• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.797-807
• /
• 2008

This paper proposes a new algorithm of extracting forward vehicle areas using the acquired lanes and road area information on road images with complex background to improve the efficiency of the vehicle detection. In the first stage, lanes are detected by taking into account the connectivity among the edges which are determined from a method of chain code. Once the lanes proceeding to the same direction with the running vehicle are detected, neighborhood roadways are found from the width and vanishing point of the acquired roadway of the running vehicle. And finally, vehicle areas, where forward vehicles are located on the road area including the center and neighborhood roadways, are extracted. Therefore, the proposed scheme of extracting forward vehicle area improves the rate of vehicle detection on the road images with complex background, and is highly efficient because of detecting vehicles within the confines of the acquired vehicle area. The superiority of the proposed algorithm is verified from experiments of the vehicle detection on road images with complex background.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.21-30
• /
• 2005

In this paper, we propose lane detection and trackinB algerian using B-Snake as robust algorithm. One of chief virtues of Lane detection algorithm using B-Snake is that it is possible to specify a wider range of lane structure because B-Spline conform an arbitrary shape by control point set and that it doesn't use any camera parameter. Using a robust algorithm called CHVEP, we find the vanishing point, width of lane and mid-line of lane because of the perspective parallel line and then we can detect the both side of lane mark using B-snake. To demonstrate that this algorithm is robust against noise, shadow and illumination variations in road image, we tested this algorithm about various image divided by weather-fine, rainy and cloudy day. The percentage of correct lane detection is over 95$\%$.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.10
• /
• pp.1247-1255
• /
• 2016

The safety and autonomous flight function of micro UAV or drones is crucial to its commercial application. The requirement of own building stable drones is still a non-trivial obstacle for researchers that want to focus on the intelligence function, such vision and navigation algorithm. The paper present a GCS using commercial drone and hardware platforms, and open source software. The system follows modular architecture and now composed of the communication, UI, image processing. Especially, lane-keeping algorithm. are designed and verified through testing at a sports stadium. The designed lane-keeping algorithm estimates drone position and heading in the lane using Hough transform for line detection, RANSAC-vanishing point algorithm for selecting the desired lines, and tracking algorithm for stability of lines. The flight of drone is controlled by 'forward', 'stop', 'clock-rotate', and 'counter-clock rotate' commands. The present implemented system can fly straight and mild curve lane at 2-3 m/s.

• Archives of design research
• /
• no.16
• /
• pp.27-38
• /
• 1996

Environmental design is the process of creating and suggesting a new culture retlectmg the spirits and scientific know ledges of an age, so il is important for a designer, who deals environment, to perceive the present trend of science, The goal of this study is to suggest a way to recover the vanishing image in current urban environment from the viewpoint of changing world-view, The process of this study is as follows. 1. According to spatial hierarchy, the role of each space and the importance of each space in correlation with human are considered. 2. The method to undersk, nd the space from the viewpoint of new paradigm and the direction of environmental design's access are suggested. 3. The notion that introduction of semi public space In urban environment is consistent with new paradigm is demonstrated and the semi public space's role of stimulation of urban activity is emphasized. The result of this study shows a possibility that semi public space, introduced by understanding of a space on the basis of new paradigm, expands the territory of life and overcomes tile negative environmental problem like disorder, increase of entropy.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.34 no.1 s.114
• /
• pp.1-9
• /
• 2006

The purposes of this study are to develop the concept and the measurement method of IGS(Index of Greenness in Streetscape) and to analyze the present condition of street environments through field surveys of IGS in Seoul. IGS is a new index which directly expresses human's perceptions of plants in a street and defined as the area ratio of which leaves of plants occupy in an eye-level view of a person standing on the center line of a street. In practice, IGS can be calculated from a photograph taken from a center point of a street at about 1.5 meter height from the ground with single lens reflex camera equiped with 50mm standard lens. The photograph must have a special composition in a way that the center point of the photograph is positioning at the visual vanishing point of street center line. Then the IGS can be calculated by computing the percentage of the area covered with the plant leaves in the photograph. Types of streets in Seoul were classified according to road functions into 4 types. We performed field surveys and calculated IGSs from 300 sample sites in Seoul. Followings summarize some of study results. The average IGSs for arterial roads, highways, alleys and back streets are 16.91%, 16.33%, 13.97% and 7.50% respectively. The difference of average IGS values between Ginkgo biloba and Platanus occidentalis was relatively large. From observation IGSs from April 4th, 2003 to October 2nd, 2003, it was evident that the range and timing of each plant species' IGS change is not the same. According to questionnaire to public officials taking charge of street greening, the current evaluated IGS is 24.4%, and it is expected to be 40.7% in the future.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.1
• /
• pp.35-43
• /
• 2020

