Search

Your search keyword '"Kim, Kyonghoon"' showing total 13 results
Start Over Author "Kim, Kyonghoon"
13 results on '"Kim, Kyonghoon"'

7. CNN- and UAV-Based Automatic 3D Modeling Methods for Building Exterior Inspection.

Author

Yoon, Jonghyeon, Shin, Hyunkyu, Kim, Kyonghoon, and Lee, Sanghyo

Subjects
BUILDING inspection, DRONE aircraft, CONSTRUCTION defects (Buildings), BUILDING maintenance, CONVOLUTIONAL neural networks, GEOGRAPHIC information systems
Abstract

Building maintenance plays an increasingly important role as buildings age. During maintenance, it is necessary to analyze building defects and record their locations when performing exterior inspections. Hence, this study proposes an automatic three-dimensional (3D) modeling method based on image analysis using unmanned aerial vehicle (UAV) flights and convolutional neural networks. A geographic information system is used to acquire geographic coordinate points (GCPs) for the geometry of the building, and a UAV is flown to collect the GCPs and images, which provide location information on the building elements and defects. Comparisons revealed that the generated 3D models were similar to the actual buildings. Next, the recorded locations of the building defects and the actual locations were examined, and the results confirmed that the defects were generated correctly. Our findings indicated that the proposed method can improve building maintenance. However, it has several limitations, which provide directions for future research. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

11. Interference Aware Real-Time Flows Scheduling in Cluster Based Wireless Sensor Networks

Author

Ali, Gohar, Kim, KyongHoon, Kim, Ki-Il, Aldwairi, Monther, Ali, Gohar, Kim, KyongHoon, Kim, Ki-Il, and Aldwairi, Monther

Abstract

For the real-time scheduling in wireless sensor networks, Time Division Multiple Access (TDMA) under cluster architecture is usually considered as reasonable as well as scalable approach. Under this architecture, several type of inferences should be taken into account to allocate time slot. For this goal, we have already proposed a new real-time scheduling algorithm. But, it has several assumptions and constraints so their deployment is limited to some specific real scenarios. In this paper, we additionally concern the interference of a node which belongs to two clusters concurrently. Token based scheduling algorithm between two cluster heads is proposed to solve this problem. Token is given to each cluster head consequently so order of slot allocation is achieved automatically. Finally, simulation results are given to prove that more flows are delivered within the deadline than previous work due to avoidance of inter-cluster interference in efficient way.

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results