System and method for spatio video image enhancement
A method for improving quality of low light video images including: receiving a current video frame; temporally enhancing it by applying a first weight matrix including higher weight factors for stationary regions and lower weight factors for moving regions to the received frame and a reference frame to generate an enhanced temporal video frame; spatially enhancing the enhanced temporal video frame by applying a second weight matrix including higher weight factors for stationary regions and lower weight factors for moving regions to generate an enhanced spatial video frame; and motion enhancing the enhanced temporal video frame by extracting matched rigid moving objects in a previous or future frame and processing each of the extracted matched rigid moving objects with a corresponding rigid object in the enhanced temporal or spatial or raw current video frame.
1. A method for improving quality of low light video images, the method comprising:
receiving a current video frame;
generating a reference video frame from the received current video frame, the reference frame including smooth image regions and non-smooth image regions;
computing a likelihood metric to determine the likelihood of a pixel to correspond to smooth image regions and non-smooth image regions in the received current video frame by comparing the generated reference frame and the received current video frame;
computing a weight matrix from the received current video frame and the generated reference frame to minimize edge blur in non-smooth image regions, wherein the weight matrix includes higher weight factors for the smooth image regions and lower weight factors for the non-smooth image regions, in the received current video frame; and
calculating a spatial video frame by applying the weight matrix with higher and lower weight factors to the received current video frame and the generated reference frame.
2. The method of claim 1 , wherein generating a reference video frame further comprises low-pass filtering the current video frame.
3. The method of claim 1 , wherein computing a likelihood metric further comprises finding the difference between the current video frame and the reference frame.
4. The method of claim 3 , wherein computing a weight matrix further comprises finding an inverse of the likelihood metric.
5. The method of claim 1 , wherein calculating a spatial video frame further comprises weighted averaging the current video frame and the reference frame by using the weight matrix.