While other commercially-available products lack the ability to accurately register complex motions of multiple objects due to their inability to enhance images beyond single-frame based sharpening and de-noising, AUG-H’s unique multi-frame registration and fusion techniques enable multi-frame based image enhancement.
AUG-H utilizes two different phenomena for multi-frame based object enhancement, which are complementary sampling and redundant sampling. For each case, accurate inter-frame motion estimation and data fusion is the key.
In the presence of camera/object motion samples of different frames of video provide complementary information. This information can be used to improve object resolution far beyond hardware capability, using a procedure known as super-resolution, and to add increasing number of constraints to achieve unprecedented de-blurring capability.
Perfect redundant video frames are obtained when there is no camera/object motion. If camera/object motion is accurately computed, redundant samples can also be estimated by interpolating complementary samples. Redundant samples can help in improving denoising and scintillation effect removal performance.
Fig. 1: Super-resolution example
Fig. 2: Deblurring example
Fig. 3: Scintillation effect removal example