Cost-effective reliability enhancement for video stitching applications based on error-tolerance

Abstract

Image (video) stitching technology has been widely used in real-time video applications. In this paper, for the first time, we address design and implementation of a reliable image (video frame) stitching system and focus on its video applications. In particular, we show that by well exploiting the inherent error-tolerability of the image stitching process, a cost-effective reliability enhancement solution can be enabled. For input images (video frames), the proposed system carries out a unique no-reference error detection process where the acceptability of potential errors in input image data can be tested. Particularly, no golden data are required, which greatly facilitates the implementation of an on-line testing process. Based on the testing results, a simple yet effective repair process is enabled for transforming unacceptable stitching results into acceptable ones. Our experimental results show that acceptability testing accuracy of our error detection process achieves 98.4 %. The experimental results on 864,000 various test cases also show that 80 % of the unacceptably erroneous stitched video frames can be successfully repaired, thereby achieving 5× lifetime extension. In addition, when compared to the typical ECC (Error Correcting Code) or TMR (Triple Modular Redundancy) reliability improvement methods, our system not only requires much less hardware cost, but also incurs only ignorable performance overhead. These lead to almost no loss in the achievable FPS (Frame Per Second), and thus real-time video stitching can still be achieved but with high reliability.