• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.555-558
• /
• 2006

In recent years, urban development has expanded rapidly in Nawabshah City of Pakistan. A major effect associated with this population trend is transformation of the landscape from natural cover types to increasingly impervious urban land. The core objective of this study are to provide time-series information to define and measure the urban land cover changes of Nawabshah, Pakistan between the years 1992 and 2002, and to examine related urbanization impacts on air quality of the study area. Two multi-temporal Landsat images acquired in 1992 and 2002 together with standard topographical maps to measure land cover changes were used in this study. The image processing and data manipulation were conducted using algorithms supplied with the ERDAS Imagine software. An unsupervised classification approach, which uses a minimum spectral distance to assign pixels to clusters, was used with the overall accuracy ranging from 84 percent to 92 percent. Land cover statistics demonstrate that during the study period (1992-2002) extensive transformation of barren and vegetated lands into urban land have taken place in Nawabshah City. Results revealed that land cover changes due to urbanization has not only contaminated the air quality of the study area but also raised the health concerns for the local residents.

• Journal of Auto-vehicle Safety Association
• /
• 제13권4호
• /
• 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.

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 한국조경학회 1999년도 정기대회 및 학술논문발표회
• /
• pp.20-21
• /
• 1999

• Ecology and Resilient Infrastructure
• /
• 제3권4호
• /
• pp.315-321
• /
• 2016

To identify the relationship between land use and thermal environment in an urban area, the air temperature was measured at different places of land use, and the changes of land use and air temperature were traced for 40 years in Incheon City. The relationship between land use and temperature was also investigated using satellite image data. The results of temperature measurements on a forest, a cropland (rice paddy), a bareland (school ground), and an urban area (asphalt road) from 19 to 21 August 2014 showed that air temperature was the highest on a pavement road. The temperature increased by about $1.4^{\circ}C$ ($0.035^{\circ}C/year$) for 40 years from 1975 to 2014 in Incheon. The changes in land use patterns of Incheon for the past 40 years showed that urban dry land, bareland and grassland have increased and cultivated land, wetland and forest land have decreased gradually. The land surface temperature (LST) was correlated with the normalized difference vegetation index (NDVI) and normalized difference built-up index (NDBI) extracted from Landsat satellite image. The land surface temperature was lower at higher NDVI, and higher at higher NDBI. Therefore, it is important to conserve and restore the land use of greenery, wetlands, and agricultural land in order to mitigate the heat island effect and improve the thermal environment in an urban area.

• Korean Association of Arts Management
• /
• 제49호
• /
• pp.149-176
• /
• 2019

It is a known fact that the spread of multiplexes has contributed to movie industry flourish and extending public rights for enjoying movies. However, in terms of Urban Discourse, Multiplexes centered in new downtown have given rise to Doughnut Phenomena in old downtown. It is especially regrettable that the local theaters which have been symbolic cultural spaces storing the 'memory of life' of local communities are disappearing due to a recession of business zone in old downtown. Japan has long been worked in various activities spotlighting on movie/image contents as the major means of creative urban regeneration. Among them, the 'Community Cinema' has made a contribution to regional revitalization by improving movie screening environment of the local community through renewal of local theaters and further creating related culture and industry in the local area. In this study, I focus on 'Fukaya Cinema' which started from NPO(Non-Profit Organization) and reused a closed industrial facility to a movie theater in cooperation with local TMO(Town Management Organization). Fukaya Cinema, which operates in the form of a business community, plays important roles as the core cultural facility in the local community and is regarded as a significant case showing a possibility of urban regeneration using movie/image contents. I investigate the specific founding process and activities of Fukaya Cinema and intend to derive the implications from that. Through this, I aim to provide the basic urban regeneration data utilizing movie/media contents.

• Journal of Korea Water Resources Association
• /
• 제56권10호
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• Korean Journal of Remote Sensing
• /
• 제33권6_3호
• /
• pp.1171-1177
• /
• 2017

This special issue introduces recent researches on KOMPSAT(KOrea Multi-Purpose SATellite) image processing and applications. In this paper, the status of KOMPSAT development and national satellite image application policy are introduced and the implications of the papers presented in the special issue are discussed. Satellite image resources and application policy that can be utilized through continuous satellite development are considered to be systematically prepared. Therefore, if data processing and application technology development for various fields such as forest and urban change detection, image correction technology introduced in this paper are continuously carried out, it is expected that the competitiveness of national satellite image will be further strengthened.

• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.260-262
• /
• 2006

One of future remote sensing techniques for transportation application is vehicle detection from the space, which could be the basis of measuring traffic volume and recognizing traffic condition in the future. This paper introduces an approach to vehicle detection using image object segmentation approach. The object-oriented image processing is particularly beneficial to high-resolution image classification of urban area, which suffers from noisy components in general. The project site was Dae-Jeon metropolitan area and a set of true color aerial images at 10cm resolution was used for the test. Authors investigated a variety of parameters such as scale, color, and shape and produced a customized solution for vehicle detection, which is based on a knowledge-based hierarchical model in the environment of eCognition. The highest tumbling block of the vehicle detection in the given data sets was to discriminate vehicles in dark color from new black asphalt pavement. Except for the cases, the overall accuracy was over 90%.

• Korean Institute of Interior Design Journal
• /
• 제17권2호
• /
• pp.30-38
• /
• 2008

It has been stated that the outer skin of an architecture should be related to and express the interior programs. It was rather moral issue than practicality. In contemporary urban cities, this nicely-linked relationship between exterior and interior has become much more complex and, in many cases, is no more valid. It tends that contemporary architectural skin is somehow separately developed and has its own logic to be independent from what is inside. This research focuses on these sort of logical design process to make unique image of skin in which conceptual thinking, spatialization and materialization are mixed together. More specifically this study articulates' expandable patternization process' based on the notion that it has a crucial role to systematically construct an image of skin. Expandable patternization has a couple of stages to complete an architectural skin. The first element is a single unit and the second is organization or arrangement of units based on a logical process. Lastly, the third is spatialization after relating the skin to the interior programs as well as environmental surroundings. It is found that, although, in most related projects, the architect or designer has followed his or her own preference or design tendencies, many skin projects has based the given unique characteristics from the beginning. This study concludes that skin design is not just an image making, but has an important role to amalgamate various aspects of an architectural projects: programs, concept of architect, environment, structure as well as image.

• Journal of KIBIM
• /
• 제11권2호
• /
• pp.54-59
• /
• 2021

In the process of designing a building, the process of expressing the designer's ideas through images is essential. However, it is expensive and time consuming for a designer to analyze every individual case image to generate a hypothetical design. This study aims to visualize the basic design draft sketch made by the designer as a real image using the Generative Adversarial Network (GAN) based on the continuously accumulated architectural case images. Through this, we proposed a method to build an automated visualization environment using artificial intelligence and to visualize the architectural idea conceived by the designer in the architectural planning stage faster and cheaper than in the past. This study was conducted using approximately 20,000 images. In our study, the GAN algorithm allowed us to represent primary materials and shades within 2 seconds, but lacked accuracy in material and shading representation. We plan to add image data in the future to address this in a follow-up study.