• Journal of the Korean Society for Nondestructive Testing
• /
• v.36 no.6
• /
• pp.451-459
• /
• 2016

Crack detection on panels during manufacturing process is an important step for ensuring the product quality. The accuracy and efficiency of traditional crack detection methods, which are performed by eye inspection, are dependent on human inspectors. Therefore, implementation of an on-line and precise crack detection is required during the panel pressing process. In this paper, a regular CCTV camera system is utilized to obtain images of panel products and an image process based crack detection technique is developed. This technique uses a comparison between the base image and a test image using an amplitude mapping of the local image. Experiments are performed in the laboratory and in the actual manufacturing lines to evaluate the performance of the developed technique. Experimental results indicate that the proposed technique could be used to effectively detect a crack on panels with high speed.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.543-552
• /
• 2008

ATIS(Advanced Traveler Information System) is the system to offer a real-time traffic information or traffic situation for the benefit of the client. One of traffic information collection methods for ATIS research is the method of image analysis. The method is divided into two : one is the method to set two loop detectors at the area and the other is the method detecting the vehicle through an image analysis. In this paper, we propose a real-time traffic information collection system to mix two methods. The system installs multiple virtual detection lines and traces the location of the vehicle. Use of multiple virtual detection lines supplements the defect of the method of loop detectors. And we drew a representative pixels in the detecting area and used it for image analysis. This is to solve the problem of time delay which increases as the image size increases. We gathered traffic images and experimented using the system and got 92.32% of detection accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.5
• /
• pp.57-65
• /
• 2010

In this paper, we propose a new real-time algorithm detecting the flame and smoke in digital CCTV images. Because the forest fire causes the enormous human life and damage of property, the early management according to the early sensing is very important. The proposed algorithm for monitoring forest fire is classified into the flame sensing and detection of smoke. The flame sensing algorithm detects a flame through the conditional test at YCbCr color model from the single frame. For the detection of smoke, firstly the background range is set by using differences between current picture and the average picture among the adjacent frames in the weighted value, and the pixels which get out of this range and have a gray-scale are detected in the smoke area. Because the proposed flame sensing algorithm is stronger than the existing algorithms in the change of the illuminance according to the quantity of sunshine, and the smoke detection algorithm senses the pixel of a gray-scale with the smoke considering the amount of change for unit time, the effective early forest fire detection is possible. The experimental results indicate that the proposed algorithm provides better performance than existing algorithms.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.2
• /
• pp.257-263
• /
• 2013

In case of image observation equipments, CCTV for short distance visual field is usually installed and operated mostly as the means of crime-prevention. However, the extensive demand for monitoring problems in case of the increase in intelligent crimes and disasters has led to the necessity of the development of long-distance observation equipments embedded with Night View functions. In case of the Night View equipments, the relevant market is set up to be focused mostly on Thermal Observation Device(hereinafter, TOD), but some shortcomings such as the limitation of image visibility and excessive maintenance cost, etc. have actually caused the necessity of new long distance Night View equipment. Moreover there might follow lots of difficulties in long-distance visualization in the event that irregular reflection is generated by minute particles in the atmosphere such as fog, smog, and dust, etc. These factors are motivate the work presented in this study. Our study is aimed at the realization of Pulsed Laser Illuminator and newly proposed Range-Gated image acquisition technology. And also the implementation of Tracker for continuous trace of the objects of interest from the obtained sequence images.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.32-40
• /
• 2021

Underground information is difficult to visually check, which can lead to a huge accident in the event of a safety accident. Recently, the Ministry of Land, Infrastructure and Transport intends to reduce safety accidents caused by the aging or damage of underground facilities through the Special Act on Underground Safety Management. GPR is increasingly being used as a technology to acquire information in underground spaces that are difficult to see with the naked eye. However, GPR's location information is corrected by checking images of CCTV and GPS information acquired during exploration. This method has an average error of about 2 meters. In this works, We used LiDAR to calibrate the GPR information and found that the error was reduced from at least 7cm to up to 40cm. If accurate GPR information collected in the future is analyzed quickly using AI, etc., it will be able to collect and utilize underground information faster than it is now to secure safety.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.691-700
• /
• 2021

