• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.257-260
• /
• 2011

본 논문에서는 비디오 데이터로부터 물체의 초기 움직임 영역을 자동으로 검출하는 방법을 소개한다. 제안하는 시스템은 먼저 입력 영상을 받아들인 후 인접된 영상으로부터 일정 크기의 정방향의 블록 단위로 움직임을 나타내는 모션 벡터를 추출한다. 그리고 추출된 모션벡터를 아웃라이어를 제거하는 강건 예측 알고리즘에 적용하여 배경에 해당하는 모션벡터와 잡음 및 움직이는 물체에 해당하는 모션벡터를 구분한다. 그런 다음, 군집화 알고리즘을 적용하여 이동하는 물체를 나타내는 모션벡터를 군집화하고, 군집화된 모션벡터에 해당하는 영역의 크기가 일정 수치 값 이상일 때 움직이는 물체가 감지되었다고 판단한다. 본 논문의 실험에서는 제안된 물체의 움직임 감지 방법이 기존의 방법에 비해 성능이 보다 우수함을 보인다.

• Proceedings of the KAIS Fall Conference
• /
• 2004.11a
• /
• pp.234-239
• /
• 2004

This paper describes preliminary results we have obtained in developing a computer vision system based on active IR illumination for real time gaze tracking for interactive graphic display. Unlike most of the existing gaze tracking techniques, which often require assuming a static head to work well and require a cumbersome calibration process fur each person, our gaze tracker can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using the Generalized Regression Neural Networks (GRNN). With GRNN, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. The effectiveness of our gaze tracker is demonstrated by preliminary experiments that involve gaze-contingent interactive graphic display.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.3101-3104
• /
• 1999

It is important to detect objects movement for obstacle recognition and path searching of autonomous robots and vehicles with vision sensor. This paper shows the method to draw out objects and to trace the trajectory of the moving object using a CCD camera and it describes the method to recognize the shape of objects.

• Journal of Sensor Science and Technology
• /
• v.25 no.1
• /
• pp.71-78
• /
• 2016

PPG signal measured by pulse oximeter can measure pulse and the oxygen saturation of arterial blood. But the PPG signal is distorted by finger movement or other movement in the body. To detect pulse from the PPG signal with motion artifact, we use band pass filter(BPF), Independent component analysis(ICA) and nonlinear autocorrelation(NAC). BPF is used to remove DC component and high frequency noise in the PPG signal with motion artifacts. ICA is used to separate pulse signal and motion artifact. However, pulse signal separated by ICA have no choice but to accompany signal distortion because pulse signal and motion artifact are not completely independent. So, we use nonlinear autocorrelation to emphasize the pure pulse signal from the distorted signal.

• Communications for Statistical Applications and Methods
• /
• v.22 no.5
• /
• pp.475-485
• /
• 2015

Similar to regression, many measures to detect influential data points in discriminant analysis have been developed. Many follow similar principles as the diagnostic measures used in linear regression in the context of discriminant analysis. Here we focus on the impact on the predicted classification posterior probability when a data point is omitted. The new method is intuitive and easily interpretable compared to existing methods. We also propose a graphical display to show the individual movement of the posterior probability of other data points when a specific data point is omitted. This enables the summaries to capture the overall pattern of the change.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1649-1656
• /
• 2016

Performance of the existing sensor-based fire detection system is limited according to factors in the environment surrounding the sensor. A number of image-based fire detection systems were introduced in order to solve these problem. But such a system can generate a false alarm for objects similar in appearance to fire due to algorithm that directly defines the characteristics of a flame. Also fir detection systems using movement between video flames cannot operate correctly as intended in an environment in which the network is unstable. In this paper, we propose an image-based fire detection method using CNN (Convolutional Neural Network). In this method, firstly we extract fire candidate region using color information from video frame input and then detect fire using trained CNN. Also, we show that the performance is significantly improved compared to the detection rate and missing rate found in previous studies.

