• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.149-152
• /
• 2016

In this paper, we propose an algorithm to track human body of input video from a single camera. The proposed method gets the difference image between gray image of input image and one of background image and also the difference image between hue image of input image and one of background image. Then we combine the results, splits foreground and background and detect human body objects. Then each object is numbered and is tracked. The proposed method tracks each object using the intensity and hue histogram of local area in objects. The proposed method is applied to video from a camera and tracked well the hided objects and the overlapped objects.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.283-294
• /
• 2006

In this paper, we propose a real-time face detection/tracking methodology with Haar wavelets and skin color. The proposed method boosts face detection and face tracking performance by combining skin color and Haar wavelets in an efficient way. The proposed method resolves the problem such as rotation and occlusion due to the characteristic of the condensation algorithm based on sampling despite it uses same features in both detection and tracking. In particular, it can be applied to a variety of applications such as face recognition and facial expression recognition which need an exact position and size of face since it not only keeps track of the position of a face, but also covers the size variation. Our test results show that our method performs well even in a complex background, a scene with varying face orientation and so on.

• Journal of the Korea Convergence Society
• /
• v.7 no.5
• /
• pp.29-34
• /
• 2016

Recently, with the development of high-tech industry, the use of the drones in various aspects of daily life is rapidly advancing. With technical and functional advancements, drones have an advantage of being easy to be utilized in the areas of use according to various lifestyles. In addition, through the diversification of the drone service converged with image processing medium such as camera and CCTV, an automated security system that can replace humans is expected to be introduced. By designing these unmanned security technology, a new convergence security drone service techniques that can strengthen the previous drone application technology will be proposed. In the proposed techniques, a biometric authentication technology will be designed as additional authentication methods that can determine the safety incorporated with security by selecting the search and areas of an object focusing on the objects in the initial windows and search windows through OpenCV technology and CAM-Shift algorithm which are an object tracking algorithm. Through such, a highly efficient security drone convergence service model will be proposed for performing unmanned security by using the drones that can continuously increase the analysis of technology on the mobility and real-time image processing.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.385-388
• /
• 2013

물류 고도화를 통한 기업 생산성 확보 및 생존 경쟁력 강화를 위해 기존의 공급망 관리(SCM) 기술에 RFID 기술을 융합함으로써 물품자동 인식, 물류정보 교환 및 추적 등의 지능화 서비스를 온라인상에서 실시간으로 제공할 수 있는 기술이 적용되고 있다. 하지만 물류정보 동기화 기술 개발 측면에서는 물류정보의 단순 가시화 시스템 개발 수준에 머물고 있는 것이 현실이고, 본격적인 확산을 위해 수집된 데이터 오류 검출 및 보정이라는 물류정보 동기화 기술 개발로 물류 시스템 운용 비용을 절감할 수 있다면 그 파급 효과가 매우 클 것이다. 지금까지는 RFID 인프라 기술 개발에 집중해 왔기에 물류정보 동기화 기술은 아직 초기 연구 단계에 머무르고 있다. 본 논문은 RFID 기반 공급망 상에서 발생할 수 있는 물류정보 동기 오류를 검출하고 보정할 수 있는 물류정보 동기화 알고리즘을 설계하고, 향후 공급망의 변화 및 확장 등의 이유로 알고리즘을 효율적으로 수정 보완할 수 있는 비즈니스 룰엔진 기반의 아키텍처를 구현하여 글로벌 물류 기업에 적용하고, 그 결과를 분석하여 물류정보 동기화 알고리즘과 구현 아키텍처의 효율성을 증명하였다.

• Journal of Korea Multimedia Society
• /
• v.17 no.7
• /
• pp.787-796
• /
• 2014

Many mobile robot navigation methods utilize laser scanners, ultrasonic sensors, vision camera, and so on for detecting obstacles and path following. However, human utilizes only vision(e.g. eye) information for navigation. In this paper, we study a mobile robot control method based on only the camera vision. The Gaussian Mixture Model and a shadow removal technology are used to divide the foreground and the background from the camera image. The mobile robot uses a combined CAMSHIFT and KLT feature tracker algorithms based on the information of the foreground to follow a person. The algorithm is verified by experiments where a person is tracked and followed by a robot in a hallway.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.155-166
• /
• 2012

