• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.105-115
• /
• 2014

In this research, we developed video analytic algorithms to detect water-level automatically and a system for proactive alarming using intelligent CCTV cameras. We applied these algorithms and a system to test-beds and verified for practical use. We made camera-selection policies and operation plans to keep the detection accuracy high and to optimize the suitability for the ever-changing weather condition, while the environmental factors such as camera shaking and weather condition can affect to detection accuracy. The estimation result of algorithms showed 90% detection accuracy for all CCTV camera types. For water level detection, NIR camera performed great. NIR camera performed over 95% accuracy in day or night, suitable in natural weather condition such as shaking condition, fog, and low light, needs similar installment skills with common cameras, and spends only 15% high cost. As a result, we practically tested water level detection algorithms and operation system based on intelligent CCTV camera. Furthermore, we expect the positive evidences when it is applied for public use.

• Journal of Biosystems Engineering
• /
• v.26 no.2
• /
• pp.169-176
• /
• 2001

Defect of apple was depreciated the product value and causes storage disease seriously. To detect the defect of ‘Fuji’apple with machine vision system, the optical characteristics of defect should be investigated. In this research, absorbance spectra of defect were acquired by spectrophotometer in the range of visible and NIR region(400∼1,100nm) and L*a*b* color values were also acquired by colorimeter. NIR machine vision system was constructed with B&W camera, frame grabber, 16 tungsten-halogen lamps, variable focal length lens and NIR bandpass filter which was mounted to lens outward. Average gray values of defect at 15 NIR wavelength were acquired and the significant NIR wavelength was selected by comparing Mahalanobis distance between sound and defective apple. As the result of Mahalanobis distance analysis, the significant wavelength to discriminate the defectives in ‘Fuji’apple were found to be 720nm for scab and 970nm for bruise and cuts and 920nm was also effective regardless of defective types.

• Journal of Sensor Science and Technology
• /
• v.26 no.2
• /
• pp.91-95
• /
• 2017

Recently, infrared (IR) spectrometers have been required in various fields such as environment, safety, mobile, automotive, and military. This IR dispersive sensor detection method of substances is widely used. In this study, we fabricated a silicon (Si) prism-based near infrared (NIR) spectrometer utilizing micro electro mechanical system (MEMS) technology. Si prism-based NIR spectrometer utilizing MEMS technology consists of upper, middle, and lower substrates. The upper substrate passes through the incident IR ray selectively. The middle substrate, acting as a prism, disperses and separates the incident IR beam. The lower substrate has an amorphous Si (a-Si)-based bolometer array to detect the IR spectrum. The fabricated Si prism-based NIR spectrometer utilizing MEMS technology has the advantage of a simple structure, easy fabrication steps, and a wide NIR region operating range.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.104-104
• /
• 2017

정상적인 부화 여부를 판별하기 위한 1차 검란은 일반적으로 5일~7일 이후에 시행된다. 미부화란을 이보다 더 빠른 시간 안에 검출할 경우 부화에 소요되는 에너지의 감소 효과 및 미부화란을 다른 용도로 활용하는 것을 기대할 수 있다. 시중에서 쉽게 구입할 수 있는 산란계인 하이라인 브라운 품종의 유정란 29개와 인위적인 미부화란을 만들기 위한 동일 품종의 무정란 11개를 사용하였으며 $38^{\circ}C$, 70% 조건의 항온항습기에서 96시간 동안 부화하였다. 스펙트럼 획득 장치의 광원은 녹색영역을 발광하는 LED램프와 일반 할로겐 광원을 별도로 사용하였으며 스펙트로미터는 VIS/NIR 영역인 520~1,180nm영역과 NIR영역인 900~1,700nm영역의 것을 사용하였다. 부화 시작 전과 부화 시작 후 1일 간격으로 각각 1개의 샘플에 대한 1개의 스펙트럼을 측정하였다. 측정 영역은 LED광원을 이용한 경우는 520~1,1800nm, 할로겐광원을 이용한 경우에는 520~1,180nm와 900~1,700nm이었다. 정상 부화여부는 4일차에서 할란하여 확인하였고, 측정 일자별로 PLS-DA분석법을 이용한 판별 모델을 개발하였다. 4일차에서 유정란 29개 중 11개가 정상 부화하였고, 18개는 미부화하였다. 3일차에서 판별 모델의 정확도는 LED광원의 VIS/NIR 영역 스펙트럼을 이용한 경우는 100%, 할로겐 광원의 VIS/NIR 영역 스펙트럼을 이용한 경우는 70%, 할로겐 광원의 NIR영역 스펙트럼을 이용한 경우는 70%였다. 4일차에서 판별 모델의 정확도는 LED광원의 VIS/NIR 영역 스펙트럼을 이용한 경우는 100%, 할로겐 광원의 VIS/NIR 영역 스펙트럼을 이용한 경우는 90%, 할로겐 광원의 NIR영역 스펙트럼을 이용한 경우는 100%였다. 부화 3일차는 정상 부화할 경우 피가 생성되는 시기이다. 피가 형성된 이후의 부화 여부를 판단하는 광원으로는 할로겐램프보다 LED램프를 사용하는 것이 더 적합한 것으로 나타났다.