Turbidity has various effects on the water quality and ecosystem of a river. High turbidity during floods increases the operation cost of a drinking water supply system. Thus, the management of turbidity is essential for providing safe water to the public. There have been various efforts to estimate turbidity in river systems for proper management and early warning of high turbidity in the water supply process. Advanced data analysis technology using machine learning has been increasingly used in water quality management processes. Artificial neural networks(ANNs) is one of the first algorithms applied, where the overfitting of a model to observed data and vanishing gradient in the backpropagation process limit the wide application of ANNs in practice. In recent years, deep learning, which overcomes the limitations of ANNs, has been applied in water quality management. LSTM(Long-Short Term Memory) is one of novel deep learning algorithms that is widely used in the analysis of time series data. In this study, LSTM is used for the prediction of high turbidity(>30 NTU) in a river from the relationship of turbidity to discharge, which enables early warning of high turbidity in a drinking water supply system. The model showed 0.98, 0.99, 0.98 and 0.99 for precision, recall, F1-score and accuracy respectively, for the prediction of high turbidity in a river with 2 hour frequency data. The sensitivity of the model to the observation intervals of data is also compared with time periods of 2 hour, 8 hour, 1 day and 2 days. The model shows higher precision with shorter observation intervals, which underscores the importance of collecting high frequency data for better management of water resources in the future.

• Korean Journal of Family Social Work
• /
• no.56
• /
• pp.5-38
• /
• 2017

This research is conducted through a qualitative methodology, and it aimed for understanding of the generalized structure of getting-together experiences from South Korean who had conversations with North Korean refugees for a long term. As a result, the study, which includes the experiences along with consideration of both contexts and timeline, shows that 'One Korean but divided into South and North', 'Synthesize of water and oil', 'Different from us', 'Understand relativism and deal with it', 'Limitation as an one race: Living different ways on a peninsula' and 'Parallel horizons: Heading to vanishing point' are the key concepts. By understanding these keys, it was able to figure out how their consciousness and acts have been developed in a long term perspective, and thus, we suggest alternative solutions that can be practiced by social workers.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1581-1587
• /
• 2020

With the emergence of convolutional neural network in the field of machine learning, the model for solving image processing problems has seen rapid development. However, the computing resources required are also rising, making it difficult to learn from a typical environment. Attention mechanism is originally proposed to prevent the gradient vanishing problem of the recurrent neural network, but this can also be used in a direction favorable to learning of the convolutional neural network. In this paper, attention mechanism is applied to convolutional neural network, and the excellence of the proposed method is demonstrated through the comparison of learning time and performance difference at this time. The proposed model showed that both learning time and performance were superior in object detection based on YOLO compared to models without attention mechanism, and experimentally demonstrated that learning time could be significantly reduced. In addition, this is expected to increase accessibility to machine learning by end users.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.11-25
• /
• 2021

The objective of this study was to analyze the impact of activation functions on flood forecasting model based on Artificial neural networks (ANNs). The traditional activation functions, the sigmoid and tanh functions, were compared with the functions which have been recently recommended for deep neural networks; the ReLU, leaky ReLU, and ELU functions. The flood forecasting model based on ANNs was designed to predict real-time runoff for 1 to 6-h lead time using the rainfall and runoff data of the past nine hours. The statistical measures such as R2, Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), the error of peak time (ETp), and the error of peak discharge (EQp) were used to evaluate the model accuracy. The tanh and ELU functions were most accurate with R2=0.97 and RMSE=30.1 (㎥/s) for 1-h lead time and R2=0.56 and RMSE=124.6~124.8 (㎥/s) for 6-h lead time. We also evaluated the learning speed by using the number of epochs that minimizes errors. The sigmoid function had the slowest learning speed due to the 'vanishing gradient problem' and the limited direction of weight update. The learning speed of the ELU function was 1.2 times faster than the tanh function. As a result, the ELU function most effectively improved the accuracy and speed of the ANNs model, so it was determined to be the best activation function for ANNs-based flood forecasting.