http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
에지 관측 모델과 파티클 필터를 이용한 이동 객체 추적
김효연 ( Hyoyeon Kim ),김기상 ( Kisang Kim ),최형일 ( Hyung-il Choi ) 한국인터넷정보학회 2016 인터넷정보학회논문지 Vol.17 No.3
본 논문에서는 에지를 사용한 관측 모델과 파티클 필터를 이용하여 실시간으로 객체를 추적하는 방법을 제안한다. 논문에서 제안하는 방법은 먼저, 초기 프레임에서 추적하고자 하는 객체를 지정한다. 지정된 객체에 대해 에지 관측 모델과 N개의 파티클 필터 집합을 생성한다. 에지 관측 모델과 파티클의 8방향 에지 모델의 중간 거리 평균을 비교하여 가중치를 계산하고, 계산된 값으로 가중치를 업데이트한다. 업데이트된 가중치를 이용해 파티클들을 리샘플링한 후, 추적 객체의 상태인 현재 위치를 추정할 수 있다. 마지막으로 본 논문에서 제안하는 방법은 여러 실험 데이터를 이용하여 기존의 방법과의 비교분석을 통해 안정적인 추적에 대한 성능을 입증한다. In this paper, we propose a method that is tracking an object in real time using particle filter and the observation model with edge. First of all, the proposed method defines the object to be tracked in the initial frame. Then, it generates the edge observation model for the object to be tracked and a set of particles. It calculates the weight by comparing the average of the middle distance in eight-way of particle filter edge model with that in edge observation model, and then updates the weight with the calculated value. After resampling particles using the updated weights, it estimates the current location of the tracked object. Finally, this paper demonstrates the performance of the stable tracking through comparison with the existing method by using a number of experimental data.
김효연(Hyoyeon Kim),김기상(Kisang Kim),최형일(Hyung-Il Choi) 한국컴퓨터정보학회 2017 韓國컴퓨터情報學會論文誌 Vol.22 No.1
In this paper, we propose an efficient method that is tracking an object in real time using particle filter and adaptive observation model. When tracking object, it happens object shape variation by camera or object movement in variety environments. The traditional method has an error of tracking from these variation, because it has fixed observation model about the selected object by the user in the initial frame. In order to overcome these problems, we propose a method that updates the observation model by calculating the similarity between the used observation model and the eight-way of edge model from the current position. If the similarity is higher than the threshold value, tracking the object using updated observation model to reset observation model. On the contrary to this, the algorithm which consists of a process is to maintain the used observation model. Finally, this paper demonstrates the performance of the stable tracking through comparison with the traditional method by using a number of experimental data.
Left pneumonectomy using self-cutting linear endoscopic stapler in a dog
이시은(Si Eun Lee),박효진(Hyojin Park),이채영(Chae-Yeong Lee),최현종(Hyeon-Jong Choi),김효연(Hyoyeon Kim),김민연(Minyeon Kim),홍정호(Jeongho Hong),유도현(DoHyeon Yu),황태성(Tae Sung Hwang),이희천(Hee Chun Lee),이재훈(Jae-Hoon Lee),이동 한국예방수의학회 2021 예방수의학회지 Vol.45 No.4
A 13-year-old mixed dog was referred to the animal medical center, Gyeongsang National University. Lung masses were diagnosed at the left cranial and caudal lobes through diagnostic imaging, and consequently, left pneumonectomy was performed using a self-cutting linear endoscopic stapler. The pulmonary arteries, veins, and bronchus of each lung lobe were sealed and resected at once, and any air leakage or bleeding was not observed after the surgery. Compared to the conventional ligation method, the self-cutting linear endoscopic stapler has the advantage of significantly reducing the operation time and enabling simple and reliable sealing.