Frame Rate Up-Conversion Algorithm Based on Infrared Image

With the more and more common use of infrared video in life, people have higher and higher requirements for infrared imaging frame rates. Better quality infrared images provide a better basis for subsequent target recognition, video compression and decompression operations. Therefore, it is of great significance to effectively obtain infrared high frame rate images and improve the quality of infrared images. As an effective means of video conversion, frame rate enhancement technology has become a research hotspot in the direction of computer vision. However, the existing video interpolation methods based on infrared images are all implemented based on block matching, which cannot well approximate the complex moving real world. In order to solve these problems, an optical flow method based on pixel motion compensation is proposed for infrared video interpolation. The second interpolation method can make better use of the motion information in the video. In the end, an optical flow optimization network is used for optimization, which can better optimize the artifacts in the optical flow estimation and improve the final image quality. Experiments show that our method has a better effect than existing methods on models on various infrared video data sets, and has lower computational complexity.