• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.5
• /
• pp.550-557
• /
• 1999

This paper describes a road-following controller using the proposed neural network for autonomous vehicle. Road-following with visual sensor like camera requires intelligent control algorithm because analysis of relation from road image to steering control is complex. The proposed neural network, relative similarity modular network(RSMN), is composed of some learning networks and a partitioniing network. The partitioning network divides input space into multiple sections by similarity of input data. Because divided section has simlar input patterns, RSMN can learn nonlinear relation such as road-following with visual control easily. Visual control uses two criteria on road image from camera; one is position of vanishing point of road, the other is slope of vanishing line of road. The controller using neural network has input of two criteria and output of steering angle. To confirm performance of the proposed neural network controller, a software is developed to simulate vehicle dynamics, camera image generation, visual control, and road-following. Also, prototype autonomous electric vehicle is developed, and usefulness of the controller is verified by physical driving test.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.3
• /
• pp.1-7
• /
• 2010

To find an appropriate illuminance range for the disability glare caused by the road lighting system installed on guardrails, the influence of the disability glare was evaluated in comparison with the road lighting system of a streetlight. To test the disability glare, an indoor laboratory was constructed and a variation of luminance contrast threshold was evaluated. As a result, when the retinal illuminance was increased and glare sources existed within the narrow visual field, the luminance contrast threshold was increased. Although the road lighting luminaire was installed as low as the height of the guardrail on the road, when out of sight, the influence of the disability glare was small in comparison with the conventional road lighting system such as a streetlight.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.525-527
• /
• 2003

Recently, the spatial resolution of earth observation satellites is significantly increased to a few meters. Such high spatial resolution images definitely will provide lots of information for detail-thirsty remote sensing users. However, it is more difficult to develop automated image algorithms for automated image feature extraction and pattern recognition. In this study, we propose a two-stage procedure to extract road information from high resolution satellite images. At first stage, a watershed segmentation technique is developed to classify the image into various regions. Then, a knowledge is built for road and used to extract the road regions. In this study, we use panchromatic and multi-spectral images of the IKONOS satellite as test dataset. The experiment result shows that the proposed technique can generate suitable and meaningful road objects from high spatial resolution satellite images. Apparently, misclassified regions such as parking lots are recognized as road needed further refinement in future research.

• Journal of Forest and Environmental Science
• /
• v.10 no.1
• /
• pp.49-56
• /
• 1994

This study was carried out to estimate forest road elongation coefficients for providing the basic information of forest road construction. As the results, road elongation coefficients were calculated 0.33 less than 5% of road gradient, 0.39 between the gradient of 6% and 10%, 0.50 between the gradient of 11% and 15%, 0.58 between the gradient of 16% and 20%, and 0.60 greater than the gradient of 20%.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.23 no.6
• /
• pp.151-166
• /
• 2020

Various experience keywords were derived through text mining analysis of two National Ecological and Cultural Exploration Routes. The results of this study were drawn as follows: The interaction between the experience keywords was analyzed by the degree centrality, closeness centrality, and betweenness centrality value calculated through the centrality analysis of the research site experience keywords. First, In the text mining analysis, 'walking' appeared as the top keyword in the I, II, and III periods of the two target areas. The keywords related to the stay type of "rental cottage" and "recreational forest" were derived for Masil Road in relation to accommodation facilities. However, the keywords related to the accommodation were not derived in Gubul Road. Second, as a result of the centrality analysis, the degree centrality of the keywords "walking", "sea", "look", "salt flats" of Masil Road and "walking", "lake" and "park" of Gubul Road was high. The keywords located at the center are "walking" and "sea" in the Masil Road, and "walking" in the Gubul Road. As an influential keyword, Masil Road is "experience" and Gubul Road is "history". Third, According to the results of the analysis, the keywords that appeared at the top of the Gubul Road are derived from the keywords related to the 1 ~ 8 course, and it is judged that the visitors are visiting the 1 ~ 8 course trail evenly. However, the Gubul Road only appears in the top keyword only for a few courses. Through this, it seems that three courses are intensively visited as the main course of 6 Gubul Road, 6-1 Gubul Road, and 8 Gubul Road.

• Journal of Forest and Environmental Science
• /
• v.20 no.1
• /
• pp.93-109
• /
• 2004

To provide the basic informations related to forest road construction of mountainous terrain, we analyzed changes of the road structure factors such as banking and cutting slope gradients, slope length, road width by the environmental factors such as locations, slope gradients, soil types, road position on physically stabilized forest roads constructed in Gangwon-do. All factors related to the road structures by locations were significant except for banking slope length. Road width, longitudinal gradients, banking and cutting slope length by slope gradients were not significantly different and banking slope gradients in the range less than $30^{\circ}$, from $30^{\circ}$ to $35^{\circ}$ and more than $40^{\circ}$ and cutting slope gradients were significantly different for all areas. Road width, longitudinal gradients, banking slope length by soil types were not significantly different and others were significantly different. All factors related to the road structures by road position were significant except for cutting slope gradients.

