Background segmentation is a process in which an algorithm removes the static background from an image. This allows only a changing section of the image. This process is important for motion detection or object tracking. In this article, an approach is proposed to compare several existing algorithms for background segmentation under severe weather conditions. Three weather conditions were tested: falling snow, rain and a sunny windy day. The test algorithms were executed on a test video containing frames collected by a dedicated Raspberry Pi camera. The frames used in the tests included cars, bicycles, motorcycles, people, and trees. Preliminary results from these tests show interesting differences in detail detection and detection noise.