• Journal of Ship and Ocean Technology
• /
• v.11 no.1
• /
• pp.36-46
• /
• 2007

The maintenance of a ship is essential for safe navigation and hence regular surveys are prescribed according to the rule of classification societies. A hull inspection is generally performed by professional divers, but it takes a long time and the efficiency is low in terms of time and cost. In this research, a ROV(Remotely Operated Vehicle) named as SNU-ROV(Seoul National University-ROV) is developed to replace the conventional inspection method. In this system, the ROV is intended to be used for inspecting ship and harbor because harbor inspection is merging as a safety measure against any possible terror actions. In order to increase the efficiency of inspection, the ROV must be able to measure the exact position of damages. SNU-ROV has a positioning system based on LBL(Long Base Line). In shallow water such as harbor, however, LBL has bad DOP(Dilution of Precision) in the depth direction due to the limited depth. Thus LBL only can not locate the exact depth position. To solve the DOP problem, a pressure sensor is introduced to LBL and a complementary filter is attached by using indirect feedback Kalman filter. Thus developed positioning system is verified by simulation and experiment in towing tank.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.39-57
• /
• 2018

The purpose of this study was to construct an artificial intelligence model that learns and estimates the relationship between vehicle queue length and link travel time in urban areas. The vehicle queue length estimation model is modeled by three models. First of all, classify whether vehicle queue is a link overflow and estimate the vehicle queue length in the link overflow and non-overflow situations. Deep learning model is implemented as Tensorflow. All models are based DNN structure, and network structure which shows minimum error after learning and testing is selected by diversifying hidden layer and node number. The accuracy of the vehicle queue link overflow classification model was 98%, and the error of the vehicle queue estimation model in case of non-overflow and overflow situation was less than 15% and less than 5%, respectively. The average error per link was about 12%. Compared with the detecting data-based method, the error was reduced by about 39%.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.88-95
• /
• 2017

As the safety fields are expanding to a variety of industrial fields, safety technology has been developed by convergence between industrial safety fields such as mechanics, ergonomics, electronics, chemistry, construction, and information science. As the technology convergence is facilitating recently advanced safety technology, it is important to explore the trends of safety technology for understanding which industrial technologies have been integrated thus far. For studying the trends of technology, the patent is considered one of the useful sources that has provided the ample information of new technology. The patent has been also used to identify the patterns of technology convergence through various quantitative methods. In this respect, this study aims to identify the convergence patterns and fields of safety technology using association rule mining(ARM)-based patent co-classification(co-class) analysis. The patent co-class data is especially useful for constructing convergence network between technological fields. Through linkages between technological fields, the core and hub classes of convergence network are explored to provide insight into the fields of safety technology. As the representative method for analyzing patent co-class network, the ARM is used to find the likelihood of co-occurrence of patent classes and the ARM network is presented to visualize the convergence network of safety technology. As a result, we find three major convergence fields of safety technology: working safety, medical safety, and vehicle safety.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.2
• /
• pp.165-173
• /
• 2011

The acoustic emission(AE) technique is a well established method to carry out structural health monitoring(SHM) of large structures. However, the real-time monitoring of the crack growth in the roller coaster support structures is not easy since the vehicle operation produces very large noise as well as crack growth. In this investigation, we present the waveform parameter filtering method to classify acoustic sources in real-time. This method filtrates only the AE hits by the target acoustic source as passing hits in a specific parameter band. According to various acoustic sources, the waveform parameters were measured and analyzed to verify the present filtering method. Also, the AE system employing the waveform parameter filter was manufactured and applied to the roller coaster support structure in an actual amusement park.

