A Robust Background Registration Method Based on Multi Match Points

The efficiency and accuracy of conventional background-registration methods usually depend on reliability of matching points, leading to the problem of instability. In this paper, we present a robust background-registration algorithm. Based on the principle of statistical majority, our algorithm establishes a new background-registration model that utilizes more points to implement the registration. Furthermore, generalized inverse transform theory is used by our model to convert registration to a full-rank linear problem so as to solve the parameters of mobility scenario. Consequently, more stable background-registration performance is achieved.