• Journal of Drive and Control
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

• Journal of Distribution Research
• /
• v.12 no.2
• /
• pp.79-102
• /
• 2007

Consumers evaluate stores by comparing stores that we, in their minds, similar and are competitive with one another; and in this way, the term "consideration set of stores" is defined as those store alternatives the consumer is aware of and evaluates positively. The purpose of this study is to aid in understanding the consideration set of stores in store choice processes in apparel product purchases. More specifically, this study aims to clarify the relation between consideration set of stores and importance of store image. As a result, the respondents of quantitative study were classified into seven groups by the number of stores and store types they considered: 1) "small-road shop sets group" ; 2) "small-market sets group" ; 3) "small- department store sets group" ; 4) "small-department store/outlet sets group" ; 5) "large-department store/market sets group" ; 6) "large-department store/road shop sets group" ; and 7) "large-department store sets group". Further, significant differences among the groups in the importance of store image were observed. For example, low prices were an important factor in both the small-market considering group and large-department store/market considering group when choosing a retail store, there were also differences in the considering groups in that for the small-department store considering group, store mileage-discount cards were important whereas ample space for relaxation around the stores were important retail store selection factors for the large-department store/road shop considering group. This study may provide a useful direction to retailers in finding out who the target customers and competitive stores are and allow retailers to make proper marketing strategies.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.6
• /
• pp.61-74
• /
• 2023

The concept of "green infrastructure" emphasizes the close relationship between natural and urban social systems, thereby providing services that protect the ecological environment and improve the quality of human life. The Green View Index(GVI) is an important indicator for measuring the supply of urban green space and contains more 3D spatial elements concerning the green space ratio. This study focused on an area within the Third Ring Road in the city of Chengdu, Sichuan Province, China. The purposes of this study were three-fold. First, this study analyzed the spatial distribution characteristics of the GVI in urban streets and its correlation with the urban park green space system using Street View image data. Second to analyze the characteristics of low GVI streets were analyzed. Third, to analyze the connectivity between road traffic and street GVI using space syntax were analyzed. This study found that the Street GVI was higher in the southwestern part of the study area than in the northeastern part. The spatial distribution of the street GVI correlated with urban park green space. Second, the street areas with low GVI are mainly concentrated in areas with dense commercial facilities, areas with new construction, areas around elevated roads, roads below Class 4, and crossroads areas. Third, the high integration and low GVI areas were mainly concentrated within the First Ring Road in the city as judged by the concentration of vehicles and population. This study provides base material for future programs to improve the GVI of streets in Chengdu, Sichuan Province.

• Journal of the Society of Disaster Information
• /
• v.15 no.4
• /
• pp.548-559
• /
• 2019

Purpose: Analysis method of V2I data driven motorway service area usage behavior to cope with manpower survey. Method: Segmentation of traveling state group and boundary using the distribution characteristics of traveling speed data of individual vehicles. Result: As a result of the verification, the use rate of resting places in lunchtime surged, and the boundary between the distribution status of the traffic speed data was clearly or unclear. Conclusion: The effect of the cost reduction is big because it can cope with the use of rest area survey by manpower and there is no limit in the time and space range of investigation. The dynamic utilization rate of each time sequence, such as a service area/drowsiness shelter/simple service area, with a V2I system, can be calculated. Identify illegal parking on highway section. Identify the unexpected situation in the road section. Identify the real-time service area utilization rate and congestion information.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• Journal of the Economic Geographical Society of Korea
• /
• v.26 no.2
• /
• pp.123-136
• /
• 2023

Upon examining land prices in the eastern district of Gyeongseong, it was observed that there were variations in land prices between the northern and southern areas, with the central part being densely populated with modern facilities such as hospitals, schools, and research institutions. As a result, the eastern district of Gyeongseong was further divided into specific sub-areas, namely the northeastern and southeastern, for a more detailed analysis of the land market in each area. In the northeastern area, factors such as distance from the central area and proximity to planned roads were found to have an impact on land prices. On the other hand, in the southeastern area, the distance between the main road, whice were IHyun Road and Jongro, was identified as a significant influencer of land prices. Therefore, the northeastern area exhibited characteristics of a hinterland, influenced by the concentration of major facilities in the central area, while the southeastern area had a strong commercial orientation, largely shaped by the influence of Jongro as a bustling commercial district. This study is significant in that it sheds light on certain aspects of the modern land market by demonstrating that factors such as accessibility to roads and anchor facilities, as well as the segmentation of the land market, were also influential in the land market a century ago.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.150-157
• /
• 2015

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.

• Journal of Platform Technology
• /
• v.9 no.4
• /
• pp.71-78
• /
• 2021

Self-driving vehicles are increasing as new alternatives to solving problems such as human safety, environment and aging. And such technology development has a great ripple effect on other industries. However, various problems are occurring. The number of casualties caused by self-driving is increasing. Although the collision of fixed obstacles is somewhat decreasing, on the contrary, the technology by active obstacles is still insignificant. Therefore, in this study, in order to solve the core problem of self-driving vehicles, we propose a method of extracting active obstacles on the road. First, a center scene is extracted from a continuous image. In addition, it was proposed to extract activity obstacles using activity size and activity repeatability information from objects included in the center scene. The center scene is calculated using region segmentation and merging. Based on these results, the size of the frequency for each pixel in the region was calculated and the size of the activity of the obstacle was calculated using information that frequently appears in activity. Compared to the results extracted directly by humans, the extraction accuracy was somewhat lower, but satisfactory results were obtained. Therefore, it is believed that the proposed method will contribute to solving the problems of self-driving and reducing human accidents.