Using Optical Flow under Bird’s-Eye View Transform to Estimate the Height of Objects around a Vehicle

Abstract:

The paper proposed a new method that can real-time estimates the height of objects with a single camera from a bird’s–eye view. Generally, it is impossible to obtain 3-D information, like the depth of objects, with a single lens camera without the additional information, such as the height and the tilt angle of the camera, are known in advance [1]. The disparity map of binocular cameras is usually employed to estimate depth. It is not suitable for vehicles to estimate the height (similar to depth estimating from a planar view) of objects from a bird’s-eye view due to the difficulties of installing and corresponding. Therefore, the optical flow to estimate the height of the object with one camera is proposed. There are two features under a dynamic bird’s–eye view of image. First, the optical flow value is proportional to the height of the object. Second, there is no perspective effect in each layer height of an image plane. Several experimental results are included to show the proposed method is feasible.

• Periodical: Applied Mechanics and Materials (Volumes 130-134)
• Pages: 1839-1845
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.130-134.1839
• Online since: October 2011
• Authors: Fung Chan Lei, Chin Yi He, Rong Ching Lo
• Keywords: Bird’s-Eye View, Camera Calibration, Estimate Height, Optical Flow

References

[1] I. Kisp´al and E. Jeges. Human height estimation using a calibrated camera. In Proc. CVPR, (2008).

[2] J. Salvi, J. Pagès, and J. Batlle, Pattern codification strategies in structured light systems, presented at Pattern Recognition, 2004, pp.827-849.

DOI: 10.1016/j.patcog.2003.10.002

[3] D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1/2/3): 7-42, April-June (2002).

DOI: 10.1109/smbv.2001.988771

[4] Zhang, Z., A flexible new technique for camera calibration, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp.1330-1334, (2000).

DOI: 10.1109/34.888718

[5] Yi-fu Chen, A surrounding bird-view monitor system with image refinement for parking assistance, National Central University for the Degree of Master, July (2009).

[6] Horn, B.K.P. and Schunck, B.G., Determining Optical Flow, Institute Of Technology Massachusetts, SUA, A.I. Memo, No. 572(1980).

[7] H.A. Mallot, H.H. Bülthoff, J.J. Little and S. Bohrer, Inverse perspective mapping simplifies optical flow computation and obstacle detection, Biological Cybernetics 64 (1991), p.177–185.

DOI: 10.1007/bf00201978