• Structural Monitoring and Maintenance
• /
• v.10 no.2
• /
• pp.133-154
• /
• 2023

Obscured structural members are mostly under-evaluated during condition assessment due to lack of visual inspection capability. Insufficient information about the integrity of these structural members poses a significant risk for public safety. Time domain reflectometry (TDR) is a novel approach in structural health monitoring (SHM). Ordinary coaxial cables "as is" without a major modification are not suitable for SHM with TDR. The objective of this study is to propose a practical and cost-effective modification approach to commercially available coaxial cables in order to use them as a "cable sensor" for damage detection with the TDR equipment for obscured structural members. The experimental validation and assessment of the proposed modification approach was achieved by conducting 3-point bending tests of the model piles as a representative obscured structural member. It can be noted that the RG59/U-6 and RG6/U-4 cable sensors expose higher strain sensitivity in comparison with non-modified "as is" versions of the cables used. As a result, the cable sensors have the capability of sensing both the presence and the location of a structural damage with a maximum aberration of 3 cm. Furthermore, the crack development can be monitored by the RG59/U-6 cable sensor with a simple calibration.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.599-605
• /
• 2017

Accurate cloud discrimination in satellite images strongly affects accuracy of remotely sensed parameter produced using it. Especially, cloud contaminated pixel over ocean is one of the major error factors such as Sea Surface Temperature (SST), ocean color, and chlorophyll-a retrievals,so accurate cloud detection is essential process and it can lead to understand ocean circulation. However, static threshold method using real-time algorithm such as Moderate Resolution Imaging Spectroradiometer (MODIS), Advanced Himawari Imager (AHI) can't fully explained reflectance variability over ocean as a function of relative positions between the sun - sea surface - satellite. In this paper, we assembled a reflectance spectral library as a function of Solar Zenith Angle (SZA) and Viewing Zenith Angle (VZA) from ocean surface reflectance with clear sky condition of Advanced Himawari Imager (AHI) identified by NOAA's cloud products and spectral library is used for applying the Dynamic Time Warping (DTW) to detect cloud pixels. We compared qualitatively between AHI cloud property and our results and it showed that AHI cloud property had general tendency toward overestimation and wrongly detected clear as unknown at high SZA. We validated by visual inspection with coincident imagery and it is generally appropriate.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1151-1157
• /
• 2017

Street Trees is an important object for urban environment improvement. Especially the height of the trees needs to be precisely measured as a factor that greatly influences the removal of air pollutants in the Urban Street Canyons. In this study, we extracted the height of the tree based on the stereo image using the precisely adjusted UAV Images of the target area. The adjustment of UAV image was applied photogrammetric SfM (Structure from motion) based on the collinear condition. We measured the height of the trees on the Street Canyon using stereoscopic vision on stereo plotting system. We also acquired the height of the building adjacent to the street trees and the average height of the road surface was calculated for accurate measurement of the height of each object. Through the visual analysis with the plotting operation system, it was possible to measure height of the tree and to calculate the relative height difference value with building quickly. This means that the height of buildings and trees can be calculated without making a 3D point cloud of UAV and it has the advantage of being able to utilize non-experts. In the future, further studies for semiautomatic/automation of this technique should be performed. The development and research of these technologies is expected to help to understand the current status of environmental policies and roadside trees in urban areas.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1095-1107
• /
• 2020

Flood monitoring using satellite data has been constrained by obtaining satellite images for flood peak and accurately extracting flooded areas from satellite data. Deep learning is a promising method for satellite image classification, yet the potential of deep learning-based flooded area extraction using SAR data remained uncertain, which has advantages in obtaining data, comparing to optical satellite data. This research explores the performance of SegNet and U-Net on image segmentation by extracting flooded areas in the Khorat basin, Mekong river basin, and Cagayan river basin in Thailand, Laos, and the Philippines from Sentinel-1 A/B satellite data. Results show that Global Accuracy, Mean IoU, and Mean BF Score of SegNet are 0.9847, 0.6016, and 0.6467 respectively, whereas those of U-Net are 0.9937, 0.7022, 0.7125. Visual interpretation shows that the classification accuracy of U-Net is higher than SegNet, but overall processing time of SegNet is around three times faster than that of U-Net. It is anticipated that the results of this research could be used when developing deep learning-based flood monitoring models and presenting fully automated flooded area extraction models.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.313-326
• /
• 2018

This paper introduces core techniques on ship detection and tracking based on a compact HF radar platform which is necessary to establish a wide-area surveillance network. Currently, most HF radar sites are primarily optimized for observing sea surface radial velocities and bearings. Therefore, many ship detection systems are vulnerable to error sources such as environmental noise and clutter when they are applied to these practical surface current observation purpose systems. In addition, due to Korea's geographical features, only compact HF radars which generates non-uniform antenna response and has no information on target information are applicable. The ship detection and tracking techniques discussed in this paper considers these practical conditions and were evaluated by real data collected from the Yellow Sea, Korea. The proposed method is composed of two parts. In the first part, ship detection, a constant false alarm rate based detector was applied and was enhanced by a PCA subspace decomposition method which reduces noise. To merge multiple detections originated from a single target due to the Doppler effect during long CPIs, a clustering method was applied. Finally, data association framework eliminates false detections by considering ship maneuvering over time. According to evaluation results, it is claimed that the proposed method produces satisfactory results within certain ranges.

