Implementation of real time object detection and tracking system with rotating camera: a survey

The task of real time detection and tracking of a moving object in a video stream is quite challenging if camera itself is moving. This paper presents a survey of real time detection and tracking of a known/unknown object in video stream with 360° (azimuth) rotating camera. It also presents a comparative study of various image tracking algorithms. The system described in this paper contains a camera that is connected to an embedded system which is capable of processing an input video stream data. The Embedded system is also having an image processing algorithm which detects an object first and then tracks it as long as it is in the line of sight of the camera. As the object moves, the embedded system rotates the camera which is mounted on a stepper motor according to the path of the moving object. The embedded system also sends data to an end user via a Wi-Fi server so that the end user can monitor the activity of the object of interest. The object can be known (already saved in system memory) or can be unknown (can be defined directly by the end user by selecting a portion of the frame in video stream). The embedded system also saves the video stream in a storage device for playback purpose.