• Journal of Navigation and Port Research
• /
• v.32 no.2
• /
• pp.127-132
• /
• 2008

The safety degree of navigation for collision avoidance is closely related with the combination between mariner's behavior and navigational environment. The condition of navigational environment is mainly decided by navigable waters, ship traffic, rule of road, sea state, weather and so on. Especially, the condition of navigable waters and ship traffic in navigational environment are ones of the important factors to attain safe navigation when mariners are underway and crossing, head on or overtaking situation. Thus this paper is to analyze the characteristics of mariner's behavior for collision avoidance caused by ship traffic and navigable waters by analyzing the contents of questionnaire and the results of international collaborative research. As a result, it can be concluded that the density of ship traffic and the area of navigable waters affect mariner's ship handling for collision avoidance.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1029-1035
• /
• 2019

In recent years, artificial intelligence (AI) services have become one of the most essential parts to extend human capabilities in various fields such as face recognition for security, weather prediction, and so on. Various learning algorithms for existing AI services are utilized, such as classification, regression, and deep learning, to increase accuracy and efficiency for humans. Nonetheless, these services face many challenges such as fake news spread on social media, stock selection, and volatility delay in stock prediction systems and inaccurate movie-based recommendation systems. In this paper, various algorithms are presented to mitigate these issues in different systems and services. Convolutional neural network algorithms are used for detecting fake news in Korean language with a Word-Embedded model. It is based on k-clique and data mining and increased accuracy in personalized recommendation-based services stock selection and volatility delay in stock prediction. Other algorithms like multi-level fusion processing address problems of lack of real-time database.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.271-280
• /
• 2023

FMCW (Frequency Modulated Continuous Wave) radar system is widely used in autonomous driving and navigation applications due to its high detection capabilities independent of weather conditions and environments. However, radar signals can be easily contaminated by various noises such as speckle noise, receiver saturation, and multipath reflection, which can worsen sensing performance. To handle this problem, we propose a learning-free noise removal technique for radar to enhance detection performance. The proposed method leverages adaptive thresholding to remove speckle noise and receiver saturation, and wavelet transform to detect multipath reflection. After noise removal, the radar image is reconstructed with the geometric structure of the surrounding environments. We verify that our method effectively eliminated noise and can be applied to autonomous driving by improving the accuracy of odometry and place recognition.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.283-298
• /
• 2022

As Synthetic Aperture Radar (SAR) image can be acquired regardless of the weather and day or night, it is highly recommended to be used for Automatic Target Recognition (ATR) in the fields of surveillance, reconnaissance, and national security. However, there are some limitations in terms of cost and operation to build various and vast amounts of target images for the SAR-ATR system. Recently, interest in the development of an ATR system based on simulated SAR images using a target model is increasing. Attributed Scattering Center (ASC) matching and template matching mainly used in SAR-ATR are applied to target classification. The method based on ASC matching was developed by World View Vector (WVV) feature reconstruction and Weighted Bipartite Graph Matching (WBGM). The template matching was carried out by calculating the correlation coefficient between two simulated images reconstructed with adjacent points to each other. For the performance analysis of the two proposed methods, the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset was used, which has been recently published by the U.S. Defense Advanced Research Projects Agency (DARPA). We conducted experiments under standard operating conditions, partial target occlusion, and random occlusion. The performance of the ASC matching is generally superior to that of the template matching. Under the standard operating condition, the average recognition rate of the ASC matching is 85.1%, and the rate of the template matching is 74.4%. Also, the ASC matching has less performance variation across 10 targets. The ASC matching performed about 10% higher than the template matching according to the amount of target partial occlusion, and even with 60% random occlusion, the recognition rate was 73.4%.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.1
• /
• pp.97-107
• /
• 2024

