Skip to content

Multimodal Classifier For Space Target Recognition

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.

Releated Posts

IEEE Streaming Workshop / Keynote Announcement

We are delighted to announce Pablo Estrada from Google and Fabian Hueske from Snowflake as the two keynote speakers of our seventh Workshop on Real-time Stream Analytics, Stream Mining, CER/CEP & Stream Data Management in Big Data.
Read More

We Collaborate on the TAUDoS Project

We started a new collaboration with Aix-Marseille University, Montreal University, Nantes University, and St-Etienne on a four-year project called TAUDoS, which focuses on Trustful AI.
Read More