• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.705-717
• /
• 2001

In this paper, we propose a rapid lane detection method to extract a preceding vehicle from sequential images captured by a single monocular CCD camera. We detect positions of lanes for an individual image within the limited area that would not be hidden and thereby compute the slopes of the detected lanes. Then we find a search area where vehicles would exist and extract the position of the preceding vehicle within the area with edge component by applying a structured method. To verify the effects of the proposed method, we capture the road images with a notebook PC and a CCD camera for PC and present the results such as processing time for lane detection, accuracy and vehicles detection against the images.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.833-841
• /
• 1998

The ann of this study is 10 propose all eff'tcient mclhod for partition of multi-dimensIOnal feature space into pattern subspace for automated generation of fuzzy rule. The suggested mclhod predicates on sequential subdivision of the fuzzy subspacc. and the size of construc1cd pattern space is variable. Under this procedure, n-dimensional pattern space, after considering the distributional characteristic patterns, is partitioned into two different pattern subspaces. From the two subspaces, the pattern space for further subdivision is chosen; then, this subdivision procedure recursively repeats itself until the stopping condition is fulfilled. The result of this study is applied to 2, 4, 7 band of satellite Landsat TM and satisfac10ry result is acquired.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.3
• /
• pp.76-79
• /
• 2014

Face recognition is very challenging because of the unexpected changes of pose, expression, and illumination. Facial detection in the mobile environments has additional difficulty since the computational resources are very limited. This paper discusses face detection based on frequency domain matched filtering in the mobile environments. Face detection is performed by a linear or phase-only matched filter and sequential verification stages. The candidate window regions are selected by a number of peaks of the matched filtering outputs. The sequential stages comprise a skin-color test and an edge mask filtering tests, which aim to remove false alarms among selected candidate windows. The algorithms are built with JAVA language on the mobile device operated by the Android platform. The simulation and experimental results show that real-time face detection can be performed successfully in the mobile environments.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.307-314
• /
• 1999

In this paper, we study on the transformation technique of sequential programs for the purpose of 'exploiting parallelism' and 'improving locality'. Based on the analysis of loop procedures of sequential programs with the factor of dependency and locality, two transformation techniques of loop distribution and loop fusion are applied to them. Transformed programs can be easily expressed as a parallel program wit thread notation, having coarse-grain parallelism and improved locality. This means that those transformations can be useful tools for optimizing and automatic-parallelizing compiler construction. Application of those techniques to SPEC95 on a solaris machine with four SPARC processors show an improvement of execution time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.380-382
• /
• 2019

GAN(Generative Adversarial Network)은 정해진 학습 데이터에서 정해진 생성자와 구분자가 서로 각각에게 적대적인 관계를 유지하며 동시에 서로에게 생산적인 관계를 유지하며 가능한 긍정적인 영향을 주며 학습하는 기계학습 분야이다. 전통적인 문장 생성은 단어의 통계적 분포를 기반으로 한 마르코프 결정 과정(Markov Decision Process)과 순환적 신경 모델(Recurrent Neural Network)을 사용하여 학습시킨다. 이러한 방법은 문장 생성과 같은 연속된 데이터를 기반으로 한 모델들의 표준 모델이 되었다. GAN은 표준모델이 존재하는 해당 분야에 새로운 모델로써 다양한 시도가 시도되고 있다. 하지만 이러한 모델의 시도에도 불구하고, 지금까지 해결하지 못하고 있는 다양한 문제점이 존재한다. 이 논문에서는 다음과 같은 두 가지 문제점에 집중하고자 한다. 첫째, Sequential 한 데이터 처리에 어려움을 겪는다. 둘째, 무작위로 생성하기 때문에 사용자가 원하는 데이터만 출력되지 않는다. 본 논문에서는 이러한 문제점을 해결하고자, 부분적인 정답 제공을 통한 조건별 생산적 적대 생성망을 설계하여 이 방법을 사용하여 해결하였다. 첫째, Sequence to Sequence 모델을 도입하여 Sequential한 데이터를 처리할 수 있도록 하여 원시적인 텍스트를 생성할 수 있게 하였다. 둘째, 부분적인 정답 제공을 통하여 문장의 생성 조건을 구분하였다. 결과적으로, 제안하는 기법들로 원시적인 감정 텍스트를 생성할 수 있었다.