• Korean Journal of Remote Sensing
• /
• v.25 no.5
• /
• pp.445-454
• /
• 2009

Localized unprecedented torrential rain and heavy rainfall cause repeated damages and make it difficult to detect and predict the landslide caused by heavy rainfall. To analyze the landslide characteristics of Inje area this study used satellite images photographed after the occurrence of landslide caused by the typhoon Ewiniar occurred in July, 2006, and for GIS analysis purpose, interpreted the satellite images (SPOT5) visually to digitize into developing parts, water traveling parts and sediment parts. For analysis of spatial characteristics, landslide areas obtained from visual interpretation of digital map, 3rd & 4th forest vegetation maps and detailed soil map and grids were overlaid and analyzed. As a result, in regard to topographic features, landslide occurred at places, of which average slope is $26.34^{\circ}$, had south, south-east, south-west aspects and average altitude of 627m. From hydrological analysis, it was found out that water traveling area rapidly spread approaching water traveling area and sediment area. From forest type analysis, it was found out that landslide occurrence was high in pine woods, and in terms of girth class attribute, landslide occurred in small-sized woods, in which the crown occupancy of trees that have the diameter at breast height, 6~16cm, was greater than 50%. From the analysis of soil series, landslide areas constitute 37.85% of OdF and 37.35% of SmF, which had sandy loam soil and excellent drainage capacity. Through this study, landslides in Inje area were characterized and SPOT5 images of 2.5m resolution could be used. But there was a difficulty in determining water traveling parts adjacent to urban area.

• Korean Journal of Remote Sensing
• /
• v.11 no.3
• /
• pp.33-47
• /
• 1995

The representation of point-observed environmental variables in Geographic Information Systems(GIS) has often been inadequate to meet the need of regional-scale ecological and environmental applications. To create a map of continuous surface that would represent more reliable spatial variations for these applications, I present three spatial estimation methods. Using a secondary variable of the proximity to coast line together with rainfall acidity data collected at the 63 acid rain monitoring stations in Korea, average rainfall acidity map was cteated using co-kriging. For comparison, two other commonly used interpolation methods (inverse distance weighting and kriging) were also applied to rainfall acidity data without reference to the secondary variable. These estimation methods were evaluated by both visual assessments of the output maps and the quantitative comparison of error measures that were obtained from cross validation. The co-kriging method produced a rainfall acidity map that showed noticeable improvement in repoducing the inherent spatial pattern as well as provided lower statistical error as compared to the methods using only the primary variable.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.905-923
• /
• 2018

In order to generate high-resolution products using UAV images, it is necessary to analyze the sharpness of the themselves measured through image analysis. When images that have unclear sharpness of UAV are used in the production, they can have a great influence on operations such as acquisition and mapping of accurate three-dimensional information using UAV. GRD (Ground Resolved Distance) has been used as an indicator of image clarity. GRD is defined as the minimum distance between two identifiable objects in an image and is used as a concept against the GSD (Ground Sampling Distance), which is a spatial sample interval. In this study, GRD is extracted by analyzing the edge target without visual analysis. In particular, GRD to GSD ratio (GRD/GSD), or GRD expressed in pixels, is used as an index for evaluation the relative image sharpness. In this paper, GRD is calculated by analyzing edge targets at various altitudes in various shooting environments using a rotary wing. Using GRD/GSD, it was possible to identify images whose sharpness was significantly lowered, and the appropriateness of the image as an image clarity index was confirmed.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.2
• /
• pp.111-116
• /
• 2019

The biotic stress of garlic and tobacco infected by bacteria and virus was evaluated using a thermal imaging camera in a growth chamber. The remote sensing technique using the thermal camera detected that garlic leaf temperature increased when the leaves were infected by bacterial soft rot of garlic. Furthermore, the temperature of leaf was relatively high for the leaves where the colony-forming unit per mL was large. Such temperature patterns were detected for tobacco leaves infected by Cucumber Mosaic Virus using thermal images. In addition, the crop water stress index (CWSI) calculated from leaf temperature also increased for the leaves infected by the virus. The event such that CWSI increased by the infection of the virus occurred before visual disease symptom appeared. Our results suggest that the thermal imaging camera would be useful for the development of crop remote sensing technique, which can be applied to a smart farm.