In recent years, lots of research have been done in computer vision domain. Video surveillance in real-time scenario, especially for humans, like tracking and behavior analysis is one of the most active research topics in computer vision and artificial intelligence in present situation. The main focus is providing the low-cost and efficient video surveillance system for home application and can have wide scope in other areas such as elevator monitoring and server room monitoring. As the traditional surveillance system requires huge storage capacity and consumes lot of network bandwidth, hence it becomes necessary to provide solution for such design issues. This paper presents the implementation of motion detection algorithm for live camera streaming and thus allows analyzing incoming image stream, and recognizing any movement occurs in the area and if so then triggers video recorder to save the information-contained video clip. © 2018, Springer Nature Singapore Pte Ltd.