Coding artifacts in video codecs can be reduced using several spatial in-loop filters that are part of the emerging video coding standard High Efficiency Video Coding (HEVC). According to this invention a method for processing the pixel value of at least one image pixel contained in a current frame of a video sequence is provided that constructs an individual motion trajectory comprising motion-shifted versions of the at least one image pixel over a plurality of preceding and/or subsequent frames, and afterwards processing the pixel value based on the individual motion trajectory. The method chooses at least one image pixel of the current frame as a start pixel of the individual motion trajectory, and adds the motion-shifted versions of the at least one image pixel of preceding and/or subsequent frames to the individual motion trajectory.
This solution may have merit if the algorithm could be incorporated with the video surveillance, autonomous transport, or defense industry. Here the level of attractiveness would largely dependent on total lines-of-code, performance, and the amount of critical computing resources needed to implement the algorithm. Real-world demonstration in commercial and industrial grade equipment could elevate the profile of this patent. Applications: While ML/AI techniques could ultimately obsolete this patent. There is a market window where this patent could be as software upgrade within existing systems. Maybe a niche opportunity, is to use the technique to help teach and improve the performance of rival MI/AL solutions. Companies: Video Surveillance and AI/Machine Learning companies.
Thank you, Conroy!!!!