To reduce the memory access latency on sharedmemory multiprocessors, several prefetching schemes have been proposed. The sequential prefetching scheme is a simple hardware-controlled scheme, which exploits the sequentiality of memory accesses to predict which blocks will be read in the near future. Aggressive sequential prefetching prefetches many blocks on each miss to reduce the miss rates and results in good performance for application programs with high sequentiality. However, conservative sequential prefetching prefetches a few blocks on each miss to avoid prefetching of useless blocks, which shows better performance than aggressive sequential prefetching for application programs with low sequentiality. We analyze the relationship between the sequentiality of application programs and the effectiveness of sequential prefetching on various memory and network latency and propose a new adaptive sequential prefetching scheme. Simply adding a small table to the sequential prefetching scheme, the proposed scheme prefetches a large number of blocks for application programs with high sequentiality and reduces the miss rates significantly, and prefetches a small number of blocks for application programs with low sequentiality and avoids loading useless blocks.

The main defficulty in recognizing 3-D objects from 2-D images is matching 2-D information to the 3-D object representation. The multiple-view approach makes this problem easy to solve by reducing the problem to 2-D to 2-D matching problem. This approach models each 3-D object by a collection of 2-D views from various viewing angles and recognizes an object in the image by finding a 2-D view that has the best match to the image. However, if the size of the model database becomes large, the approach requires long time for the recognition of objects. In this paper we present a 3-D object recognition algorithm based on multiple-view approach. To reduce the recognition time, the proposed algorithm uses the coarse-to-fine process previously proposed by the authors and a genetic algorithm-based search scheme for the selection of a best matched model in the database. And, we could verify from the results of the experiments that the algorithm proposed in this paper is useful to speed up the recognition process in multiple-view based object recognition systems.

This paper describes a vision system with dual viewing angles, i. e., wide and narrow viewing angles, and a scheme of user-friendly speech dialogue environment based on the vision system. The wide viewing angle provides a wide viewing field for wide range motion tracking, and the narrow viewing angle is capable of following a target in wide viewing field to take the image of the target with sufficient resolution. For a fast and robust motion tracking, modified motion energy (MME) and existence energy (EE) are defined to detect the motion of the target and extract the motion region at the same time. Instead of using a physical device such as a foot switch commonly used in speech dialogue systems, the begin/end of an utterance is detected from the movement of user's mouth in our system. Without recognizing the movement of lips directly, the shape variation of the region between lips is tracked for more stable recognition of the span of a dialogue. The tracking speed is about 10 frames/sec when no recognition is performed and about 5 frames/sec when both tracking and recognition are performed without using any special hardware.

Clothoid or cornu spiral segments were used as transition spirals forming C-and S-shaped curves between circles as well as straight lines in various situations of highway road design. These transitions are the center lines of rail, highway road design. The above C and S-shaped form curves consist one or more transition segments. We study the possibility of using the single transition spirals in the situations that use many transition spirals to form smooth transition spline between circles as well as straight lines. We also compute the bounds for the scaling of such single spirals using the practical equation. This paper is aimed to give a method avoiding non-linear equations by finding range for the scaling factor of the clothoids which can take initially an appropriate closer value from this range.

A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.

Producing realistic images and animations of flames is one of the most interesting subjects in the field of computer graphics. In a recent paper, we described a two-dimensional particle-based visual method of simulating flames. In the present paper, we first extend the simulation method, without losing any of its desirable features, in such a way that it functions in three-dimensional space. We then present an efficient method of producing an image of the scene, including flames acting as volume light sources, which normally requires a large amount of computing time in the usual simulation approaches. Finally, we demonstrate the capabilities of our visual simulation method by showing sample images generated by it, which are excerpted from an animation.

The approach presented in this paper was intended for extending conventional Markov random field (MRF) models to a more practical problem: the unsupervised and adaptive segmentation of gray-level images. The "unsupervised" segmentation means that all the model parameters, including the number of image classes, are unknown and have to be estimated from the observed image. In addition, the "adaptive" segmentation means that both the region distribution and the image feature within a region are all location-dependent and their corresponding parameters must be estimated from location to location. We estimated local parameters independently from multiple small windows under the assumption that an observed image consists of objects with smooth surfaces, no texture. Due to this assumption, the intensity of each region is a slowly varying function plus noise, and the conventional homogeneous hidden MRF (HMRF) models are appropriate for these windows. In each window, we employed the EM algorithm for maximum-likelihood (ML) parameter estimation, and then, the estimated parameters were used for "maximizer of the posterior marginals" (MPM) segmentation. To keep continuous segments between windows, a scheme for combining window fragments was proposed. The scheme comprises two parts: the programming of windows and the Bayesian merging of window fragments. Finally, a remerging procedure is used as post processing to remove the over-segmented small regions that possibly exist after the Bayesian merging. Since the final segments are obtained from merging, the number of image classes is automatically determined. The use of multiple parallel windows makes our algorithm to be suitable for parallel implementation. The experimental results of real-world images showed that the surfaces (objects) consistent with our reasonable model assumptions were all correctly segmented as connected regions.

Since spontaneously spoken language expressions appear continuously, the transfer stage of a spoken language machine translation system have to work incrementally. In such the system, the high degree of incrementality is also strongly required rather than that of quality. This paper proposes an incremental machine translation system, which translates English spoken words into Japanese in accordance with the order of appearances of them. The system is composed of three modules: incremental parsing, transfer and generation, which work synchronously. The transfer module utilizes some features and phenomena characterizing Japanese spoken language: flexible wordorder, ellipses, repetitions and so forth. This in influenced by the observational facts that such characteristics frequently appear in Japanese uttered by English-Japanese interpreters. Their frequent utilization is the key to success of the exceedingly incremental translation between English and Japanese, which have different word-order. We have implemented a prototype system Sync/Trans, which parses English dialogues incrementally and generates Japanese immediately. To evaluate Sync/Trans we fave made an experiment with the conversations consisting of 27 dialogues and 218 sentences. 190 of the sentences are correct, providing a success rate of 87.2%. This result shows our incremental method to be a promising technique for spoken language translation with acceptable accuracy and high real-time nature.