http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
서민호 ( Seo Minho ),박정훈 ( Park Junghoon ),육동빈 ( Youk Dongbin ) 한국도로교통공단 2020 교통안전연구 Vol.39 No.-
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.