• Convergence Security Journal
• /
• v.20 no.3
• /
• pp.53-60
• /
• 2020

At the present stage of the fourth industrial revolution, machine learning and artificial intelligence technologies are rapidly developing, and there is a movement to apply machine learning technology in the security field. Malicious code, including new and transformed, generates an average of 390,000 a day worldwide. Statistics show that security companies ignore or miss 31 percent of alarms. As many malicious codes are generated, it is becoming difficult for humans to detect all malicious codes. As a result, research on the detection of malware and network intrusion events through machine learning is being actively conducted in academia and industry. In international conferences and journals, research on security data analysis using deep learning, a field of machine learning, is presented. have. However, these papers focus on detection accuracy and modify several parameters to improve detection accuracy but do not consider the ratio of dataset. Therefore, this paper aims to reduce the cost and resources of many machine learning research by finding the ratio of dataset that can derive the highest detection accuracy in CNN Mobile net-based malware detection model.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.2
• /
• pp.11-18
• /
• 2019

In this paper, we propose a framework that can perform acceleration collision detection efficiently by using a cone based collision area in a particle-based system which requires collision detection with many objects. Three conditions determine particle and cone-based collision regions: 1) If there is a cone position within the radius of the adjacent particle, 2) In the case where the position of the adjacent particle exists in the cone area, 3) When adjacent particles exist between two vectors forming a cone area. As a result, it is defined that when the above conditions are all satisfied, the particle and the region of a cone have collided. In this paper, we automatically update the area of the cone, which is the collision detection area, according to the particle movement. Determine the direction and length of the cone based on the position and velocity of the particle to calculate the dynamic change of the cone. Collision detection is performed quickly using only the particles in the finally calculated area. The acceleration method proposed in this paper is simple to implement because it is executed with a closed form equation instead of explicitly creating the tree data structure, and collision inspection performance is improved in all results.

• The KIPS Transactions:PartB
• /
• v.18B no.3
• /
• pp.117-130
• /
• 2011

The purpose of this study is to produce a better way to detect crossroad accidents, which involves an efficient method to produce background images in consideration of object movement and preserve/demonstrate the candidate accident region. One of the prior studies proposed an employment of traffic signal interval within crossroad to detect accidents on crossroad, but it may cause a failure to detect unwanted accidents if any object is covered on an accident site. This study adopted inverse perspective mapping to control the scale of object, and proposed different ways such as producing robust background images enough to resist surrounding noise, generating candidate accident regions through information on object movement, and by using edge information to preserve and delete the candidate accident region. In order to measure the performance of proposed algorithm, a variety of traffic images were saved and used for experiment (e.g. recorded images on rush hours via DVR installed on crossroad, different accident images recorded in day and night rainy days, and recorded images including surrounding noise of lighting and shades). As a result, it was found that there were all 20 experiment cases of accident detected and actual effective rate of accident detection amounted to 76.9% on average. In addition, the image processing rate ranged from 10~14 frame/sec depending on the area of detection region. Thus, it is concluded that there will be no problem in real-time image processing.

• Korean Journal of Ecology and Environment
• /
• v.55 no.4
• /
• pp.294-304
• /
• 2022

This study carried out from March 2021 to October 2021 in the upper part (St. 1) and middle part (St. 2) section of Yongsu stream, a branch of the Geum river, using PIT telemetry to understand the movement patterns and habitat characteristics of Odontobutis interrupta, a Korean endemic species. O. interrupta collection was used kick net (5×5 mm) and fish trap (5×5 mm). After collecting fish, PIT tag insertion was performed immediately in the site. Reader (HPR Plus Reader, biomark, USA) and portable Antenna (BP Plus Portable Antenna, biomark, USA) were used for detection of fish to monitoring the tagged O. interrupta. As a result of PIT telemetry applied to 70 individuals, mean movement distance was 36.5 (SE, ±6.6) m. There was a significant difference between total length and movement distance (P≤0.05). O. interrupta was mainly identified in average water depth, 36.2±1.9 cm, average water velocity, 0.03±0.07 m s^-1 and average distance from watershed, 4.4±0.3 m. Extent of rock used for habitat was varied from 32 to 4,000 cm². There was no statistical difference between the area of the first selected rock and the area of the after selected rock (P>0.05). but there was significant difference between total length and the area of the rock except for detection before 24 hours (P<0.01). Therefore, to restore the habitat, it is considered necessary to create various substrate structures by providing various habitat environments (water depth, flow rate, stone, etc.) for each individual size.