• Korean Journal of Remote Sensing
• /
• v.20 no.5
• /
• pp.329-335
• /
• 2004

Biotop map can be utilized for nature conservation and assessment of environmental impact for human activities in urban area. High resolution satellite images such as IKONOS and KOMPSAT1-EOC were interpreted to classify land use, hydrology, impermeable pavement ratio and vegetation for biotop mapping. Wildlife habitat map and detailed vegetation map obtained from former study results were used as ground truth data. Vegetation was investigated directly for the area where the detailed vegetation map is not available. All these maps were combined and the boundaries were delineated to produce the biotop map. Within the boundary, the characteristics of each polygon were identified, and named. This study investigates the possibility of biotop mapping using high resolution satellite remote sensing data together with field data with the goal of contributing to nature conservation in urban area.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.1
• /
• pp.78-83
• /
• 2007

Robot collects surrounding information to recognize tile unknown environment by using various sensors such as visual, infrared ray and ultra sonic sensors. Although visual sensor is the most popular one, it has some difficulties in collecting data in dark or too bright environment due to sensitivity of the light. It also requests significant amount of calculation on collecting data from certain images with marked, straight and curved ones. As an alternative, ultra sonic sensor can simply overcome this visual sensing system's flaw and easily be used. It is easier than visual system, especially in case of collecting data on object and distance in dark environment. Ultra sonic sensor can replace the expensive visual sensing system not only in avoiding obstacles but also in reaching to the target area smoothly. The purpose of this paper is to develop the algorithm to optimize the environmental recognition, path planning and free-ranging by minimizing errors caused by inaccurate information and by considering characteristics of the ultra sonic rays such as refraction and diffusion. This paper also realizes the system that can recognize the environment and make the appropriate path planning by applying the algorithm on this moving robot.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.551-554
• /
• 2006

House management is very important in water resource protection in order to provide sustainable drinking water for about four millions population in northern Taiwan. House management can be a simple job that can be done without any ingredient of remote sensing or geographic information systems. Remote sensing and GIS integration for house management can provide more efficient management prescription when land use enforcement, soil and water conservation, sewage management, garbage collection, and reforestation have to be managed simultaneously. The objective of this paper was to integrate remote sensing and GIS to manage houses in a water resource protection district. More than four thousand houses have been surveyed and created as a house data base. Site map of every single house and very detail information consisting of address, ownership, date of creation, building materials, acreages floor by floor, parcel information, and types of house condition. Some houses have their photos in different directions. One house has its own card consists these information and these attributes were created into a house data base. Site maps of all houses were created with the same coordinates system as parcel maps, topographic maps, sewage maps, and city planning maps. Visual Basic.NET, Visual C#.NET have been implemented to develop computer programs for house information inquiry and maps overlay among house maps and other GIS map layers. Remote sensing techniques have been implemented to generate the background information of a single house in the past 15 years. Digital orthophoto maps at a scale of 1:5000 overlay with house site maps are very useful in determination of a house was there or not for a given year. Satellite images if their resolutions good enough are also very useful in this type of daily government operations. The developed house management systems can work with commercial GIS software such as ArcView and ArcPad. Remote sensing provided image information of a single house whether it was there or not in a given year. GIS provided overlay and inquiry functions to automatically extract attributes of a given house by ownership, address, and so on when certain house management prescriptions have to be made by government agency. File format is the key component that makes remote sensing and GIS integration smoothly. The developed house management systems are user friendly and can be modified to meet needs encountered in a single task of a government technician.

