• 한국지리정보학회지
• /
• 제14권3호
• /
• pp.126-135
• /
• 2011

산불 감시 시설의 탐지확률을 높이고, 감시 자원의 운영 효율성을 높이기 위해서는 어디를 감시해야 하는가에 대한 사전 분석이 요구된다. 본 연구에서는 산불 감시 우선지역을 기존 감시 시설의 가시권과 해당 지역의 산불발생 확률 분석 결과를 이용하여 선정하는 방안을 제시하였다. 즉 발생 확률이 높으면서, 가시성이 떨어지는 곳을 우선 감시 지역으로 정의하고, 퍼지함수를 이용한 변환과 가중치 부여에 의한 중첩분석을 통해 산불감시 우선지도를 생성하였다. 봉화지역을 대상으로 분석한 결과, 감시 우선 지역은 산지가 많은 북부 지역보다는 인구가 많은 중남부 지역에 많이 분포하였다. 개발된 산불감시 우선지역 분석 체계는 한정된 감시 자원의 적정 배치 위치를 선정하는데 기여할 수 있을 것으로 예상된다.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.159-168
• /
• 2019

Accurate forest fires detection algorithms remain a challenging issue, because, some of the objects have the same features with fire, which may result in high false alarms rate. This paper presents a new video-based, image processing forest fires detection method, which consists of four stages. First, a background-subtraction algorithm is applied to detect moving regions. Secondly, candidate fire regions are determined using CIE $L{\ast}a{\ast}b{\ast}$ color space. Thirdly, special wavelet analysis is used to differentiate between actual fire and fire-like objects, because candidate regions may contain moving fire-like objects. Finally, support vector machine is used to classify the region of interest to either real fire or non-fire. The final experimental results verify that the proposed method effectively identifies the forest fires.

• 한국항행학회논문지
• /
• 제27권5호
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.381-404
• /
• 2022

Forest fires inflict great losses of human lives and serious damages to ecological systems. Hence, numerous fire detection methods have been proposed, one of which is fire detection based on sensors. However, these methods reveal several limitations when applied in large spaces like forests such as high cost, high level of false alarm, limited battery capacity, and other problems. In this research, we propose a novel forest fire detection method based on image processing and correlation coefficient. Firstly, two fire detection conditions are applied in RGB color space to distinguish between fire pixels and the background. Secondly, the image is converted from RGB to YCbCr color space with two fire detection conditions being applied in this color space. Finally, the correlation coefficient is used to distinguish between fires and objects with fire-like colors. Our proposed algorithm is tested and evaluated on eleven fire and non-fire videos collected from the internet and achieves up to 95.87% and 97.89% of F-score and accuracy respectively in performance evaluation.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.574-577
• /
• 2006

In this paper, we developed a forest fire detection algorithm which uses a regression function between NDVI and land surface temperature. Previous detection algorithms use the land surface temperature as a main factor to discriminate fire pixels from non-fire pixels. These algorithms assume that the surface temperatures of non-fire pixels are intrinsically analogous and obey Gaussian normal distribution, regardless of land surface types and conditions. And the temperature thresholds for detecting fire pixels are derived from the statistical distribution of non-fire pixels’ temperature using heuristic methods. This assumption makes the temperature distribution of non-fire pixels very diverse and sometimes slightly overlapped with that of fire pixel. So, sometimes there occur omission errors in the cases of small fires. To ease such problem somewhat, we separated non-fire pixels into each land cover type by clustering algorithm and calculated the residuals between the temperature of a pixel under examination whether fire pixel or not and estimated temperature of the pixel using the linear regression between surface temperature and NDVI. As a result, this algorithm could modify the temperature threshold considering land types and conditions and showed improved detection accuracy.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.621-632
• /
• 2013

The most important things for a forest fire detection system are the exact extraction of the smoke from image and being able to clearly distinguish the smoke from those with similar qualities, such as clouds and fog. This research presents an intelligent forest fire detection algorithm via image processing by using the Gaussian Mixture model (GMM), which can be applied to detect smoke at the earliest time possible in a forest. GMMs are usually addressed by making the model adaptive so that its parameters can track changing illuminations and by making the model more complex so that it can represent multimodal backgrounds more accurately for smoke plume segmentation in the forest. Also, in this paper, we suggest a way to classify the smoke plumes via a feature extraction using HSL(Hue, Saturation and Lightness or Luminanace) color space analysis.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.927-935
• /
• 2021

This study conducted a study to improve the problems of the existing fire sensor system. In the case of the existing system, it took more than 3 minutes to detect a fire even at a short distance, making it difficult to extinguish the initial fire. In order to improve these problems, in this study, a fire detection system using an infrared thermal imaging camera was studied. The infrared image-based fire detection system is relatively wide and can detect fire over a long distance, so it has the advantage of being applicable to many fire detection systems. As a result of conducting a field test using the fire detection system, a fire that occurred about 2 km ahead was detected within about 10 seconds. Since the fire detection function of this system can detect within 10 seconds from a distance of about 2 km, it was applicable to forest fires that occur frequently in spring and autumn.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.157-160
• /
• 2008

This study analyzed on the area of Samcheok, Kangwondo about forest fire alarming area and enlargement of the area. Then, visible area by unattended watching camera and watchtower for forest fire which were run by Samcheok was cross-checked with geographic information system, and it could be whether effective on watching the area where the forest fire risk was high enough and also it could be expanded to larger forest fire. The result of study, the visible area by watching facilities only holds for 13.4% of the whole forest fire alarming area, but the forest fire can be observed even though it is occurred in small valley because of smoke and all the forest fire have been occurred in daytime. Therefore, it can be determined that watching area will be extended around 50.3% while the observation radii of watching facilities raise by 4km. However, Samcheok has much greater area of mountain area in compared to any other cities or counties, watching facilities should be installed and run additionally for extinguishing the forest fire from the beginning.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.690-695
• /
• 2002

In this forest fire experiment the ThermoViewer was set up on the platform built on a tree and observed the temperature change, before, during and after the fire. The fire experiment had been carried out not only the day of the forest fire experiment but also continued for four months after the forest fire had been gone. The results from the experiment showed that the temperature difference is significant in the afternoon; therefore, afternoon satellite passing is better and suitable time for active forest fires and burnt scars detection; moreover, after 83 days, the burnt and un-burnt vegetation become almost the same condition, fully regenerated and the temperature difference become nearly 0$^{\circ}$ Celsius, so there is not enough temperature different between burnt and un-burnt vegetation for current sensors to distinguish the difference anymore.

• 대한공간정보학회지
• /
• 제24권4호
• /
• pp.3-11
• /
• 2016

Sixty four percent of Korean territory consists of forest which is fragile for forest fire. However, it is difficult to detect the disaster-induced damages due to topographic complexity in mountainous areas and harsh weather conditions. For this reason, satellite imaging systems have been widely utilized to detect the damage caused by forest fire. In particular, ground vegetation condition can be estimated from multi-spectral satellite images and change detection technique has been used to detect forest fire damages. However, since Korea has clear four seasons, simple change detection technique has limitation. In this regard, this study applied the NDVI(normalized difference vegetation index) annual cycle modeling technique on time-series of Landsat images from 1991 to 2007 to analyze influence of forest fire of Yangyang-gun, Gangwon-do in 2005 on vegetation condition. The encouraging result was obtained when comparing the areas where forest fire occurs with non-damaged areas. The mean value of NDVI was decreased by 0.07 before and after the forest fire. On the other hand, annual variability of NDVI had been increasing and peak value of NDVI was stationary after the forest fire. It is interpreted that understory vegetation was seriously damaged from the forest fire occurred in 2005.