The IP cameras have rapidly replaced the analog CCTVs as the cameras have the advantages of not only being able to remotely monitor, but also supplying power through the UTP cable, In this paper, we introduce the protocol architecture of the ONVIF standard which is widely applied to the IP camera and other Internet protocols to support it, and implement the ONVIF Device on a commercial board. Although these functions can be controlled by the Client (PC), several functions such as privacy masks, temperature display of the thermal camera, and ROI (Region of Interest) are implemented through a web viewer on the device. Through the experiment, the functions of ONVIF Profile S and web viewer are verified through SOAP messages exchanged between Device (IP camera) and Client program and streamed images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1762-1769
• /
• 2021

The final goal of this study is to develop a system that can analyze whether a wanted vehicle is a criminal vehicle from images collected from black boxes, smartphones, CCTVs, and so on. Data collection was collected using a self-developed black box. The used data in this study has used a total of 83,753 cases such as the eight vehicle types(truck, RV, passenger car, van, SUV, bus, sports car, electric vehicle) and 434 vehicle models. As a result of vehicle recognition using YOLO v5, mAP was found to be 80%. As a result of identifying the vehicle model with ReXNet using the self-developed black box, the accuracy was found to be 99%. The result was verified by surveying field police officers. These results suggest that improving the accuracy of data labeling helps to improve vehicle recognition performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.890-895
• /
• 2021

Recently, the "Act of Serious Disasters, etc" was enacted and institutional and social interest in safety accidents is increasing. In this paper, we analyze statistical data published by government agency on safety accidents that occur in manufacturing sites, and compare various object detection models based on deep learning to build a model to determine dangerous situations to reduce the occurrence of safety accidents. The data-set was directly constructed by collecting images from CCTVs at the manufacturing site, and the YOLO-v4, SSD, CenterNet models were used as training data and evaluation data for learning. As a result, the YOLO-v4 model obtained a value of 81% of mAP. It is meaningful to select a class in an industrial field and directly build a dataset to learn a model, and it is thought that it can be used as an initial research data for a system that determines a risk situation and infers it.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.303-303
• /
• 2023

실용적인 표면영상유속계를 만들기 위해서는 적절한 하드웨어와 소프트웨어로 시스템을 구성해야 한다. 이를 위해서 본 연구에서는 하드웨어로 CCTV를 선택하고, 초음파 수위계를 이용하여 수위를 지속적으로 읽어들이도록 구성하였다. 한편, 소프트웨어적으로는 11변수 투영법을 적용하여 변화하는 수위에 따라 정확한 측정점을 재구성하도록 하고, 아울러 각 측정점에서 주흐름방향으로 정확한 시공간영상을 작성하고, 이 시공간영상(spatio-temporal image)들을 분석하였다. 그결과, 5분 간격으로 촬영된 1분 길이의 영상을 지속적으로 촬영하고 분석하여 유량을 산정하는 표면영상유속계측 시스템을 구축하였다. 본고에서는 이러한 소프트웨어 개선방향중 하나인 주흐름방향의 시공간영상 작성법을 소개한다. 먼저, 11변수 투영법을 이용하여 하천의 표면영상에 대한 좌표변환계수를 산정하였다. 그리고 이 좌표변환계수를 이용하여, 하천의 수위변화에 따라 표면영상내의 측정점이 적절히 수정될 수 있도록 하였다. 그 다음 이 측정점에서 측정횡단면과 수직이 되는 방향을 선정하고, 이 방향이 영상내에서 하천 측정횡단면과 수직인 방향, 즉 주흐름방향이 되도록 하였다. 촬영된 1분간의 동영상의 각 측정점 위치에서 잘라낸 시공간체적(spatio-temporal image volume)에서 주흐름방향의 시공간영상을 잘라내고 이를 상호상관법이나 고속푸리에변환을 이용하여 분석하였다. 이 때 만들어진 시공간영상은 주흐름방향과 정확하게 일치하여, 기존의 표면영상유속계의 문제이던, 일부 측정점의 유속벡터가 주흐름방향과 일치하지 않던 문제를 해결할 수 있었다. 개발된 방법으로 표면영상유속계를 제작하여 인수천에 시험 설치하고 호우 사상에 대해 검토한 결과 정확하고 신속하며 연속적인 유량측정이 가능하였다.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.