Sensor assisted Motion Estimation

Linear displacement estimation of a mobile device is useful in various real time applications, such as Global Motion Estimation (GME) in video encoding, video surveillance etc. Present state of the art techniques perform the global motion estimation using techniques predominantly based on image processing algorithms. These require complex computations and more power consumption. In this paper a novel approach, Sensor assisted Motion Estimation (SaME), to estimate the linear displacement of a mobile device using inbuilt sensors, is proposed. SaME uses inbuilt 3-axis accelerometer to determine the linear displacement along X, Y and Z axes. SaME algorithm is a combination of basic image processing techniques, sensor data and Artificial Intelligence. The Artificial Neural Network (ANN) is used to build the artificial intelligence. ANN is trained to map the sensor data from inbuilt accelerometer to the corresponding displacement data acquired via simple image processing techniques. The resultant model is used to estimate the linear displacement of the mobile device using the sensor data as input. From the results it can be concluded that the inbuilt sensors can be used to arrive at reliable estimates of linear displacement via the proposed method.