교통객체 인식 정확도를 위한 소실점 기반 3D 객체 인식 방법
Vanishing point-based 3D object detection method for improving traffic object recognition accuracy
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
이 논문은 영상 카메라를 이용하여 교통 객체를 인식하고자 하는 경우, 영상 내 객체 인식 정확도를 높이기 위해 소실점을 이용하여 객체에 대한 3D 바운딩 박스를 생성하는 방법이다. 최근인공지능을 이용하여 교통 영상 카메라로 촬영된 차량을 검출하고자 하는 경우 이 3D 바운딩 박스 생성 알고리즘을 적용하고자 한다. 카메라 설치 각도와 카메라가 촬영한 영상의 방향성을 분석하여 종 방향 소실점(VP1)과 횡 방향 소실점(VP2)을 도출하고 이를 기반으로 분석 대상 동영상에서 이동하는 객체를 특정하게 된다. 이 알고리즘을 적용하면 감지된 객체의 위치, 종류, 크기등 객체 정보 검출이 용이하고, 이를 자동차와 같은 이동류에 적용하는 경우 이를 트래킹하여 각객체가 이동한 위치와 좌표, 이동속도 및 방향 등을 알 수 있다. 실제 도로에 적용한 결과 트래킹이 10% 향상되었으며 특히 음영지역(큰 차에 가려진 극히 적은 차량 부위)의 인식율과 트래킹이100% 개선되는 등 교통 데이터 분석 정확성을 향상시킬 수 있었다.
Abstract
In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.
참고문헌 (12)
- Y. Horry, "Tour into the picture : using a spidery mesh interface to make animation from a single image", Proceedings of SIGRAPH ‘97, pp.225~232 (1997)
- F. A. van den Heuvel, "vanishing point detection for architectural photogrammetry", International Archives of Photogrammetry and Remote Sensing, XXXII(5), pp.652~659 (1998)
- Hyung Woo Kang, "Tour Into the Picture using a Vanishing Line and its Extension to Panoramic Images", Computer Graphics Forum, 20(3), pp.132~141 (2001), Wiley[DOI]
- Ross Girshick, "Fast R-CNN", Proceedings of the IEEE international conference on computer vision, pp.440~1448 (2015)
- Shaoqing Ren, "Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Network", Advances in neural information processing system, 91~99 (2015)
- Mingjie Liu, "Online multiple object tracking using confidence score‐based appearance model learning and hierarchical data association", IET Computer Vision, 13(3), pp.312~318 (2019), Institution of Engineering and Technology (IET)[DOI]
- Morgan Quigley, "ROS:an open-source Robot Operating System", ICRA workshop on open source software, 3(3.2), pp.5~ (2009)
- B. Wu, "SqueezeSegV2:Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a Lidar Point Cloud", ICRA, 6(3), pp.1721~1737 (2019)[DOI]
- Xiaozhi Chen, "Multi-View 3D Object Detection Network for Autonomous Driving", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1907~1915 (2017)
- Pan Wei, "Lidar and Camera Detection Fusion in a Real-Time Industrial Multi-Sensor Collision Avoidance System", Electronics, 7(84) (2018)[DOI]