Direct Ego-Motion Estimation Using Normal Flows

Ding Yuan, Miao Liu, Hong Zhang

Abstract: In this paper we present a novel method that estimates the motion parameters of a monocular camera, which is under unconstrained movement. Different from the traditional works which tackle the problem by establishing motion correspondences, or by calculating optical flows within the image sequence, the proposed method estimates the motion parameters directly by using the information of spatio-temporal gradient of the image intensity. Hence, our method requires no specific assumptions about the captured scene, like it is smooth almost everywhere or it must contain distinct features etc. We have tested the methods on both synthetic image data and real image sequences. Experimental results show that the developed methods are effective in determining the camera motion parameters.