• Journal of Korean Society of Forest Science
• /
• v.81 no.2
• /
• pp.139-145
• /
• 1992

A planning method of optimum forest road was tested in the compartment II of Kangweon National University Forests by using a digital terrain model under four evaluation factors, i. e., minimum road length, average skidding distance, exploitative index, and ratio of inaccessible points. The results of the study were as follows : 1. Optimum forest road design based on the minimum road length was shown as 6035.6m, 12.73m/ha, 279.9m, 1.43, and 15.7% for total road length, forest road density, average skidding distance, exploitative index, and ratio of inaccessible points, respectively. 2. Optimum forest road design based on the average skidding distance was shown as 7828.5m, 16.52m/ha, 198.4m, 1.31, and 4.0% for total road length, forest road density, average skidding distance, exploitative index, and ratio of inaccessible points, respectively. 3. Optimum forest road design based on the exploitative index was shown as 7410.6m, 15.64m/ha, 210.9m, 1.26, and 5.0% for total road length, forest road density, average skidding distance, exploitative index, and ratio of inaccessible points, respectively. 4. Optimum forest road design based on the ratio of inaccessible points was shown as 8307.1m, 17.53 m/ha, 184.9m, 1.29, and 2.5% for total road length, forest road density, average skidding distance, exploitative index, and ratio of inaccessible points, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.604-609
• /
• 2019

A variety of complaints about road signs have occurred for various reasons, such as new road facilities, new road signs such as road name signs, and an increase in nearby important facilities. In addition, there are many road signs that are in violation of road sign regulations. The basic principles of road signs, the connectivity of guide names, the location suitability, and a consistent road sign guidance system have not implemented. To solve these problems, various errors were investigated on major road signs on eight national highways, including direction signs, distance signs, boundary signs, and route signs. In addition, we classified the errors on road signs by grade to give them maintenance priority. We also analyzed the error status of signs for each route and grade. Based on the data, the problems of the road signs were derived, and an improvement plan is discussed. Based on this research, more systematic installation and management of road signs through cooperation between the government and local governments could increase the efficiency of road signs, as well as provide safer and more convenient road sign guidance systems for road users.

• Korean Journal of Agricultural Science
• /
• v.37 no.3
• /
• pp.471-479
• /
• 2010

Forest roads of 16,424km have been constructed as infrastructure for efficient management of forest. The demand of forest road have been also increased steadily with SOC conception for forest management and wood production. But, accuracy verification by completion drawing of forest road needed aspects extration of geographic information to sound like forest road construction and completion drawing. However, verification for completion drawing has not ascertained. This study carried out the evaluation for position accuracy about constructed forest road in Chungcheongnam-do for evaluating horizontal position accuracy of completion drawing of forest road. In result, first of distance of completion drawing and real route designed completion drawing longer than the real route as Gongju 83m, Seosan 66m, Nonsan 27m and Dangjin 19m, respectively. Second, RMSE by point-correspondence was 11m~14.7m, buffering analysis appeared difference of 18~24m. Finally, index of shape was the similar completion and real route through 6.5~7.4 and data information of forest road corresponds to be perfect. For such reasons, the existing completion drawings have a problem that it cannot use graphic information for drawing digital map according to the regulation, and there is an urgent need for improvement to solve this problem in the process of design and construction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3369-3385
• /
• 2019

There are various research challenges in vehicular ad hoc networks (VANETs) that need to be focused until an extensive deployment of it becomes conceivable. Design and development of a scalable routing algorithm for VANETs is one of the critical issue due to frequent path disruptions caused by the vehicle's mobility. This study aims to provide a novel road-aware routing protocol for vehicular networks named as Two-level hierarchical Hybrid Road-Aware (THERA) routing for vehicular ad hoc networks. The proposed protocol is designed explicitly for inter-vehicle communication. In THERA, roads are distributed into non-overlapping road segments to reduce the routing overhead. Unlike other protocols, discovery process does not flood the network with packet broadcasts. Instead, THERA uses the concept of Gateway Vehicles (GV) for the discovery process. In addition, a route between source and destination is flexible to changing topology, as THERA only requires road segment ID and destination ID for the communication. Furthermore, Road-Aware routing reduces the traffic congestion, bypasses the single point of failure, and facilitates the network management. Finally yet importantly, this paper also proposes a probabilistical model to estimate a path duration for each road segment using the highway mobility model. The flexibility of the proposed protocol is evaluated by performing extensive simulations in NS3. We have used SUMO simulator to generate real time vehicular traffic on the roads of Gangnam, South Korea. Comparative analysis of the results confirm that routing overhead for maintaining the network topology is smaller than few previously proposed routing algorithms.