Video Snow Removal Based on Self-Adaptation Snow Detection and Patch-Based Gaussian Mixture Model

Abstract

Video desnowing has become a challenging research topic in computer vision in recent years. Existing methods cannot remove most of the snow in heavy snow scenes and will cause the deformation of moving objects when used for snowy videos that include moving objects. These methods have poor generalizability, exhibiting poor performance when removing snow from videos with different resolutions. In this paper, we propose a new video snow removal method based on self-adaptation snow detection and a patch-based Gaussian mixture model (VSRSG). First, an optical flow estimation method and a support vector machine (SVM) are used to detect snowflakes, and a self-adaptation threshold process is used to remove dense snowflakes in the snowflake detection map to obtain a sparse snowflake detection map. Then, a patch-based Gaussian mixture model (PBGMM), which can remove moving objects and both sparse and dense snowflakes from videos and restore a clear video background, is applied for background modeling. A Markov random field (MRF) and self-adaptation threshold processing are used to extract sparse snowflakes and moving objects and combine them with the background to form an input video without dense snowflakes. Finally, a similar block matching method is employed to fill in the detected snowflake pixels with the information from adjacent frames to remove the sparse snowflakes in the near range. This method can also remove snowflakes in front of moving objects. Experiments show that the proposed method can simultaneously remove sparse snowflakes, dense snowflakes and snowflakes in front of moving objects and outperforms other state-of-the-art methods.INDEX TERMS Video desnowing, self-adaptation snowflake detection, patch-based Gaussian mixture model, low-rank background modeling, moving foreground detection.

Fabric Defect Detection Based on Machine Learning

“…The patches including defects are extracted from the defective fabric image by neighborhood growth with similar features [19].…”

U2-Net_S Fire Smoke Segmentation Based on Multiscale Edge Fusion Convolutional Encoder and Edge Supervision

“…The segmentation of the main body and edge contours of smoke is too rough. It is worth noting that there has been a trend in traditional smoke segmentation methods to use significant object detection to segment smoke [27] , and researchers are also starting to pay more attention to the overall integrity and local details of Liu Zhiying et al [28] improved the Deeplab v3+ network model by improving its ASPP structure through heterogeneous receptive field fusion, and incorporating a channel attention module into its architecture. Salman Khan et al [30] incorporated a designed multi-scale atrous separable convolutional encoder and an improved decoder into the Deeplab v3+ model, and added a pixel-wise classifier to improve the model.…”

Comparative Monte Carlo Analysis of Background Estimation Algorithms for Unmanned Aerial Vehicle Detection

“…The algorithms used in this article are listed in Table 1, and they are part of the OpenCV library. These algorithms are often used in various applications, but new ones are constantly being developed [18][19][20][21][22][23]. This is due to many reasons.…”