 |
    |
Real-Time Stereo Vision: Making More Out of Dynamic Programming
Jan Salmen1, Marc Schlipsing1, Johann Edelbrunner1, Stefan Hegemann2, and Stefan Lüke2
1Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany
Jan.Salmen@neuroinformatik.rub.de
Marc.Schlipsing@neuroinformatik.rub.de
Hannes.Edelbrunner@neuroinformatik.rub.de
2Continental AG, Division Chassis & Safety, Germany
stefan.hegemann@continental-corporation.com
stefan.lueke@continental-corporation.com
Abstract. Dynamic Programming (DP) is a popular and efficient method for calculating disparity maps from stereo images. It allows for meeting real-time constraints even on low-cost hardware. Therefore, it is frequently used in real-world applications, although more accurate algorithms exist. We present a refined DP stereo processing algorithm which is based on a standard implementation. However it is more flexible and shows increased performance. In particular, we introduce the idea of multi-path backtracking to exploit the information gained from DP more effectively. We show how to automatically tune all parameters of our approach offline by an evolutionary algorithm. The performance was assessed on benchmark data. The number of incorrect disparities was reduced by 40 % compared to the DP reference implementation while the overall complexity increased only slightly.
LNCS 5702, p. 1096 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2009