3-D Modeling of an Outdoor Scene from Multiple Image Sequences by Estimating Camera Motion Parameters
Three-dimensional (3-D) models of outdoor scenes can be widely used in a number of fields such as object recognition, navigation, scenic simulation, and mixed reality. Such models are often made manually with high costs, so that automatic 3-D reconstruction has been widely investigated. In related works, a dense 3-D model is generated by using a stereo method. However, such approaches cannot use several hundred images together for dense depth estimation of large constructs and urban environments because it is difficult to accurately calibrate a large number of cameras. This paper proposes a novel dense 3-D reconstruction method that uses multiple image sequences. First, our method estimates extrinsic camera parameters of each image sequence, and then reconstructs a dense 3-D model of a scene using an extended multi-baseline stereo and voxel voting techniques.
- 1.N. Yokoya, T. Shakunaga and M. Kanbara: “Passive Range Sensing Techniques: Depth from Images,” IEICE Trans. Inf. and Syst., Vol. E82-D, No. 3, pp. 523–533, 1999.Google Scholar
- 6.T. Sato, M. Kanbara, H. Takemura and N. Yokoya: “3-D Reconstruction from a Monocular Image Sequence by Tracking Markers and Natural Features,” Proc. 14th Int. Conf. on Vision Interface, pp. 157–164, 2001.Google Scholar
- 9.R. Y. Tsai: “An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision,” Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 364–374, 1986.Google Scholar
- 10.S. Ikeda, T. Sato and N. Yokoya: “An Calibration Method for an Omnidirectional Multi-camera System,” Proc. SPIE, Vol. 5006, 2003.Google Scholar