In this paper, we present a novel algorithm for odometry computation based on ceiling vision. The main contribution in this algorithm is the introduction of principal direction detection that can greatly reduce error accumulation problem present in most visual odometry estimation approaches. The principal direction is defined based on the fact that our ceiling is filled with artificial vertical and horizontal lines and these lines can be used as reference for the current robot's heading direction. The proposed approach can be operated in realtime and it performs well even with camera's disturbance. A moving low-cost RGB-D camera (Kinect), mounted on a robot, is used to continuously acquire point clouds. Iterative Closest Point (ICP) is the common way to estimate current camera position by calculating the translation and rotation to the previous frame. However, its performance suffers from data association problem or it requires pre-alignment information. Unlike ICP, the performance of the proposed approach does not rely on data association knowledge. Using this method, two point clouds are pre-aligned. Hence, we can use ICP to fine-tune the transformation parameters and to minimize registration error. Experimental results demonstrate the performance and stability of the proposed system under disturbance in real-time.