• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.443-461
• /
• 2022

Target Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.451-456
• /
• 2004

Signature based intrusion detection system (IDS), having stored rules for detecting intrusions at the library, judges whether new inputs are intrusion or not by matching them with the new inputs. However their policy has two restrictions generally. First, when they couldn't make rules against new intrusions, false negative (FN) errors may are taken place. Second, when they made a lot of rules for maintaining diversification, the amount of resources grows larger proportional to their amount. In this paper, we propose the learning algorithm which can evolve the competent of anomaly detectors having the ability to detect anomalous attacks by genetic algorithm. The anomaly detectors are the population be composed of by following the negative selection procedure of the biological immune system. To show the effectiveness of proposed system, we apply the learning algorithm to the artificial network environment, which is a computer security system.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.4
• /
• pp.347-350
• /
• 2017

In this paper, we implemented a real-time 2.4 GHz direction finding system using a time-modulated array(TMA) and an Universal Software Radio Peripheral(USRP). Our system consists of two commercial monopole antennas, self-designed switch board, and an USRP, and it is controlled using LabVIEW program in real-time. From measured results, it is verified that our system can exactly detect the incident angle within 4 degree in the range of 30 degree. Our direction finding system has advantages of a simple hardware architecture than conventional one with multiple receivers, and a simple algorithm only by using a main lobe and a first side-lobe of switching frequency.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.21-29
• /
• 2015

This paper proposes a shot change detection algorithm by using frame segmentation and the object changes among moving blocks. In order to detect the rapid moving changes of objects between two consecutive frames, the moving blocks on the diagonal are defined, and their histograms are calculated. When a block of the current frame is compared to the moving blocks of the next frame, the block histograms are used and the threshold of a shot change detection is automatically adjusted by Otsu's threshold method. The proposed algorithm was tested for the various types of color or gray videos such as films, dramas, animations, and video tapes in National Archives of Korea. The experimental results showed that the proposed algorithm could enhance the detection rate when compared to the studied methods that use brightness, histogram, or segmentation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.75-81
• /
• 2004

Signature based intrusion detection system (IDS), having stored rules for detecting intrusions at the library, judges whether new inputs are intrusion or not by matching them with the new inputs. However their policy has two restrictions generally. First, when they couldn`t make rules against new intrusions, false negative (FN) errors may are taken place. Second, when they made a lot of rules for maintaining diversification, the amount of resources grows larger proportional to their amount. In this paper, we propose the learning algorithm which can evolve the competent of anomaly detectors having the ability to detect anomalous attacks by genetic algorithm. The anomaly detectors are the population be composed of by following the negative selection procedure of the biological immune system. To show the effectiveness of proposed system, we apply the learning algorithm to the artificial network environment, which is a computer security system.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.665-674
• /
• 2003

In this paper, we propose an approach to correlate alerts using a clustering analysis of data mining techniques in order to support intrusion detection system. Intrusion detection techniques are still far from perfect. Current intrusion detection systems cannot fully detect novel attacks. However, intrucsion detection techniques are still far from perfect. Current intrusion detection systems cannot fully detect novel attacks or variations of known attacks without generating a large amount of false alerts. In addition, all the current intrusion detection systems focus on low-level attacks or anomalies. Consequently, the intrusion detection systems to underatand the intrusion behind the alerts and take appropriate actions. The clustering analysis groups data objects into clusters such that objects belonging to the same cluster are similar, while those belonging to different ones are dissimilar. As using clustering technique, we can analyze alert data efficiently and extract high-level knowledgy about attacks. Namely, it is possible to classify new type of alert as well as existed. And it helps to understand logical steps and strategies behind series of attacks using sequences of clusters, and can potentially be applied to predict attacks in progress.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.15-17
• /
• 2021

This paper proposes a drone flight trajectory method for accurate air pollutant emission designation detection. In areas with many factories, such as industrial complexes, there are workplaces that illegally emit air pollutants in a situation where monitoring is neglected. In the past, studies have been actively conducted to measure air pollutants in these areas using drones. The measurement method using a drone uses a method of detecting pollution by stopping around the chimney of a factory, but it has a problem in that the detection of air pollutants is inaccurate depending on environmental factors such as air pressure and wind. Therefore, this paper proposes a drone flight trajectory method for accurate air pollutant emission designation detection. This paper devises a screw orbit flight method in which a drone flies upward while rotating the chimney, and the total area of the chimney is detected and measured considering environmental factors. In the experiment, our proposal shows a higher performance than the existing method.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1763-1770
• /
• 2023

The availability of high-resolution satellite image time series data has led to an increase in change detection research. Various methods are being studied, such as satellite image pixel and object-level change detection algorithms, as well as algorithms that apply deep learning technology. In this paper, we propose a QGIS plugin-based system to enhance the utilization of these useful results and present an actual implementation case. The proposed system is a system for intensive change detection and monitoring of areas of interest, and we propose a convenient system expansion method for algorithms to be developed in the future. Furthermore, it is expected to contribute to the construction of satellite image utilization systems by presenting the basic structure of commercialization of change detection research.

• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.33-39
• /
• 2014

Chemical accidents are the cause of the accident site during the initial responders to quickly and easily see materials and concentration method for the U.S. Environmental Protection Agency(EPA) is widely used in the initial response team direct reading detection equipment used. Ministry of the tubular gas detection equipment to detect direct reading detection equipment used in the event of an accident scene, and shell-and-tube gas detector for rapid detection and identification and precise analysis of causative pollutants before about strategically can identify the quantitative and qualitative useful equipment. However, those who initially respond to the scene of a direct reading detection equipment and a simple lack of understanding of how to use the numbers only because of the way you want to check the accuracy of detection results have been raising questions about the increase. The scene of the accident in order to obtain an accurate detection results used in this paper, the Ministry of Environment of gas detectors detect tubular Kitagawa and Draeger detector tube to check the reactivity of the material on-site detection of early response of those who were to raise the accuracy of the results.