Techniques are presented for monocular visual simultaneous localization and mapping (SLAM) based on detecting a translational motion in the movement of the camera using at least one motion sensor, while the camera is performing panoramic SLAM, and initializing a three dimensional map for tracking of finite features. Motion sensors may include one or more sensors, including inertial (gyroscope, accelerometer), magnetic (compass), vision (camera) or any other sensors built into mobile devices.