• Journal of Information Processing Systems
• /
• v.12 no.1
• /
• pp.149-168
• /
• 2016

The Active Appearance Model (AAM) is a class of deformable models, which, in the segmentation process, integrates the priori knowledge on the shape and the texture and deformation of the structures studied. This model in its sequential form is computationally intensive and operates on large data sets. This paper presents another framework to implement the standard version of the AAM model. We suggest a distributed and parallel approach justified by the characteristics of the model and their potentialities. We introduce a schema for the representation of the overall model and we study of operations that can be parallelized. This approach is intended to exploit the benefits build in the area of advanced image processing.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.311-314
• /
• 1995

This paper presents a method for measuring tool wear parameters based on two dimensional image information. The tool wear images were obtained from an ITV camera with magnifying and lighting devices, and were analyzed using image processing techniques such as thresholding, noise filtering and boundary tracing. Thresholding was used to transform the captured gray scale image into a binary image for rapid sequential image processing. The threshold level was determined using a novel technique in which the brightness histograms of two concentric windows containing the tool wear image were compared. The use of noise filtering and boundary tracing to reduce the measuring errors was explored. Performance tests of the measurement precision and processing speed revealed that the direct method was highly effective in intermittent tool wear monitoring.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.5
• /
• pp.407-412
• /
• 2003

An effective methodology is .reported for determining the optimal capacity (lot-size) of batch processing and storage networks which include material recycle or reprocessing streams. We assume that any given storage unit can store one material type which can be purchased from suppliers, be internally produced, internally consumed and/or sold to customers. We further assume that a storage unit is connected to all processing stages that use or produce the material to which that storage unit is dedicated. Each processing stage transforms a set of feedstock materials or intermediates into a set of products with constant conversion factors. The objective for optimization is to minimize the total cost composed of raw material procurement, setup and inventory holding costs as well as the capital costs of processing stages and storage units. A novel production and inventory analysis formulation, the PSW(Periodic Square Wave) model, provides useful expressions for the upper/lower bounds and average level of the storage inventory hold-up. The expressions for the Kuhn-Tucker conditions of the optimization problem can be reduced to two subproblems. The first yields analytical solutions for determining batch sizes while the second is a separable concave minimization network flow subproblem whose solution yields the average material flow rates through the networks. For the special case in which the number of storage is equal to the number of process stages and raw materials storage units, a complete analytical solution for average flow rates can be derived. The analytical solution for the multistage, strictly sequential batch-storage network case can also be obtained via this approach. The principal contribution of this study is thus the generalization and the extension to non-sequential networks with recycle streams. An illustrative example is presented to demonstrate the results obtainable using this approach.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.271-277
• /
• 2017

As a result of rapid industrialization, air pollutants are seriously threatening the health of the people, the forecast is becoming more and more important. In forecasting air quality, it is very important to create a reliable initial field because the initial field input to the air quality forecasting model affects the accuracy of the forecast. There are several methods for enhancing the initial field input. One of the necessary techniques is data assimilation. The number of operations and the time required for such data assimilation is exponentially increased as the forecasting area is widened and the number of observation sites increases. Therefore, as the forecast size increases, it is difficult to apply the existing sequential processing method to a field requiring fast processing speed. In this paper, we propose a method that can process Cresman's method, which is one of the data assimilation techniques, in real time using CUDA. As a result, the proposed parallel processing method using CUDA improved at least 35 times faster than the conventional sequential method and other parallel processing methods.

• Journal of Forest and Environmental Science
• /
• v.33 no.4
• /
• pp.355-360
• /
• 2017

This study was aimed to analyze the increased forestry incomes by combining timber production and wood processing, which is one of 6th industrialization types in Korean forestry. The selected household has been engaged in forestry for two generations and they produce timber and associated wood products in their own facility. The wood products include dimension lumber, interior wood material, cutting board, and cube chips, the household also utilize logging and sawmill residues as well as seed and seedlings as by-products. Incomes and expenses that have been incurred on individual processes of the sequential timber production and wood processing were surveyed, and we analyzed the economic outcomes of entire business. The results of this study indicate that the gross income of the household is 122.3 million Korean won and the net income is 93.6 million Korean won. The net income of the household is approximately 2.8 times higher than the average net income of whole households in the forestry of Korea in 2016, which is approximately 4.3 times higher than that of households that have been particularly engaged in timber production over the country. We found that the 6th industrialization by combining the two sequential processes creates approximately 3.2 times as much added value compared to the case relying on timber production only.