• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04b
• /
• pp.899-902
• /
• 2001

본 논문은 도로 상에서 움직이는 물체를 검출하고 웨이블릿 변환을 이용하여 검출된 물체를 추적하는 방법을 제안한다. 제안한 방법은 후보 영역 추출 단계와 물체 판별 단계 그리고 추적 단계로 이루어진다. 첫번째 단계에서는 연속된 두 프레임간의 차영상 분석 방법을 기반하여 움직이는 물체에 의해 발생한 영역과 그 이외의 다른 영역들을 검출한다. 두 번째 단계에서는 검출된 영역에 포함되어 있는 물체를 웨이블릿 변환 계수를 입력하는 신경망을 사용하여 판별한다. 그리고 판별된 물체의 위치 및 크기 정보와 웨이블릿 변환 계수를 이용하여 추적한다. 제안한 방법을 실험한 결과, 물체 추적률은 93%, 프레임당 처리 시간은 0.19ms 이다. 본 논문에서 제안한 방법은 실시간 교통 감시 시스템에 유용하게 적용될 수 있다.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.07a
• /
• pp.292-297
• /
• 2002

농업인구가 점차 감소함에 따라 인력의 부족에 따른 농업생산 시설의 자동화가 불가피하며 노동 집약적이던 농업은 급속한 기계화로 인하여 농업 생산의 자동화가 차츰 현실화 되어가고 있다. 특히 시설내의 자동화는 특용 작물 등의 고부가가치 상품에만 한정되어 있으므로, 이를 개선하기 위해서는 광범위한 분야에서 자동화에 의한 전문화와 생산성 향상을 도모해야 한다 대부분의 기계 및 공정 등이 현재 점차적으로 무인자동화로 발전되고 있으며, 작업의 편리성을 강조하고 있다. 앞으로의 농업기계는 무인자동차 시스템의 도입으로 인하여 누구나 손쉽게 작업설정을 하고 기계 스스로 원활하게 작업을 수행할 수 있도록 개선되어야 한다. (중략)

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.511-515
• /
• 1998

본 논문에서는 전경과 배경을 동시에 고려하는 이동 물체 추적 기법을 제안한다. 본 논문에서 제안하는 이동 물체 추적 기법은 카메라가 고정되지 않은 동적인 환경에서 연속적으로 촬영된 동영상으로부터 배경과 전경을 분리한 후 배경으로부터는 카메라의 동작을, 그리고 전경으로부터는 이동 물체를 추적한다. 배경에서는 영상의 움직임을 나타내는 동작 벡터를 추출하여 2차원 파라미터 동작 모델인 어파인 동작 모델에 적합시키고, 회귀분석법을 통해 어파인 동작 모델을 구성하는 파라미터를 추출하여 분석함으로써 다양한 카메라의 동작을 구한다. 전경에서는 칼라 정보를 이용하여 물체들의 모델을 생성하고 매 시점마다 모델을 수정하면서 이동 물체를 추적한다. 본 논문에서는 카메라의 동작 및 이동 물체의 추적 시 예측 알고리즘인 칼만 필터를 활용함으로써 보다 효율적이고 강건한 추적이 가능하다. 또한, 배경에서 추출된 카메라의 동작 정보를 전경에서 추출하는 이동 물체의 이동궤적 정보 계산 시 활용함으로써 보다 정확하게 장면을 분석할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.629-632
• /
• 2002

본 논문에서는 획득 영상에서 k-평균 알고리즘에 의한 무게중심을 이용하여 이동 물체를 검출하고 추적하는 방법을 제안하였다. 이동 물체의 검출은 획득 영상에 대하여 차영상 후 에지 검출에 의해 수행된다. 제안한 검출 방법은 빛의 밝기와 각도에 의해 발생된 그림자 등의 변형을 제거하고, 이동 물체만을 검출할 수 있어, 빛에 영향을 받은 영상에 대해서도 이동 물체를 양호하게 검출할 수 있다. 물체 추적은 검출된 이동 물체에 대하여 k-평균 알고리즘으로 세 개의 물체 무게중심을 구하고, 무게중심 부근의 화소 평균값과 무게중심간의 거리를 구한다. 다음 프레임들에 대하여 탐색영역의 화소 평균값에 의해 후보 무게중심을 구하고, 물체 무게중심과 구한 후보 무게중심들의 표준편차와 무게중심간의 거리 차를 이용하여 이동 물체를 추적한다. 그 결과, 이동 물체의 추적 속도를 개선시켰고, 물체 추적 오차율을 줄였다.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.225-232
• /
• 2022

When we drive a vehicle in an IoT environment, there is a problem in that information of car users is collected without permission. The security measures used in the existing wired network environment cannot solve the security problem of cars running in the Internet of Things environment. Information should only be shared with entities that have been given permission to use it. In this paper, we intend to propose a method to prevent the illegal use of vehicle information. The method we propose is to use attribute-based encryption and dynamic threshold encryption. Real-time processing technology and cooperative technology are required to implement our proposed method. That's why we use fog computing's proxy servers to build smart gateways in cars. Proxy servers can collect information in real time and then process large amounts of computation. The performance of our proposed algorithm and system was verified by simulating it using NS2.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.131-147
• /
• 2020