Despite the rapid advancement in image recognition technology, achieving perfect digitization of tabular documents and handwritten documents still challenges. The purpose of this study is to improve the accuracy of digitizing the logbook by correcting errors by utilizing associated rules considered during logbook entries. Through this, it is expected to enhance the accuracy and reliability of data extracted from logbook through OCR programs. This model is to improve the accuracy of digitizing the logbook of the training ship "Saenuri" at the Mokpo Maritime University by correcting errors identified after Optical Character Recognition (OCR) program recognition. The model identified and corrected errors by utilizing associated rules considered during logbook entries. To evaluate the effect of model, the data before and after correction were divided by features, and comparisons were made between the same sailing number and the same feature. Using this model, approximately 10.6% of errors out of the total estimated error rate of about 11.8% were identified, and 56 out of 123 errors were corrected. A limitation of this study is that it only focuses on information from Dist.Run to Stand Course sections of the logbook, which contain navigational information. Future research will aim to correct more information from the logbook, including weather information, to overcome this limitation.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.201-212
• /
• 2011

In this paper, we suggest a system of detecting a vehicle with lane violation, which can detect the vehicle with lane violation, by using the feature point tracking. The whole algorism in the suggested system of detecting a vehicle with lane violation is composed of three stages such as feature extraction, register and tracking in feature for the tracking-targeted vehicle, and detecting a vehicle with lane violation. The feature is extracted from the morphological gradient image, which results in constructing robust detection system against shadows, weather conditions, head lights and illumination conditions without distinction day and night. The system shows excellent performance for the data captured at day time, night time, and rainy night time as much as 99.49% for positive recognition ratio and 0.51% for error ratio. Also the system is so fast as much as 91.34 frames per second in average that it may be possible for real-time processing.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.4
• /
• pp.677-686
• /
• 2023

In this paper, we study the design and implementation of a smart home outing care system that recognizes the user's purpose of going out and delivers useful information that can help when going out. RSS service data of the Korea Meteorological Administration can be transmitted in real time using ESP8266, and a system that can provide weather information to users after analyzing the data using Arduino MEGA is implemented. Using App Inventor, you can pack the necessary items without forgetting, and you can change the settings according to the desired weather and purpose. The position of the microphone was placed outside to increase awareness by 12%, and the sensitivity of the pressure sensor was set to a maximum of 210 kΩ. If there is an obstacle between the doors, the doors open automatically. An ultrasonic sensor was placed on the ceiling of the drawer to recognize an object within the range of 0.5cm to 10cm to check the existence of an object, and a camera was installed to research a security reinforcement system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.545-550
• /
• 2013

In pattern recognition field, data classification is an essential process for extracting meaningful information from data. Adaptive boosting algorithm, known as AdaBoost algorithm, is a kind of improved boosting algorithm for applying to real data analysis. It consists of weak classifiers, such as random guessing or random forest, which performance is slightly more than 50% and weights for combining the classifiers. And a strong classifier is created with the weak classifiers and the weights. In this paper, a research is performed using AdaBoost algorithm for detecting chaff echo which has similar characteristics to precipitation echo and interrupts weather forecasting. The entire process for implementing chaff echo classifier starts spatial and temporal clustering based on similarity with weather radar data. With them, learning data set is prepared that separated chaff echo and non-chaff echo, and the AdaBoost classifier is generated as a result. For verifying the classifier, actual chaff echo appearance case is applied, and it is confirmed that the classifier can distinguish chaff echo efficiently.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.6
• /
• pp.63-70
• /
• 2011

A bicycle is different from vehicles in the structure that a rider is fully exposed to the surrounding environment. Therefore, it needs to make use of prior information about local weather, air quality, trail road condition. Moreover, since it depends on human power for moving, it should acquire route property such as hill slope, winding, and road surface to improve its efficiency in everyday use. Recent mobile applications which are to be used during bicycle riding let us aware of the necessity of development of intelligent bicycles. This study aims to develop a riding state (up-hill, down-hill, accelerating, braking) recognition algorithm using a low-power wrist watch type embedded system which has 3-axis accelerometer and wireless communication capability. The developed algorithm was applied to 19 experimental riding data and showed more than 95% of correct recognition over 83.3% of the total dataset. The altitude and temperature sensor also in the embedded system mounted on the bicycle is being used to improve the accuracy of the algorithm. The developed riding state recognition algorithm is expected to be a platform technology for intelligent bicycle interface system.