Real-time image de-blurring and image processing for a robotic vision system

This paper proposes a method for real-time de-blurring of images captured by a robotic system. De-blurring is achieved by combining a dynamics-based approach and parallel computing. Existing methods have successfully restored a blurry image but were not suitable for real-time applications. The dynamics-based method with parallel programming in the FPGA is used to estimate the PSF during the camera exposure window. The deconvolution process, which involves iterative matrix calculations with millions of pixels, is then performed on the GPU to achieve real-time performance.

The proposed method has been evaluated by using a robotic system which has a total of 32 piezoelectric actuators and one vision sensor. The frame rate of image de-blurring ranges from 20.32 to 40.68 fps and thus real-time performance is achieved. In comparison to existing methods, the proposed method produces the best image quality. The dynamics-based approach is extended to real-time image stitching which is computationally cheap and robust to motion blur. It is demonstrated from image stitching that real-time de-blurring is beneficial for image processing.