• 대한전자공학회논문지SP
• /
• 제45권4호
• /
• pp.32-40
• /
• 2008

기존의 보안 감시 시스템은 화각이 좁은 일반 렌즈를 주로 사용하여 천정이 낮고 실내가 넓은 환경에 적용하기가 어려웠다. 이를 해결하기 위해 단순히 카메라의 수를 늘리는 방법은 비용의 증가와 설치의 어려움 등의 문제가 있다. 따라서 본 논문에서는 화각이 180도인 어안 카메라를 다수 설치한 사용자 감시 시스템을 제안하였다. 단일 어안 카메라에서 물체간의 교차에 의한 가림현상이 발생되는 문제를 해결하기 위해서 카메라간의 상동관계를 다중 어안 카메라 시스템에 적용하였다. $17{\times}14m$의 공간의 2.5m 높이에 설치된 4대의 어안 카메라에서 5명이 서로 교차하면서 움직이도록 하여 수행한 결과, 단일 어안카메라에서 최대 46.1% 낮은 검출율을 보인 반면 제안된 시스템에서 83.0%로 향상된 성능을 보였다.

• 제어로봇시스템학회논문지
• /
• 제21권7호
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.418-427
• /
• 2016

A smart parking management requires to track a vehicle in a indoor parking lot and to detect the place where the vehicle is parked. An advanced parking system watches all space of the parking lot with CCTV cameras. We can use these cameras for vehicles tracking and detection. In order to cover a wide area with a camera, a fisheye lens is used. In this case the shape and size of an moving vehicle vary much with distance and angle to the camera. This makes vehicle detection and tracking difficult. In addition to the fisheye lens, the vehicle headlights also makes vehicle detection and tracking difficult. This paper describes a method of realtime vehicle detection and tracking robust to the harsh situation described above. In each image frame, we update the region of a vehicle and estimate the vehicle movement. First we approximate the shape of a car with a quadrangle and estimate the four sides of the car using multiple histograms of oriented gradient. Second we create a template by applying a distance transform to the car region and estimate the motion of the car with a template matching method.