• Journal of Sensor Science and Technology
• /
• v.20 no.6
• /
• pp.388-392
• /
• 2011

In this paper, a face detection method for interactive TV control system using a new feature, edge histogram feature, with a support vector machine(SVM) in the near-infrared(NIR) images is proposed. The edge histogram feature is extracted using 16-directional edge intensity and a histogram. Compared to the previous method using local binary pattern(LBP) feature, the proposed method using edge histogram feature has better performance in both smaller feature size and lower equal error rate(EER) for face detection experiments in NIR databases.

• Journal of Digital Contents Society
• /
• v.13 no.2
• /
• pp.189-195
• /
• 2012

In this paper, face detection method in NIR(Near-InfraRed) images for human recognition is proposed. Edge histogram based on edge intensity and its direction, has been used to detect effectively faces on NIR image. The edge histogram descripts and discriminates face effectively because it is strong in environment of lighting change. SVM(Support Vector Machine) has been used as a classifier to detect face and the proposed method showed better performance with smaller features than in ULBP(Uniform Local Binary Pattern) based method.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_3
• /
• pp.889-900
• /
• 2017

In this study, we analyzed the paper about NIR (Near-Infrared) remote sensing data and systematically summarized the research and application fields of NIR. To do this, we conducted a case study on the use of NIR in domestic journals, and SCI journals in the field of technology development for the last 5 years. After selection, a total of 281 journals were analyzed. For the statistical analysis, the classification was divided into subclasses and the dominant research trends were examined. As a result, the researchers who wrote the papers made the highest score of about 60% or more at university. In the field of application, 50% of land, 30% of environment, and 11% of disaster were distributed on SCI journals. In Korea, on the other hand, 55% of land, 24% of environment and 10% of disasters were distributed. In addition, 17% of the national land management and 8% of the geological / natural resources. Disaster observation using NIR was used for landslide, drought, weather disaster and flood. In particular, meteorological disasters are a result of study on Asian dust. However, there were no results of forest fire detection in Korea. Considering the domestic situation, it seems necessary to carry out additional and active research on this. It is expected that this statistical analysis data will be used as basic data to help expand the NIR technology development and utilization field in Korea in the future.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.02a
• /
• pp.445-450
• /
• 2000

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.113-127
• /
• 2015

Recently, there has been a growing interest in UAS(Unmanned Aerial System), and it is required to develop techniques to effectively detect water body from the recorded images in order to implement flood monitoring using UAS. This study used a UAS with RGB and NIR+RG bands to achieve images, and applied supervised classification method to evaluate the accuracy of water body detection. Firstly, the result for accuracy in water body image classification by RGB images showed high Kappa coefficients of 0.791 and 0.783 for the artificial neural network and minimum distance method respectively, and the maximum likelihood method showed the lowest, 0.561. Moreover, in the evaluation of accuracy in water body image classification by NIR+RG images, the magalanobis and minimum distance method showed high values of 0.869 and 0.830 respectively, and in the artificial neural network method, it was very low as 0.779. Especially, RGB band revealed errors to classify trees or grasslands of Songsan amusement park as water body, but NIR+RG presented noticeable improvement in this matter. Therefore, it was concluded that images with NIR+RG band, compared those with RGB band, are more effective for detection of water body when the mahalanobis and minimum distance method were applied.

• Publications of The Korean Astronomical Society
• /
• v.27 no.4
• /
• pp.145-146
• /
• 2012

We present the results from B-, R-, I-, J- and H-band observations of the NEP-Wide survey field. The NEP-Wide survey is an AKARI survey of the North Ecliptic Pole covering ~ 5 square degrees area. Our optical/NIR imaging supports the AKARI IR imaging data by providing a crucial coverage in the optical/NIR. The optical data were obtained in 2007 using the 1.5 m telescope and SNUCAM at Maidanak Observatory, Uzbekistan. The NIR data were obtained in 2008 with FLAMINGOS on the KPNO 2.1 m telescope. We used IRAF, SExtractor, SCAMP, and SWarp for reducing the raw data, I-band fringe pattern removal, astrometry, standard photometry calibration, and source detection. Our optical-NIR data reach the depths of B ~ 23.4, R ~ 23.1, I ~ 22.3, J ~ 21.05, and H ~ 20.64 AB mag at 5-sigma. Here, we present the astrometric accuracy, galaxy number counts, completeness, and reliability, as well as redshift tracks of some normal galaxies and quasars on the B - R vs. R - I color-color diagram. The photometric data are being used for identifying optical counterparts of the IR data provided by AKARI, studying their SEDs, and selecting interesting objects for spectroscopic follow-up studies.