Target-tracking-based ultra-low-bit-rate video coding

In this paper, we present an automated region-of-interest-based video coding system for use in ultra-low-bandwidth applications. Region-of-interest (ROI) coding methodology specifies that targets or ROIs be coded at higher fidelity using a greater number of available bits, while the remainder of the scene or background is coded using fewer bits. This allows the target regions within the scene to be well preserved, while dramatically reducing the number of bits required to code the video sequence, thus reducing the transmission bandwidth and storage requirements. In the proposed system, the ROI contours are specified automatically by a video target detection and tracking algorithm that continuously monitors the incoming video stream for the presence of targets. When targets appear in the scene, the detection/tracking stage feeds the target position and size information to the video compression stage, which applies a greater percentage of available bits to these areas, thereby preserving their appearance relative to the non-target or background portion of the scene. In the proposed system, position information is updated in real time and is efficiently exchanged between the transmitter and receiver. Coding examples are presented for infrared (IR) video sequences to demonstrate the outstanding performance of the proposed system.