• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.6_2
• /
• pp.1025-1032
• /
• 2020

In this paper, we propose a method to classify road weather conditions into rain, fog, and sun using a SVM (Support Vector Machine) classifier after extracting weather features from images acquired in real time using an optical sensor installed on a roadside post. A multi-dimensional weather feature vector consisting of factors such as image sharpeness, image entropy, Michelson contrast, MSCN (Mean Subtraction and Contrast Normalization), dark channel prior, image colorfulness, and local binary pattern as global features of weather-related images was extracted from road images, and then a road weather classifier was created by performing machine learning on 700 sun images, 2,000 rain images, and 1,000 fog images. Finally, the classification performance was tested for 140 sun images, 510 rain images, and 240 fog images. Overall classification performance is assessed to be applicable in real road services and can be enhanced further with optimization along with year-round data collection and training.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• 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.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.4 no.4 s.15
• /
• pp.35-42
• /
• 2004

Accurate classification of water area is a preliminary step to analyze the flooded area and damages caused by flood. This is essential process for monitoring the region where annually repeating flood is a problem. The accurate estimation of flooded area can ultimately be utilized as a primary source of information for the policy decision. In this paper, flooded areas was classified using 1:25,000 land use map and a RADARSAT image of Ok-Chun and Bo-Eun located in Chung-Book province taken in 12th of August, 1998. Then we analyzed the flood area based on GIS. A RADARSAT image was used to classify the flooded areas with slope theme generated from digital elevation model. In processing on a RADARSAT image, the geometric correction was performed by a backwardgeocoding method based on ephemeris data and one control point for near real time flood area analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1503-1508
• /
• 2009

This study applied image processing techniques, constructed to real-time, to thermal infrared camera image. Thermal infrared image data was utilized for hot mapping, cool mapping, and rainbow mapping according to changing temperature. It was histogram image processing techniques so that detected shade contrast function of the thermal infrared image, and the thermal infrared image's edge was extracted to classification of object. Moreover, extraction of temperature from image was measured by using the image information program.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.1-9
• /
• 2021

This research examines deep learning based image recognition models for beef sirloin classification. The sirloin of beef can be classified as the upper sirloin, the lower sirloin, and the ribeye, whereas during the distribution process they are often simply unified into the sirloin region. In this work, for detailed classification of beef sirloin regions we develop a model that can learn image information in a reasonable computation time using the MobileNet algorithm. In addition, to increase the accuracy of the model we introduce data augmentation methods as well, which amplifies the image data collected during the distribution process. This data augmentation enables to consider a larger size of training data set by which the accuracy of the model can be significantly improved. The data generated during the data proliferation process was tested using the MobileNet algorithm, where the test data set was obtained from the distribution processes in the real-world practice. Through the computational experiences we confirm that the accuracy of the suggested model is up to 83%. We expect that the classification model of this study can contribute to providing a more accurate and detailed information exchange between suppliers and consumers during the distribution process of beef sirloin.

• Journal of the Semiconductor & Display Technology
• /
• v.8 no.3
• /
• pp.39-44
• /
• 2009

Local Binary Pattern (LBP) is becoming a popular tool for various machine vision applications such as face recognition, classification and background subtraction. In this paper, we propose a new extension of LBP, called the Diagonal LBP (DLBP), to handle the image-based gender classification problem arise in interactive display systems. Instead of comparing neighbor pixels with the center pixel, DLBP generates codes by comparing a neighbor pixel with the diagonal pixel (the neighbor pixel in the opposite side). It can reduce by half the code length of LBP and consequently, can improve the computation complexity. The Support Vector Machine is utilized as the gender classifier, and the texture profile based on DLBP is adopted as the feature vector. Experimental results revealed that our approach based on the diagonal LPB is very efficient and can be utilized in various real-time pattern classification applications.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1415-1422
• /
• 2019

Background subtraction is the major task of computer vision and image processing to detect changes in video. The best performing background subtraction is computationally expensive that cannot be used in real time in a typical computing environment. The proposed algorithm improves the background subtraction algorithm of the widely used MOG with the image resizing algorithm. The proposed image resizing algorithm is designed to drastically reduce the amount of computation and to utilize local information, which is robust against noise such as camera movement. Experimental results of the proposed algorithm have a classification capability that is close to the state of the art background subtraction method and the processing speed is more than 10 times faster.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.107-112
• /
• 2022

In an embedded system such as a drone, it is difficult to store, transfer and analyze the entire hyper-spectral image to a server in real time because it takes a lot of power and time. Therefore, the hyper-spectral image data is transmitted to the server through dimension reduction or compression pre-processing. Feature selection method are used to send only the bands for analysis purpose, and these algorithms usually take a lot of processing time depending on the size of the image, even though the efficiency is high. In this paper, by improving the temporal disadvantage of the band selection algorithm, the time taken 24 hours was reduced to around 60-180 seconds based on the 40000*682 image resolution of 8GB data, and the use of 7.6GB RAM was significantly reduced to 2.3GB using 45 out of 150 bands. However, in terms of pixel classification performance, more than 98% of analysis results were derived similarly to the previous one.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.319-326
• /
• 2002

In this paper, we have designed and implemented cluttering classification systems- unsupervised classifiers-for the processing of satellite remote sensing images. Implemented systems adopt various design patterns which include a factory pattern and a strategy pattern to support various satellite images'formats and to design compatible systems. The clustering systems consist of sequential clustering, K-Means clustering, ISODATA clustering and Fuzzy C-Means clustering classifiers. The systems are tested by using a Landsat TM satellite image for the classification input. As results, these clustering systems are well designed to extract sample data for the classification of satellite images of which there is no previous knowledge. The systems can be provided with real-time base clustering tools, compatibilities and components' reusabilities as well.