http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 육동빈 (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Support Vector Machine을 이용한 실시간 도로기상 검지 방법
서민호,육동빈,박새롬,전진호,박정훈,Seo, Min-ho,Youk, Dong-bin,Park, Sae-rom,Jun, Jin-ho,Park, Jung-hoon 한국산업융합학회 2020 한국산업융합학회 논문집 Vol.23 No.6
In this paper, we propose a method to classify road weather conditions into rain, fog, and sun using a SVM (Support Vector Machine) classifier after extracting weather features from images acquired in real time using an optical sensor installed on a roadside post. A multi-dimensional weather feature vector consisting of factors such as image sharpeness, image entropy, Michelson contrast, MSCN (Mean Subtraction and Contrast Normalization), dark channel prior, image colorfulness, and local binary pattern as global features of weather-related images was extracted from road images, and then a road weather classifier was created by performing machine learning on 700 sun images, 2,000 rain images, and 1,000 fog images. Finally, the classification performance was tested for 140 sun images, 510 rain images, and 240 fog images. Overall classification performance is assessed to be applicable in real road services and can be enhanced further with optimization along with year-round data collection and training.
-
서민호 ( Seo Minho ),박정훈 ( Park Junghoon ),육동빈 ( Youk Dongbin ) 한국도로교통공단 2020 교통안전연구 Vol.39 No.-
본 논문에서는 단안 카메라로부터 획득된 영상에 딥러닝 기반의 객체 인식 기술인 합성곱 신경망(Convolutional Neural Networks; CNN) 모델을 적용하여 보행자를 검출하고 검출된 보행자의 영상좌표를 지도좌표로 변환한 후 비례식으로부터 보행자의 신장을 유추하였다. 이를 위해 3.5m 고도의 지주물에 LDC(Lens Distortion Compensation)가 적용된 단안 카메라를 설치하고 보행자를 시준하도록 pitch와 yaw 각을 설정한 후 촬영을 수행하였다. 이후 합성곱 신경망 모델을 촬영된 보행자에 적용, bounding box를 활용하여 객체의 좌표를 실시간으로 추출하였고, bounding box의 index 정보를 이용하여 각 객체에 영상좌표를 부여하고 이를 지도좌표로 변환한 후 비례식을 이용해서 보행자의 신장을 산출하였으며 결과를 평가하였다. In this paper, the convolutional neural network (CNN) model, which is an object-recognition technology based on deep learning, was applied to images acquired from a monocular camera to detect pedestrians. The detected image coordinates of the pedestrians were converted to map coordinates, and the height of the pedestrians was inferred using a proportional equation. For this, a monocular camera equipped with lens distortion compensation was installed at an altitude of 3.5 m, and the pitch and yaw angles were set to collimate pedestrians. That is how we proceed image capturing. In the CNN model, the image coordinates of the object were acquired in real-time using the bounding box. After converting the image coordinates of the acquired object to map coordinates, the height of pedestrians could be calculated using a proportional equation.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
