Iterated Training Algorithm for Surveillance Video Applications

Motion detection is done for videos with various methodologies. Especially in surveillance video applications lot of techniques are implied in the past for the detection of motion with the color mapping of the object. There lies a problem for these sorts of applications in such a way that, it will map the moving object as a single entity. But in sensitive applications like satellite imaging systems, cancer cell or medical imaging systems, the sub objects movement is also taken into account for efficient decision making. So a new methodology is developed in this project for the multiple objects and sub objects movement in sensitive video applications. A methodology was developed for static images by Fellenszwalb et al for multiple object detection. This methodology is implied for dynamic video and tested for medical imaging and satellite imaging videos obtained from various sources of the internet. The system is developed asa real time solution for the developed problem statement.