Abstract:
Identifying the surface topographic changes accurately plays a vital role in the task of planetary exploration. In this study, a lightweight mobile vision transformer-bas...Show MoreMetadata
Abstract:
Identifying the surface topographic changes accurately plays a vital role in the task of planetary exploration. In this study, a lightweight mobile vision transformer-based planetary image change detection (MViT-PCD) was proposed for monitoring dynamic surface changes using bitemporal images. The mobile vision transformer (MobileViT) was first introduced to make the most of the spatial information available. Subsequently, a multiscale feature differentiation and fusion (MFDF) block was adopted to improve the distinguishability of multilevel contextual information. Moreover, the strategy of information maximization (IM) was integrated to refine the model performance on the heterogeneous dataset. Then, experiments were conducted on the public Martian datasets. Compared with other state-of-the-art (SOTA) methods, the MViT-PCD provides favorable performance, with the highest accuracy of 97.2% and 82.9%, respectively, under the speed of 43.4 frame per second (FPS). Code is available at https://github.com/lynn1023-max/MViTPCD.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)