• Smart Structures and Systems
• /
• v.8 no.5
• /
• pp.471-486
• /
• 2011

Various types of strain sensors have been developed and widely used in the field for monitoring the mechanical deformation of structures. However, conventional strain sensors are not suited for measuring large strains associated with impact damage and local crack propagation. In addition, strain sensors are resistive-type transducers, which mean that the sensors require an external electrical or power source. In this study, a gold nanoparticle (GNP)-based polymer composite is proposed for large strain sensing. Fabrication of the composites relies on a novel and simple in situ GNP reduction technique that is performed directly within the elastomeric poly(dimethyl siloxane) (PDMS) matrix. First, the reducing and stabilizing capacities of PDMS constituents and mixtures are evaluated via visual observation, ultraviolet-visible (UV-Vis) spectroscopy, and transmission electron microscopy. The large strain sensing capacity of the GNP-PDMS thin film is then validated by correlating changes in thin film optical properties (e.g., maximum UV-Vis light absorption) with applied tensile strains. Also, the composite's strain sensing performance (e.g., sensitivity and sensing range) is also characterized with respect to gold chloride concentrations within the PDMS mixture.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.455-457
• /
• 2003

Diverse researches are working moving objects. The most important activities in a moving object database system are query and analysis of spatio -temporal data providing decision-making and problem solving support. Traditional spatial database query language and tools are inappropriate of the real world entities. This paper presents a spatio-temporal query and analysis tool with visual environment. It provides effective, interactive and user-friendly as well as statistic analysis. The moving objects database system stores plentiful moving objects data and performs spatio-temporal and nonspatio-temporal queries.

• Spatial Information Research
• /
• v.14 no.3 s.38
• /
• pp.299-319
• /
• 2006

This research is primarily intended to investigate the potential of estimating green space threshold in terms of total volume control using degradation trends of green space derived from remote sensing and GIS. An empirical study for a case study site was conducted to demonstrate how a standard remote sensing and GIS technology can be used to assist in estimating the total control volume for green space in terms of area-wide information, spatial resolution and change detection etc. Guidelines for a replicable methodology are presented to provide a strong theoretical basis for the standardization of factors involved in the estimation of the green space threshold; the meaningful definition of land mosaic, redefinition of degradation trends for green space. It was demonstrated that the degradation trends of green space could be used effectively as an indicator to restrict further development of the sites since the visual maps generated from remote sensing and GIS can present area-wide visual evidences by permanent record. It is anticipated that this research output could be used as a valuable reference to support more scientific and objective decision-making in introducing aggregate control of green space.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.200-208
• /
• 2016

Compressed sensing is a signal processing technique for efficiently acquiring and reconstructing in an under-sampled (i.e., under Nyquist rate) representation. A block compressed sensing with projected Landweber (BCS-SPL) framework is most widely known, but, it has high computational complexity at decoder side. In this paper, by introducing adaptive exit criteria instead of fixed exit criteria to SPL framework, an effective fast algorithm is designed in such a way that it can utilize efficiently the sparsity property in DCT coefficients during the iterative thresholding process. Experimental results show that the proposed algorithm results in the significant reduction of the decoding time, while providing better visual qualities than conventional algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1694-1699
• /
• 2003

A windshield wiper system plays a key part in assuring the driver's safety during the rainfall. However, because the quantity of rain and snow vary irregularly according to time and the velocity of the automobile, a driver changes wiper speed and interval from time to time to secure enough visual field in the traditional windshield wiper system. Because a manual operation of windshield wiper distracts driver's sensitivity and causes inadvertent driving, this is becoming a direct cause of traffic accidents. Therefore, this paper presents the basic architecture of a vision-based smart windshield wiper system and a rain sensing algorithm that regulates speed and interval of the windshield wiper automatically according to the quantity of rain or snow. This paper also introduces a fuzzy wiper control algorithm based on human's expertise, and evaluates the performance of the suggested algorithm in an experimental simulator.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.260-263
• /
• 2005

This study was carried out to investigate the effects of spatial resolutions on digital image for detecting pine trees damaged by pine wilt disease. Color infrared images taken from PKNU-3 multispectral airborne photographing system with a spatial resolution of 50cm was used as a basic data. Further test images with spatial resolutions of 1m, 2m and 4m were made from the basic data to test the detecting capacity on each spatial resolution. The test was performed with visual interpretation both on mono and stereo modus and compared with field surveying data. It can be conclude that it needs less than 1m spational resolutions or 1m spatial resolutions with stereo pair in order to detect pine trees damaged by pine wilt disease.