http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Signature 기반의 겹쳐진 원형 물체 검출 및 인식 기법
박상범(SangBum Park),한헌수(Hernsoo Hahn),한영준(Youngjoon Han) 제어로봇시스템학회 2008 제어·로봇·시스템학회 논문지 Vol.14 No.1
This paper proposes a new algorithm for detecting and recognizing overlapped objects among a stack of arbitrarily located objects using a signature representation scheme. The proposed algorithm consists of two processes of detecting overlap of objects and of determining the boundary between overlapping objects. To determine overlap of objects, in the first step, the edge image of object region is extracted and those areas in the object region are considered as the object areas if an area is surrounded by a closed edge. For each object, its signature image is constructed by measuring the distances of those edge points from the center of the object, along the angle axis, which are located at every angle with reference to the center of the object. When an object is not overlapped, its features which consist of the positions and angles of outstanding points in the signature are searched in the database to find its corresponding model. When an object is overlapped, its features are partially matched with those object models among which the best matching model is selected as the corresponding model. The boundary among the overlapping objects is determined by projecting the signature to the original image. The performance of the proposed algorithm has been tested with the task of picking the top or non-overlapped object from a stack of arbitrarily located objects. In the experiment, a recognition rate of 98% has been achieved.
환경 변화에 강인한 차선 검출 로직을 위한 영상 개선 알고리즘
박상범(Sangbum Park),서성진(Sungjin Seo),조준범(Junbeom Cho) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
We proposed the image enhancement algorithm for the robust lane detection technique. There are many noises such as text, temporary lane under construction, skid mark and so on. Especially lane mark on the road has few characteristic features such as linearity or connectivity to isolate from background in the image. Therefore, it is too difficult detecting lane mark in each image frame. In this paper, we used luminance, chrominance and reflectance features for lane detection. There are three kinds of lane on the road : white, yellow, blue. We are using color enhancement filter to determine lane region in the image. The yellow and blue lane has significantly bigger value in the chrominance region. When the color enhancement filter is acting on the blue lane, blue value is bigger than other values in the color domain with constant rate and yellow lane is detected with similar way. The reflectance feature on the lane is detected using homomorphic filter. The homomorphic filter is widely used in the image enhancement field, so we apply this filter as preprocessing filter of many filters in this method. Finally, we compared our proposed method for lane detection with other methods such as intensity transformation, histogram modeling.
인문,사회과학편 : 명시·암시적 상황인식이 페널티 킥 막기 성공률과 P300에 미치는 영향
김진구(Kim,JinGu),박상범(Park,SangBum) 한국체육학회 2007 한국체육학회지 Vol.46 No.2
본 연구의 목적은 첫째, 명시·암시적 상황인식이 골키퍼의 페널티 킥 막기 성공률(방향 예측)에 어떤 영향을 미치는 지를 연구하는데 있으며, 둘째 페널티킥에서 골키퍼가 상대와 맞서 상황인식을 하는 동안 나타나는 P300(정보처리)을 연구하고자 한다. 피험자는 무선 표집된 45명의 남자대학생으로 이들은 각각 (1) 암시적 상황인식집단, (2) 명시적 상황인식집단, 그리고 (3) 통제집단에 각각 15명씩 무작위로 배치되었다. 축구선수 5명에게 방향을 지정해 주고 페널티킥을 하도록 한 후 촬영하여 자료화면으로 만들었다. 방향은 ① 좌상, ② 좌하, ③ 가운데, ④ 우상, 그리고 ⑤ 우하 방향에 숫자가 나타나도록 편집하였다. 과제는 공의 방향을 예측하여 가능한 한 빨리 앞에 놓인 젤리빈 스위치는 누르는 것이었다. 연구 결과, 명시 · 암시적 방법 모두 페널티킥 막기 성공률을 향상시키는 것으로 나타났다. 그러나 ERP 분석에서는 암시적 집단 피험자들의 P300 잠재기가 명시적 집단이나 통제집단 피험자들보다 길었으며, 진폭도 암시적 명시적 그리고 통제집단보다 순서로 높게 나타났다. The purposes of this study were: (1) to investigate how explicit and implicit situation awareness affect goal-keepers' blocking success-ratio in penalty-kicks and (2) to examine P300 to determine situation awareness while the goal keepers facing with kicking. Participants were forty-five university students whose age ranged 19 to 29 years, with a mean age of 21.8. They were randomly assigned to one of three experimental conditions :(1) implicit situation awareness group, (2) explicit situation awareness group and (3) control group. In this experiment, five high school soccer players have kicked about 100 penalty-kicks and have filmed. Clips were designed with ① left upper, ③ left lower, ③ center, ④ right upper and ⓒ right lower balls. The task was pressing one of five jelly buttons which placed in front of participants as fast as possible when the participants supposed to anticipate or aware the direction of ball. The results of this study indicated that explicit and implicit situation awareness were a beneficial tool to improve keeper7 s blocking success ratio in penality kicks situation_ In P300 analysis, the latency of P300 for the implicit situation awareness group was longer than the explicit situation awareness and control groups. In addition, the amplitudes of P300 of the implicit group were higher than the explicit and control groups.