This paper proposed a reliable method for estimating the neck tilting angle while walking using a 3-axis accelerometer. Conventionally tilting angle is estimated by observing the gravitational force that applies on the sensor in static pose. However, while walking the external acceleration of the movement might heavily affect the estimation result. Therefore, we proposed a simple method based on human gait characteristics and step detection to eliminate the external forces in the accelerometer output. The experiment was done with five persons walking in a treadmill with different speeds under the observation of a camera system. The result showed that the proposed method provided an accurate estimation compared with conventional method of direct estimation.