Real Time Video Analysis using Smart Phone Camera for Stroboscopic Image

TL;DR

This paper presents a real-time method for creating stroboscopic images from video captured by smartphones, enabling motion analysis without high-end equipment.

Contribution

It introduces a novel foreground segmentation and background subtraction technique optimized for smartphone cameras to generate stroboscopic images.

Findings

Effective foreground segmentation from smartphone video

Accurate modeling of dynamic background changes

Potential to replace traditional stroboscopic systems

Abstract

Motion capturing and there by segmentation of the motion of any moving object from a sequence of continuous images or a video is not an exceptional task in computer vision area. Smart-phone camera application is an added integration for the development of such tasks and it also provides for a smooth testing. A new approach has been proposed for segmenting out the foreground moving object from the background and then masking the sequential motion with the static background which is commonly known as stroboscopic image. In this paper the whole process of the stroboscopic image construction technique has been clearly described along with some necessary constraints which is due to the traditional problem of estimating and modeling dynamic background changes. The background subtraction technique has been properly estimated here and number of sequential motion have also been calculated with the correlation between the motion of the object and its time of occurrence. This can be a very effective application that can replace the traditional stroboscopic system using high end SLR cameras, tripod stand, shutter speed control and position etc.