• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.5
• /
• pp.894-902
• /
• 2010

This paper presents a vision-based robust off-road terrain classification method against environmental variation. As a supervised classification algorithm, we applied a neural network classifier using wavelet features extracted from wavelet transform of an image. In order to get over an effect of overall image feature variation, we adopted environment sensors and gathered the training parameters database according to environmental conditions. The robust terrain classification algorithm against environmental variation was implemented by choosing an optimal parameter using environmental information. The proposed algorithm was embedded on a processor board under the VxWorks real-time operating system. The processor board is containing four 1GHz 7448 PowerPC CPUs. In order to implement an optimal software architecture on which a distributed parallel processing is possible, we measured and analyzed the data delivery time between the CPUs. And the performance of the present algorithm was verified, comparing classification results using the real off-road images acquired under various environmental conditions in conformity with applied classifiers and features. Experiments show the robustness of the classification results on any environmental condition.

• Journal of People, Plants, and Environment
• /
• v.21 no.6
• /
• pp.545-555
• /
• 2018

The purpose of this study was to analyze land use plans of 61 residential complexes and identify the factors that caused the variation of urban parks and green space ratio depending on the land ownership processing method. The ratio of urban parks and green space of expropriation districts was higher than that of replotting districts. Within the same city and country as well as other regions, the parks and green space ratio of land expropriation districts increased higher than 7% compared to that of replotting districts. The variation of urban parks and green space ratio was mainly related to the ratio of road. Small housing complexes such as detached house and quasi-residential sites resulted to expand space for road construction, thus, the areas of urban parks or green space came to reduce. The average urban parks and green space ratio in the urban development by the expropriation method and replotting method are 24.5% and 16.8% respectively. In order to prevent the reduction of urban parks and green space ratio according to the preference of detached house sites or quasi-residential sites in development zones, it is necessary to make systematic adjustment such as adjusting the urban parks and green space ratio securing standard.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.3
• /
• pp.169-174
• /
• 2015

Noise problem that occurs on the road is raising a lot of problems in the economic, social and environmental aspects. The active noise control (ANC) systems based on the filtered-X least mean square(FxLMS) algorithm have a problem with compensating the acoustic feedback of secondary route. However, newly proposed correlation-LMS(CLMS) and expanded CLMS algorithms have slightly much calculation and are minutely behind performance, these have a advantage not in measuring transfer function onerously so that we can easily adapt these in real time. The CLMS and expanded CLMS algorithm was developed to improve the real-time implementation performance under the variable input noise such as road noise environment. In this paper, we compared and analyzed their performance. From the results of the Matlab simulation for an ANC system, it is shown that expanded CLMS algorithms are more convergence speed and keep the desirable performance even in the input of road noise situation.

• Journal of Environmental Impact Assessment
• /
• v.21 no.5
• /
• pp.801-811
• /
• 2012

For biodiversity conservation, Biological Impact Assessment is very important. The focus of the study is to enhance efficient Environment Impact Assessment(EIA) based on collecting existing information of endangered species covering the status survey, estimation of effects and reducing methods. Habitat Suitability Index(HSI) can be applicable to Ecological Impact Assessment and finding various reducing methods based on estimating effects. For this study, the EIA report of Samjang - Sanchung highway construction was chosen as an example and Prionailurus bengalensis euptilura as an endangered species was chosen to assess the ecosystem impact on road construction. Water, road, ground coverage, slope, altitude as variables of habitat were weighted and final HSI map was calculated using Arc map and Arc view. Through comparing of before and after HSI, quantitative estimating on effects was possible to minimize impact of road construction to wildlife habitat.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.4
• /
• pp.179-188
• /
• 2007

Vehicle recognition is very important preprocess to get vehicle information for traffic management. This is a basic study to apply LiDAR data for extracting traffic information. Hence, this study presents two algorithms, one of them is for extracting road points from LiDAR data and then extracting vehicle points on the road, the other is for estimating the size of extracted vehicle. As a result, in the wide area, the number of vehicles on the road and the size of the vehicles were recognized from the LiDAR data.

