In this paper, we propose a multi-modal framework to tackle the SPARK Challenge by classifying satellites using RGB and depth images. Our framework is mainly based on Auto-Encoders (AE)s to embed the two modalities in a common latent space in order to exploit redundant and complementary information between the two types of data.
Ichraf Lahouli, Mahmoud Jarraya, and Gianmarco Aversano, Multimodal Classifier For Space Target Recognition, In Proc. of The 2021 IEEE International Conference on Image Processing, September 2021.
Click here to access the paper.