著者
泉田 喜一郎 椎屋 和久 高橋 洋海 デルウィシュ サラハ
出版者
The Institute of Electrical Engineers of Japan
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.122, no.3, pp.498-505, 2002-03-01 (Released:2008-12-19)
参考文献数
13
被引用文献数
1 1

This study is concerned with detection of objects in motion from time serial pictures of a 6-D. of freedom motion monocular camera. As a point in real space throw an image on corresponding pixels of time serial pictures. So to solve this problem to find out the corresponding algorithm is essential. In this paper we proposed a new method of the detection of motion objects based on compensating background image shift caused by camera rotation and translation. The main point of this idea is, to take two pictures by the passive sensor (CCD camera) in two different times tk and tk+_??_ while the platform is moving, by correcting them rotationally (also called vertical rectification) the rotation disparity will be excluded, and we get two parallel frames that will be matched through their histograms for the translation-distortion extraction.
著者
椎屋 和久 泉田 喜一郎 デルウィシュ サラハ 外山 太郎
出版者
The Institute of Electrical Engineers of Japan
雑誌
電気学会論文誌. C, 電子・情報・システム部門誌 = The transactions of the Institute of Electrical Engineers of Japan. C, A publication of Electronics, Information and System Society (ISSN:03854221)
巻号頁・発行日
vol.123, no.3, pp.511-516, 2003-03-01
参考文献数
11
被引用文献数
2 3

This paper is concerned with the calculation of the epipolar line based on the time series images of a moving monocular camera. The purpose of our research is to present a simple method to calculate the epipolar line with sufficient accuracy for matching between the time series images. In this paper we propose an useful method which allows as to calculate the epipolar line by using the compound sensor that combined a monocular camera and an inertial sensor. The inertial sensor gives us the rotation angles and the accelerated velocity vectors of the camera. First, a pair of camera-images is changed into the relation of parallel stereo vision, by the use of the rotation angles. And the baseline between the parallel images is determined by using the rotation data and the acceleration data. Next, the epipolar line of a targeted point is obtained. Moreover, we show the validity of this method which used the combined sensor that can be applied even when a camera carries out movement of 6 degrees of freedom, by the experiment using the camera images and the inertial sensor's data.