Real-time motion amplification on mobile devices
This work addresses the problem of real-time motion detection and amplification for mobile users in fields like engineering and medicine, but it is incremental as it builds on existing motion enhancement techniques.
The paper introduced a motion amplification algorithm called MEMAD for real-time use on mobile devices, enabling the amplification of small or subtle motions in video streams, and demonstrated its implementation in an Android app with examples from engineering, biological, and medical sciences.
A simple motion amplification algorithm suitable for real-time applications on mobile devices, including smartphones, is presented. It is based on motion enhancement by moving average differencing (MEMAD), a temporal high-pass filter for video streams. MEMAD can amplify small moving objects or subtle motion in larger objects. It is computationally sufficiently simple to be implemented in real time on smartphones. In the specific implementation as an Android phone app, MEMAD is demonstrated on examples chosen such as to motivate applications in the engineering, biological, and medical sciences.