• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.143-146
• /
• 2007

객체의 특징점을 추출할 때, 일반적으로 모델 기반 접근을 사용한다. 본 논문에서는 이러한 모델 기반 특징점 추출 알고리즘으로 PCA를 근간으로 하는 Active Appearance Model을 이용하는데, 기존의 AAM 알고리즘은 모든 특징점을 하나의 군집으로 기준하여 PCA를 수행하지만 본 논문에서는 이것을 각 주요 부위별 학습 모델로 분리하여 수행한다. 그리고 이러한 모델에서 특징점을 찾을 때, 발산하는 문제에 빠지지 않기 위한 방법을 제시한다. 제시한 방법의 모델을 이용하여 실험 할 경우의 결과와 이를 통한 개별 모델의 특성에 대하여 파악한 결과를 제시한다.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.410-414
• /
• 2004

The MODIS Land Rapid Response System (RRS) has been developed to provide rapid access to MODIS data globally, with initial emphasis on 250 m color composite imagery and active fire data. Fire detection is based on a contextual algorithm that exploits the strong emission of mid-infrared radiation from fires. This algorithm examines each pixel of the MODIS swath, and ultimately assigns to each one of the following classes: missing data, cloud, water, non-fire, fire, or unknown. In this paper, we introduce the MODIS Rapid Response System established at the Korea Aerospace Research Institute (KARI) and present some application results for Korea using the direct broadcast data acquired at KARI ground station.

• ETRI Journal
• /
• v.34 no.5
• /
• pp.791-794
• /
• 2012

We propose an efficient framework to realistically render 3D faces with a reduced set of points. First, a robust active appearance model is presented to detect facial features in the projected faces under different illumination conditions. Then, an adaptive simplification of 3D faces is proposed to reduce the number of points, yet preserve the detected facial features. Finally, the point model is rendered directly, without such additional processing as parameterization of skin texture. This fully automatic framework is very effective in rendering massive facial data on mobile devices.

• Proceedings of the KIPE Conference
• /
• 2002.07a
• /
• pp.555-558
• /
• 2002

The general ways of the anti-islanding can be classified into the active method and passive method. The passive method which use only the voltage information when power failure occurs has much possibility of the wrong detection. And the active method detects the change of the voltage frequency as instantaneously changing the frequency of the inverter output current. Therefore, in this paper, the method to inject arbitrary order harmonics into controlled current is proposed. In this method islanding can be detected by measuring the amount of load voltage of injected harmonics order. And as a current control method predictive control method is used, which make actual current accurately to track reference current by Instantaneously computing converter output voltage and has fast response in transient state. This parer proposed method was verified by simulation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.271-276
• /
• 2008

The intrusion detection system is one of the active fields of research in wireless networks. Intrusion detection in wireless mobile Ad hoc network is challenging because the network topologies is dynamic, lack centralization and are vulnerable to attacks. This paper is about the effective enhancement of the IDS technique that is being implemented in the mobile ad hoc network and deals with security and vulnerabilities issues which results in the better performance and detection of the intrusion.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.22 no.4
• /
• pp.98-103
• /
• 1986

The passive acoustic system only has generally used in fish detection. But the passive acoustic system has not been tried in fishing since Freytag has proposed a possibilities of the passive detection of fishes in 1963. This paper describes the .feasible aspects of fish detection by listening of the sound they make. The passive acoustic system accompanied the active acoustic system may expand the range of detection and compensate for lack of capabilities each other, but there are some difficulties in noise rejection because the fre9uency range of ship noises covers the whole range vf biological sounds. The attempt to collect useful informations from underwater would be greatly contributed in fisheries.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.235-238
• /
• 2019

In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

• Structural Monitoring and Maintenance
• /
• v.4 no.4
• /
• pp.381-396
• /
• 2017

Structural health monitoring (SHM) is a necessity for reliable and efficient functioning of engineering systems. Damage detection (DD) is a crucial component of any SHM system. Lamb waves are a popular means to DD owing to their sensitivity to small damages over a substantial length. This typically involves an active sensing paradigm in a pitch-catch setting, that involves two piezo-sensors, a transmitter and a receiver. In this paper, we propose a data-intensive DD approach for beam structures using high frequency signals acquired from beams in a pitch-catch setting. The key idea is to develop a statistical learning-based approach, that harnesses the inherent sparsity in the problem. The proposed approach performs damage detection, localization in beams. In addition, quantification is possible too with prior calibration. We demonstrate numerically that the proposed approach achieves 100% accuracy in detection and localization even with a signal to noise ratio of 25 dB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5592-5609
• /
• 2017

JPEG steganography detection is an active research topic in the field of information hiding due to the wide use of JPEG image in social network, image-sharing websites, and Internet communication, etc. In this paper, a new steganalysis method for content-adaptive JPEG steganography is proposed by integrating the evolutionary feature selection and classifier ensemble selection. First, the whole framework of the proposed steganalysis method is presented and then the characteristic of the proposed method is analyzed. Second, the feature selection method based on genetic algorithm is given and the implement process is described in detail. Third, the method of classifier ensemble selection is proposed based on Pareto evolutionary optimization. The experimental results indicate the proposed steganalysis method can achieve a competitive detection performance by compared with the state-of-the-art steganalysis methods when used for the detection of the latest content-adaptive JPEG steganography algorithms.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.