Abstract

In view of the traditional three-frame difference method that will produce noise when detecting moving targets, and the edge information is not complete, the Gaussian filtering algorithm is optimized. The traditional Gaussian filtering has a good effect on image smoothing, but its edge information will also be affected. The smooth, optimized algorithm can well remove the noise through two convolutions, and can also well retain the edge information, and can well retain the detected target information. Through experimental analysis, the optimized algorithm can well meet the processing of moving target images in complex backgrounds, and has high real-time performance and strong robustness.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call