STEG-Net: Spatiotemporal Edge Guidance Network for Video Salient Object Detection

摘要

Over the past decades, video salient object detection (VSOD) has achieved rapid development. However, the effect of edge information on spatial and temporal features extraction has not been explored. The method STEG-Net is proposed to solve the problem, we use the extracted edge information to guide the extraction of spatial and temporal features simultaneously. We combine deep texture information with shallow edge information, which can not only retain the edge of the object but also enhance the global information, leading to the more accurate location of the object. At the same time, the shallow edge information and the deep texture information are complementary. As a result, edge information and salient features could advance each other while extracting features. Finally, we evaluate the 16 state-of-the-art VSOD methods on ViSal and FBMS data sets. At the same time we also evaluate the 13 state-of-the-art VSOD methods on UVSD and MCL data sets. The experiment results indicate that the proposed method outperforms the state-of-the-art approaches.