http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김동기(Donggi Kim),최홍철(Hongchul Choi),유성준(Seong Joon Yoo),한동일(Dongil Han) 대한전기학회 2015 대한전기학회 학술대회 논문집 Vol.2015 No.4
This study proposes an algorithm for recognizing apple trees in image and detecting apples to measure the number of apples on apple trees. The proposed algorithm explores whether there are apple trees based on the number of image block-unit edges and then detect apple areas. In order to extract colors appropriate for apple areas, CIE L*a*b* color space was used to extract colors. In order to extract a circle in the form of an apple, Histogram of Oriented Gradients (HOG) was used. Then using AdaBoost Learning algorithm, characteristics data on apples were learned and generated. With generated data, detection of apple areas was made. Then we apply a weight to the apple area extracted by using the CIE L*a*b* to find more accurate apple area. The proposed algorithm had a higher detection rate than existing pixel-based image processing algorithms and minimized false detection.
김동기(Donggi Kim),최홍철(Hongchul Choi),유성준(Seong Joon Yoo),한동일(Dongil Han) 대한전기학회 2015 정보 및 제어 심포지엄 논문집 Vol.2015 No.4
This study proposes an algorithm for recognizing apple trees in image and detecting apples to measure the number of apples on apple trees. The proposed algorithm explores whether there are apple trees based on the number of image block-unit edges and then detect apple areas. In order to extract colors appropriate for apple areas, CIE L*a*b* color space was used to extract colors. In order to extract a circle in the form of an apple, Histogram of Oriented Gradients (HOG) was used. Then using AdaBoost Learning algorithm, characteristics data on apples were learned and generated. With generated data, detection of apple areas was made. Then we apply a weight to the apple area extracted by using the CIE L*a*b* to find more accurate apple area. The proposed algorithm had a higher detection rate than existing pixel-based image processing algorithms and minimized false detection.
김동기(Donggi Kim),최홍철(Hongchul Choi),유성준(Seong Joon Yoo),한동일(Dongil Han) 대한전자공학회 2015 대한전자공학회 학술대회 Vol.2015 No.6
This study proposes an algorithm for recognizing apple trees in image and detecting green apples to measure the number of apples on apple trees. The proposed algorithm searches whether there are apple trees based on the number of image block-unit edges and then detect apple areas. In order to remove colors appropriate for background areas, CIE L*a*b* color space was used to extract colors. In order to extract apple characteristics strong against illumination change, modified census transform (MCT) was used. Then using AdaBoost Learning algorithm, characteristics data on apples were learned and generated. With generated data, detection of apple areas was made. The proposed algorithm has proved the effectiveness for the green apple detection.
황수환(Suhwan Hwang),김은수(EunSue Kim),이봉준(Bongjun Lee),김길주(Giljoo Kim),김동기(Donggi Kim),김승재(Seungjae Kim),이인호(Inho Lee) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
It is the essential technique to detect the position of passenger head before rear collision for minimizing the passenger neck injury. This research introduces the technique of measuring distance between the head and headrest using the electrostatic capacity sensor in the headrest. According to the sensor material, the detecting performance of sensor was investigated. And the reliability was also tested with the new developed test-bench. On the other hand, the new mechanism is applied to the pre-crash headrest for moving the headrest front-upward. When the distance between the head rest and passenger head is measured accurately, pre-crash headrest could be adjusted to most proper position for Whiplash protection. New developed headrests can access passenger heads close to 10㎜ within 0.8 second.
박상환(Sanghwan Park),편종권(Jongkweon Pyun),김형준(Hyeongjun Kim),황수환(Suhwan Hwang),이미현(Mihyun Lee),김동기(Donggi Kim),김정찬(Jeongchan Kim) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
Integration of functions currently being applied to develop and integrate the controller is analyzed by the synergy. And the process of developing integrated control over the results obtained from the designers of future vehicle to suggest approaches to controller design is aimed.