Visual surveillance transformer

In a visual surveillance system, even the same object should exhibit different detection results depending on the surrounding environment configuration. To this end, the model for visual surveillance needs to detect an object by understanding the state of the object according to the environment on the image. In this study, for such visual surveillance, an object segmentation model applied with a transformer structure suitable for image processing was used to divide objects inside the image into foreground and background. A modified attention structure was presented for the corresponding transformer structure, and the results of object segmentation models according to the type of input data were compared.