RFID (Radio Frequency Identification) identifies a specific object by radio signals. As the tag provides a unique ID for the purpose of identification, RFID technology effectively solves the ambiguity and occlusion problem that challenges the laser or camera-based approach. This paper proposes an approach to track a moving object based on the integration of RFID and laser ranging information using a particle filter. To be precise, we split laser scan points into different clusters which contain the potential moving objects and calculate the radial velocity of each cluster. The velocity information is compared with the radial velocity estimated from RFID phase difference. In order to achieve the positioning of the moving object, we select a number of K best matching clusters to update the weights of the particle filter. To further improve the positioning accuracy, we incorporate RFID signal strength information into the particle filter using a pre-trained sensor model. The proposed approach is tested on a SCITOS service robot under different types of tags and various human velocities. The results show that fusion of signal strength and laser ranging information has significantly increased the positioning accuracy when compared to radial velocity matching-based or signal strength-based approaches. The proposed approach provides a solution for human machine interaction and object tracking, which has potential applications in many fields for example supermarkets, libraries, shopping malls, and exhibitions.

• Journal of Internet Computing and Services
• /
• v.12 no.2
• /
• pp.19-28
• /
• 2011

Recently, ubiquitous computing and related technologies is more and more growing concern about. Depending on the trend, the moving object recognition and tracking research have been required in order to meet the diverse needs of the user. In the location-based services, one of the most important issues in the indoor environment is to provide location-aware services. In this paper, the effective algorithm to help estimate the position of moving objects in an indoor environment is proposed. We propose an algorithm that combined the existing trilateration measurement and the improved measurement of environmental adaptation scene analysis. The proposed indoor location estimation algorithm use the trilateration measurement when we have enough anchor in the line-of-sight environment. Otherwise that use measurement of environmental adaptation scene analysis. Consequently, the proposed algorithm has been improved the localization accuracy of a moving object as well as was able to reduce complexity of the algorithm.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.1
• /
• pp.66-77
• /
• 2006

In this paper, we researched the searching and tracking locations of a home resident using ON/OFF switches and sensors and designed a remote monitoring system. As an implementation environment, this system is developed on the base of the distributed object group framework we have developed from previous works. In order to trace the moving locations of a home resident, we firstly showed a home structure which attaches ON/OFF switches and sensors to home appliances and indoor facilities being fixed in home. Whenever a home resident opens/closes these objects, the signals operated from ON/OFF switches and sensors are sent to a home server system. In this time, the real locations of ON/OFF switches and sensors that the signals are being occurred must be the current location that he/she stays. A home server system provides the functionalities that map the real location of a resident in home to virtual location designed on remote desk-tops or terminals like PDAs, and that construct a healthcare database consisted of moving patterns, moving ranges, momentum for analyzing the given searching locations and times Finally, this system provides these information for remotely monitoring services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.207-214
• /
• 2016

RFID technology is a technology perceiving information with the device called reader and tag which is now used in public transportation such as Hi-pass. In this paper, we design a system which tracks indoor location using this technology. GPS, the most frequently used location-tracking system, has a defect that its accuracy decreases when the device is indoor. In suggested experiment, we simulate signals according to the moving of located objects, then compare with the result of the experiment. Based on the extracted data, we inform data which is for the purpose of tracking system based on analysis of the route and errors. Simulations for the tracking were performed with relocation of real objects. In the real experiment, we arrange the readers around the room and move the tagged object that we like to know the location, then analyze the data from the equipment. This paper suggests the analyzed data for the future indoor tag tracking applications. We expect that the RFID based location positioning data will be used for other indoor positioning research and development.

• Journal of Internet Computing and Services
• /
• v.18 no.4
• /
• pp.61-67
• /
• 2017

Recently, CCTV has been combined with areas such as big data, artificial intelligence, and image analysis to detect various abnormal behaviors and to detect and analyze the overall situation of objects such as people. Image analysis research for this intelligent video surveillance function is progressing actively. However, CCTV images using 2D information generally have limitations such as object misrecognition due to lack of topological information. This problem can be solved by adding the depth information of the object created by using two cameras to the image. In this paper, we perform background modeling using Mixture of Gaussian technique and detect whether there are moving objects by segmenting the foreground from the modeled background. In order to perform the depth information-based segmentation using the RGB information-based segmentation results, stereo-based depth maps are generated using two cameras. Next, the RGB-based segmented region is set as a domain for extracting depth information, and depth-based segmentation is performed within the domain. In order to detect the center point of a robustly segmented object and to track the direction, the movement of the object is tracked by applying the CAMShift technique, which is the most basic object tracking method. From the experiments, we prove the efficiency of the proposed object detection and tracking method using the RGB-D model.