Dense optical flow via robust data fusion

Locally optimised differential methods for computing optical flow have the merit of being faster and more reliable under noise when compared to their globally optimised counterparts. However, they produce sparse flow estimates as a result of being unable to deal with local image regions of little texture. They are also particularly inefficient for regions whose change of feature-constancy function is highly nonlinear. In this study, we treat several limitations of the local approach in monochrome images. We present a robust H_∞ data fusion-based framework to propagate flow information from high confidence regions to those suspected of poor quality estimates. The adopted data fusion engine is tolerant towards uncertainty and error inherited in the optical flow computation process. A new integrated confidence measure is also presented to predict the accuracy of the recovered flow across the image enabling the data fusion engine to work as an intelligent filling-in effect, not only when the intensity is problematic but also for other uncertain regions. Results demonstrate the significance of the proposed method.