obtained from the Boeing Company.
In this paper we describe a low cost approach to the compression of sequences of video images. The target application of this algorithm is video conferencing.
ISBN:
(纸本)0819414824
In this paper we describe a low cost approach to the compression of sequences of video images. The target application of this algorithm is video conferencing.
We analyze simple everyday actions with a view to developing strategies that an intelligent robot can use to perform these same actions. The domain of tasks studied are in the class of simple machine-type actions invo...
详细信息
ISBN:
(纸本)0819415480
We analyze simple everyday actions with a view to developing strategies that an intelligent robot can use to perform these same actions. The domain of tasks studied are in the class of simple machine-type actions involving hand tools. The tool is assumed to be composed of two principal geometric primitives that serve as the handle and the output end respectively. A task is modeled as an operation on a target object by the tool. This desired effect determines a motion trajectory for the output end of the tool. The decisions on grasp location and orientation are made based on the handle motions computed above. In addition to planning grasps and manipulations, we also formulate strategies for recognizing such tools. Tool recognition (from visual input) is based on the geometric information extracted. All objects in a scene are segmented into volumetric primitives. The primitives are then analyzed for their suitability to participate in the required task. Different primitives are ranked according to these criteria and the most suitable object is chosen to function as the tool.
In this paper, we discuss methods for multispectral ATR (Automated Target Recognition) of small targets that are sensed under suboptimal conditions, such as haze, smoke, and low light levels. In particular, we discuss...
详细信息
ISBN:
(纸本)081941624X
In this paper, we discuss methods for multispectral ATR (Automated Target Recognition) of small targets that are sensed under suboptimal conditions, such as haze, smoke, and low light levels. In particular, we discuss our ongoing development of algorithms and software that effect intelligent object recognition by selecting ATR filter parameters according to ambient conditions. Our algorithms are expressed in terms of IA (image algebra), a concise, rigorous notation that unifies linear and nonlinear mathematics in the image processing domain. IA has been implemented on a variety of parallel computers, with preprocessors available for the Ada and FORTRAN languages. An image algebra C++ class library has recently been made available. Thus, our algorithms are both feasible implementationally and portable to numerous machines. Analyses emphasize the aspects of image algebra that aid the design of multispectral vision algorithms, such as parameterized templates that facilitate the flexible specification of ATR filters.
This paper analyzes a new method to detect targets. The new method, called `super noncoherent integration' (SNCI), can improve overall detection performance by typically 5 dB to 10 dB relative to conventional nonc...
详细信息
ISBN:
(纸本)0819415391
This paper analyzes a new method to detect targets. The new method, called `super noncoherent integration' (SNCI), can improve overall detection performance by typically 5 dB to 10 dB relative to conventional noncoherent integration. A simple back-of-the-envelope formula is derived which quantifies the performance improvement of SNCI. Conventional noncoherent integration (CNCI) uses only amplitude measurements to distinguish targets from noise or clutter. In contrast, SNCI uses amplitude data in addition to: monopulse data, quadrature monopulse data, range and Doppler data over a sequence of N transmitted radar waveforms.
Many radar systems need to be able to accurately determine a target's height above terrain. In airborne early warning (AEW) systems, the radar antenna is limited in its vertical aperture, thus producing a broad be...
详细信息
ISBN:
(纸本)0819415219
Many radar systems need to be able to accurately determine a target's height above terrain. In airborne early warning (AEW) systems, the radar antenna is limited in its vertical aperture, thus producing a broad beamwidth in elevation. This reduces its curacy for height fmding. An alternate method of height fmding is to measure the delay of a ground-bounce (multipath) signal from the target, referenced to the direct line of sight path. This has been demonstrated successfully with AEW radars which operate over water in certain situations, but has had limited success over land. The problem has been the lack of an accurate, robust signal processing algorithm for determining the time delay between closely spaced direct and ground bounce returns. Our basic objective was to make credible the premise that an airborne AEW radar can accurately determine height of targets by processing the delayed echo due to the multipath ground bounce. Current AEW systems use this technique, but in a limited way -usually only over water, where the surface reflection is strong and predictable and when it is well separated from the direct reflection. It has been recognized for some time that land also can cause multipath reflections, but due to its irregular nature, this technique has not been exploited thoroughly. Therefore, our objectives were to show height finding can be done accurately when the direct pulse overlaps the specular return (over water or land). The signal processing problem is essentially one of performing time-of-arrival estimation of two or more pulse returns; the direct plus one or more ground bounce echoes. For typical AEW scenarios, the echoes may overlap the direct return and are usually of lower amplitude. Therefore, the algorithm must make use of the maximum information content of the signal and should have as low a threshold signal to noise ratio as possible in order to apply in the greatest number of conditions. This problem will also occur in laser radar systems, a
A new classification system for text-independent speaker recognition is presented. Text- independent speaker recognition systems generally model each speaker with a single classifier. The traditional methods use unsup...
详细信息
ISBN:
(纸本)0819416010
A new classification system for text-independent speaker recognition is presented. Text- independent speaker recognition systems generally model each speaker with a single classifier. The traditional methods use unsupervised training algorithms, such as vector quantization (VQ), to model each speaker. Such methods base their decision on the distortion between an observation and the speaker model. Recently, supervised training algorithms, such as neural networks, have been successfully applied to speaker recognition. Here, each speaker is represented by a neural network. Due to their discriminative training, neural networks capture the differences between speakers and use this criteria for decision making. Hence, the output of a neural network can be considered as an interclass measure. The VQ classifier, on the other hand, uses a distortion which is independent of the other speaker models, and can be considered as an intraclass measure. Since these two measures are based on different criteria, they can be effectively combined to yield improved performance. This paper uses data fusion concepts to combine the outputs of the neural tree network and VQ classifiers. The combined system is evaluated for text-independent speaker identification and verification and is shown to outperform either classifier when used individually.
暂无评论