본 논문은 고속토로에 설치되어 있는 CCTV카메라 영상을 이용하여 자동으로 교통정보를 수집할 수 있도록 영상검지기 기능을 부가하는 방법을 제안한다. 현행 고속도로 영상검지기에서 수집되는 교통정보는 차로별로 교통정보를 검지하여 수집할 수 있으나 이 방법은 대형차량이 지나가는 경우 Occlusion에 의한 오 검지 빈도가 빈번히 발생하고 있다. 또한 이 Occlusion의 영향으로 고속도로 8차로 중 최고 6차로까지만 검지가 가능하고 그 이상의 차로를 검지한다는 것은 불가능하다. 따라서 본 논문에서는 교통정보를 차로볕 검지를 하지 않고 전체 차로를 포함하는 검지영역을 설정한 다음 다음 이 검지영역 안에서 차량이 통과할 때까지 개별차량을 추적하여 교통정보를 수집함으로써 고속도로 8차로까지 검지가 가능한 알고리즘을 제안한다. 본 연구는 실제 경부고속도로 상행선 기흥IC에 실험용 CCTV카메라를 설치하여 획득한 영상과, 청계터널 앞 도로에서 녹화한 영상을 대상으로 실험을 하였으며, 영상처리는 frame-grabber보드에서 초당 30프레임으로 캡쳐를 한 다음 $640{\times}480$ 해상도와 빠른 데이터 처리를 위해서 256 gray-level로 영상처리를 하였다.
본 논문은 고속토로에 설치되어 있는 CCTV카메라 영상을 이용하여 자동으로 교통정보를 수집할 수 있도록 영상검지기 기능을 부가하는 방법을 제안한다. 현행 고속도로 영상검지기에서 수집되는 교통정보는 차로별로 교통정보를 검지하여 수집할 수 있으나 이 방법은 대형차량이 지나가는 경우 Occlusion에 의한 오 검지 빈도가 빈번히 발생하고 있다. 또한 이 Occlusion의 영향으로 고속도로 8차로 중 최고 6차로까지만 검지가 가능하고 그 이상의 차로를 검지한다는 것은 불가능하다. 따라서 본 논문에서는 교통정보를 차로볕 검지를 하지 않고 전체 차로를 포함하는 검지영역을 설정한 다음 다음 이 검지영역 안에서 차량이 통과할 때까지 개별차량을 추적하여 교통정보를 수집함으로써 고속도로 8차로까지 검지가 가능한 알고리즘을 제안한다. 본 연구는 실제 경부고속도로 상행선 기흥IC에 실험용 CCTV카메라를 설치하여 획득한 영상과, 청계터널 앞 도로에서 녹화한 영상을 대상으로 실험을 하였으며, 영상처리는 frame-grabber보드에서 초당 30프레임으로 캡쳐를 한 다음 $640{\times}480$ 해상도와 빠른 데이터 처리를 위해서 256 gray-level로 영상처리를 하였다.
This paper is proposed to algorithm for measuring traffic information automatically, for example, volume count, speed and occupancy rate, from CCTV camera images installed on highway, add to function of image detectors which can be collected the traffic information. Recently the method of traffic in...
This paper is proposed to algorithm for measuring traffic information automatically, for example, volume count, speed and occupancy rate, from CCTV camera images installed on highway, add to function of image detectors which can be collected the traffic information. Recently the method of traffic informations are counted in lane one by one, but this manner is occurred critical errors by occlusion frequently in case of passing larger vehicles(bus, truck etc.) and is impossible to measure in the 8 lanes of highway. In this paper, installed the detection area include with all lanes, traffic informations are collected using tracking algorithm with passing vehicles individually in this detection area, thus possible to detect all of 8 lanes. The experiment have been conducted two different real road scenes for 20 minutes. For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, $640{\times}480$ pixels resolution and 256 gray-levels to reduce the total amount of data to be interpreted.
This paper is proposed to algorithm for measuring traffic information automatically, for example, volume count, speed and occupancy rate, from CCTV camera images installed on highway, add to function of image detectors which can be collected the traffic information. Recently the method of traffic informations are counted in lane one by one, but this manner is occurred critical errors by occlusion frequently in case of passing larger vehicles(bus, truck etc.) and is impossible to measure in the 8 lanes of highway. In this paper, installed the detection area include with all lanes, traffic informations are collected using tracking algorithm with passing vehicles individually in this detection area, thus possible to detect all of 8 lanes. The experiment have been conducted two different real road scenes for 20 minutes. For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, $640{\times}480$ pixels resolution and 256 gray-levels to reduce the total amount of data to be interpreted.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
제안 방법
Therefore, it is not possible to measure all over the 8 lanes (including upstream and downstream). In this research to solve the problem of occlusion, one detection area block is set up including all of 8 lanes, and tracking should be applied that the vehicles pass through a detection block.
Therefore, it is impossible to measure all over the 6 lanes including upstream and downstream. In this research to solve this problem, one detection area block is set up including all of 8 lanes, and tracking should be applied that the vehicles pass through a detection block.
In this research, for measuring traffic information automatically such as volume count, speed and occupancy rate, from CCTV camera images installed on highway, and then being added function of image detectors which can be collected the traffic information. Recently, the most algorithms of traffic informations using image surveillance system have a critical errors by occlusion[10] in case of passing larger vehicles such as bus, truck etc.
In this research, the detection area is divided into n><n sub-blocks in order to decide 나le VAR(Vehicle Area Rectangle). If white colors in each sub-block are distributed more than A% after binarization, occupancy flag should be TRUE.
대상 데이터
Experiments have been conducted on image data captured at CCTV camera installed 15 meters high at Kiheung Interchange(IC) upstream place on the highway and video recorded image from image detector system at Chungkye tunnel. The images of Kiheung IC was collected on July 5, 2001, from 2-00pm for 20 minutes and images at the front of Chungkye tunnel was recorded on October 22, 1998, from ll:15am for 20 minutes.
For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, 640x480 pixels resolution and 256 gray-levels to reduce the total amount of data to be interpreted.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.