• Korean Journal of Remote Sensing
• /
• v.32 no.2
• /
• pp.87-96
• /
• 2016

Red tide, causes aquaculture industry the damages in Korea every summer, was usually detected by using satellite, aquaculture information was difficult to detect by using satellite. Therefore, we suggests the method for detecting the red tide using the coastal observation and the product from the unmanned aerial Vehicle. As a result, we obtained the high resolution unmanned aerial Vehicle images, detected the red tide by using the unsupervised classification from the true color images and the simple algorithm from the RGB color images. Compared the previous color images, unmanned aerial Vehicle images were clearly classified the ocean color, we were able to identify the red tide distribution in sea surface. These methods were determined to accurately monitor the red tide distribution on the aquaculture fields in the coastal waters where is established the aquaculture.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.97-113
• /
• 2023

Swift and appropriate responses in emergency situations like objects falling on the road can bring convenience to road users and effectively reduces secondary traffic accidents. In Korea, current intelligent transportation system (ITS)-based detection systems for emergency road situations mainly rely on loop detectors and CCTV cameras, which only capture road data within detection range of the equipment. Therefore, a new detection method is needed to identify emergency situations in spatially shaded areas that existing ITS detection systems cannot reach. In this study, we propose a ResNet-based algorithm that detects and classifies emergency situations from vehicle camera footage. We collected front-view driving videos recorded on Korean highways, labeling each video by defining the type of emergency, and training the proposed algorithm with the data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.3
• /
• pp.41-46
• /
• 2011

The tire damage classification method is researched by periodicity detection of ultrasonic envelope signals to occur at the driving vehicle tire. Because periodic signals is generated by rotations of the damaged tire, it should convert to pulse for using the density function. After time intervals of pulses are represented by the density function, the dominant periodicity is detected. The threshold to make a pulse is calculated by moving average of envelope signals. The result of time density function in case of one damage material, the first peak's time is equals to tire's rotation period, 162ms and 102ms, about the speed of 50km/h and 80km/h. In case of more than one damage material, the sum of each peak's time is equals to tire's rotation period about the speed.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.88-88
• /
• 2022

Detection of stress responses in crops is important to diagnose crop growth and evaluate yield. Also, the multi-spectral sensor is effectively known to evaluate stress caused by nutrient and moisture in crops or biological agents such as weeds or diseases. Therefore, in this experiment, multispectral images were taken by an unmanned aerial vehicle(UAV) under field condition. The experiment was conducted in the long-term fertilizer field in the National Institute of Crop Science, and experiment area was divided into different status of NPK(Control, N-deficiency, P-deficiency, K-deficiency, Non-fertilizer). Total 11 vegetation indices were created with RGB and NIR reflectance values using python. Variations in nutrient content in plants affect the amount of light reflected or absorbed for each wavelength band. Therefore, the objective of this experiment was to evaluate vegetation indices derived from multispectral reflectance data as input into machine learning algorithm for the classification of nutritional deficiency in rice. RandomForest model was used as a representative ensemble model, and parameters were adjusted through hyperparameter tuning such as RandomSearchCV. As a result, training accuracy was 0.95 and test accuracy was 0.80, and IPCA, NDRE, and EVI were included in the top three indices for feature importance. Also, precision, recall, and f1-score, which are indicators for evaluating the performance of the classification model, showed a distribution of 0.7-0.9 for each class.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.680-682
• /
• 1999

In this paper, we propose an traffic data acquisition method and automatic vehicle classification system using laser. We use a invisible laser to minimize measuring error caused by environmental variation. also we use radio frequency data communication and PCMCIA for operating convenience.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.267-276
• /
• 2016

Human detection technologies are widely used in smart homes and autonomous vehicles. However, in order to detect human, autonomous vehicle researchers have used a high-resolution LIDAR and smart home researchers have applied a camera with a narrow detection range. In this paper, we propose a novel method using a low-cost and low-resolution LIDAR that can detect human fast and precisely without complex learning algorithm and additional devices. In other words, human can be distinguished from objects by using a new human characteristics function which is empirically extracted from the characteristics of a human. In addition, we verified the effectiveness of the proposed algorithm through a number of experiments.