This paper proposes a new method of estimating the hand pose through the Mean-Shift tracking algorithm using the fusion of color and depth information for marker-less augmented reality. On marker-less augmented reality, the most of previous studies detect the hand region using the skin color from simple experimental background. Because finger features should be detected on the hand, the hand pose that can be measured from cameras is restricted considerably. However, the proposed method can easily detect the hand pose from complex background through the new Mean-Shift tracking method using the fusion of the color and depth information from 3D sensor. The proposed method of estimating the hand pose uses the gravity point and two random points on the hand without largely constraints. The proposed Mean-Shift tracking method has about 50 pixels error less than general tracking method just using color value. The augmented reality experiment of the proposed method shows results of its performance being as good as marker based one on the complex background.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.159-166
• /
• 2012

There are several ways such as GPS(Global Positioning System) and INS (Inertial Navigation System) to track the location of moving vehicle. The GPS has the advantages of having non-accumulative error even if it brings about errors. In order to obtain the position information, we need to receive at least 3 satellites information. But, the weak point is that GPS is not useful when the 혠 signal is weak or it is in the incommunicable region such as tunnel. In the case of INS, the information of the position and posture of mobile with several Hz~several hundreds Hz data speed is recorded for velocity, direction. INS shows a very precise navigational performance for a short period, but it has the disadvantage of increasing velocity components because of the accumulated error during integration over time. In this paper, sensor fusion algorithm is applied to both of INS and GPS for the position information to overcome the drawbacks. The proposed system gets an accurate position information from experiment using SVD in a non-accessible GPS terrain.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.6
• /
• pp.1161-1175
• /
• 2018

An unexpected event could be easily followed by a large secondary accident due to the limitation in sight of drivers in road tunnels. Therefore, a series of automated incident detection systems have been under operation, which, however, appear in very low detection rates due to very low image qualities on CCTVs in tunnels. In order to overcome that limit, deep learning based tunnel incident detection system was developed, which already showed high detection rates in November of 2017. However, since the object detection process could deal with only still images, moving direction and speed of moving vehicles could not be identified. Furthermore it was hard to detect stopping and reverse the status of moving vehicles. Therefore, apart from the object detection, an object tracking method has been introduced and combined with the detection algorithm to track the moving vehicles. Also, stopping-reverse discrimination algorithm was proposed, thereby implementing into the combined incident detection processes. Each performance on detection of stopping, reverse driving and fire incident state were evaluated with showing 100% detection rate. But the detection for 'person' object appears relatively low success rate to 78.5%. Nevertheless, it is believed that the enlarged richness of image big-data could dramatically enhance the detection capacity of the automatic incident detection system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.159-164
• /
• 2019

Detecting wildfire using only color in image information is a very difficult issue. This paper proposes an algorithm to detect forest fire area by analyzing color and motion of the area in the video including forest fire. The proposed algorithm removes the background region using the Gaussian Mixture based background segmentation algorithm, which does not depend on the lighting conditions. In addition, the RGB channel is changed to an HSV channel to extract flame candidates based on color. The extracted flame candidates judge that it is not a flame if the area moves while labeling and tracking. If the flame candidate areas extracted in this way are in the same position for more than 2 minutes, it is regarded as flame. Experimental results using the implemented algorithm confirmed the validity.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.119-122
• /
• 2022

연합학습은, 데이터 샘플을 보유하는 다수의 분산 에지 디바이스 또는 서버들이 원본 데이터를 공유하지 않고 기계학습 문제를 해결하기 위해 협력하는 기술로서, 각 클라이언트는 소유한 원본 데이터를 로컬모델 학습에만 사용함으로써, 데이터 소유자의 프라이버시를 보호하고, 데이터 소유 및 활용의 파편화 문제를 해결할 수 있다. 연합학습을 위해서는 통계적 이질성 및 시스템적 이질성 문제 해결이 필수적이며, 인공지능 모델 정확도와 시스템 성능을 향상하기 위한 다양한 연구가 진행되고 있다. 최근, 중앙서버 의존형 연합학습의 문제점을 극복하고, 데이터 무결성 및 추적성과 데이터 소유자 및 연합학습 참여자에게 보상을 효과적으로 제공하기 위한, 블록체인 융합 연합학습기술이 주목받고 있다. 본 연구에서는 이더리움 기반 블록체인 인프라와 호환되는 연합학습 레퍼런스 아키텍처를 정의 및 구현하고, 해당 아키텍처의 실용성과 확장성을 검증하기 위하여 대표적인 연합학습 알고리즘과 데이터셋에 대한 실험을 수행하였다.