http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
윤석민(Frank Yun),유한주(Haanju Yoo),최진영(Jinyoung Choi) 대한전기학회 2009 정보 및 제어 심포지엄 논문집 Vol.2009 No.5
We present an efficient and robust measurement model for visual tracking. This approach builds on and extends work on subspace representations of measurement model. Subspace-based tracking algorithms have been introduced to visual tracking literature for a decade and show considerable tracking performance due to its robustness in matching. However the measures used in their measurement models are often restricted to few approaches. We propose a novel measure of object matching using Angle In Feature Space, which aims to improve the discriminability of matching in subspace. Therefore, our tracking algorithm can distinguish target from similar background clutters which often cause erroneous drift by conventional Distance From Feature Space measure. Experiments demonstrate the effectiveness of the proposed tracking algorithm under severe cluttered background.
실환경 적용을 위한 다중 시점 다중 객체 탐지 및 추적 시스템
전영한(Younghan Jeon),김기경(Kikyung Kim),유한주(Haanju Yoo),변문섭(Moonsub Byeon),최진영(Jin Young Choi) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.6
In this paper we propose a system for multiple object detection and tracking with multiple cameras. The system follows the tracking-by-detection framework and is designed to meet the performance required in actual environment such as smart class. Detection results are obtained by ACF(Aggregated Channel Features) detector and tracklets are generated based on these detection proposals. Tracklets are associated by the proposed online algorithm based on Multiple Hypothesis Tracking (MHT). Experiments show a comparable performance with the state-of-the-art batch algorithms on PETS2009 dataset and validate the applicability to real environment using the Smart-class dataset
실 환경 보행자 탐지를 위한 선택적 피라미드 탐색 알고리즘
김기경(Kikyung Kim),전영한(Younghan Jeon),유한주(Haanju Yoo),변문섭(Moonsub Byeon),최진영(Jin Young Choi) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.6
In this paper, we propose a selective pyramid searching algorithm for pedestrian detection in real environments. We generate a pedestrian height map using static camera constraints. Given a pixel location with the pedestrian height map, we can select the pyramid used for searching. With the selective pyramid searching method, the sliding window searching can be done efficiently with a proper scale. In our experiments, It is shown that the proposed algorithm reduces computational time greatly without loss of precision.