• International Journal of Highway Engineering
• /
• v.19 no.2
• /
• pp.167-174
• /
• 2017

PURPOSES: This study aims to analyze the impact of the implementation of a school zone traffic safety improvement project on the number of accidents involving children in these zones. METHODS : To analyze the correlation between school zone traffic safety features of roads in the zone and the number of accidents involving children, we developed an occurrence probability model of traffic accidents involving children by using a binary logistic regression model with SPSS 23.0 software. Two separate models were developed for two zones: interior block and arterial road. RESULTS :The model depicted that in the case of the interior block, shorter sidewalk width, speed bump, and an elevated crosswalk were key factors affecting the occurrence of accidents involving children. In the case of arterial roads exceeding a width of 12 m, the speed limit, roadside barriers, and red paving of road surfaces were found to be the key factors. CONCLUSIONS:The results of this study can serve as the elementary research data to help improve the effectiveness of school zone traffic safety improvement projects and school zone road repair projects in future.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.277-282
• /
• 2006

Road traffic noise is not produced by any one factor rather occurs as a composition of various factors. Its occurrence is made by running engine noise, tire frictional, and exhaust noise etc. The quality of the noise depends on the size of the vehicles, rotation and engine speed, vehicle load, package state of the road and incline etc. The occurrence of noise level of heavy trucks appears louder than smaller vehicles and the noise levels produced differs according to speed and load etc between similar size vehicles. Other factors such as traffic density, average speed, mixing rate of heavy vehicles, and the distance between vehicles also generate road traffic noise. In this paper we examine 2, 4, and 6-lane roads in Jeonju. Consequently, this study examined the means used to measure road traffic noise. It was found that when there is a large traffic density and the average velocity is below 70 km/hr, the noise level could receive a relative proper value by the current measuring means. But in the case of night-time, it was found that the current measuring method is inapposite.

• Korean Journal of Agricultural Science
• /
• v.40 no.3
• /
• pp.209-214
• /
• 2013

This study examined the work time, work posture, and work intensity for the actual measurement step in forest road the design work that was being carried out. The measurement of the forest road was being carried by a team of three workers and a team of four workers. The examination of work time found that the measurement of 1km took about 8 hours for the four-worker team and 12 hours for the three-worker team. The examination of work intensity found that the energy metabolic rates of the three-worker team were lower than four-worker team. Because their energy consumption per minute decreased as their work time and rest time increased. Furthermore, when appropriate rest time was applied according to work time, the energy metabolic rate decreased and the work intensity became lower. The four-worker team was more advantageous from the time and cost aspects of the forest road measurement work. Furthermore, as the rest time was very low compared to the work time, more efficient forest road measurement work would be possible if the work intensity was lowered by considering the rest time when calculating the standard work time.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.1-7
• /
• 2020

This study is a study on the development of AEBS test scenarios for traffic accidents in Korea, and was compared and analyzed using the Traffic Accident Analysis Program. To ensure the safety of passengers and pedestrians in traffic accidents, the number of cars equipped with ADAS is increasing rapidly at all car manufacturers in each country. For traffic accidents used in this study, the domestic traffic accident database (ACCC) produced by SAMSONG was used. Domestic traffic accidents differ from overseas traffic accidents in terms of road type, signal system, driver's seat location and number of vehicles. ACCC databases, which supplemented and reinforced these differences, built a database based on the PC-CRASH program. In the study, we analyze the types of accidents to develop comparative scenarios for each type of road and collision type of traffic accidents. When the road types of traffic accidents in Korea were divided into five types and the collision types were divided into six, it was confirmed that the most types of FRONT-SIDE crashes appeared at the intersection. It is expected that the frequency of possible traffic accidents and collision types can be predicted according to the road type in the accident database, we that it can be used as an AEBS test scenario development suitable for the domestic road environment.