Onboard Computer Vision for Tactical Drones

Boosting onboard autonomy by compressing EdgeTAM for segmentation and object tracking under constrained compute budgets.

Multiverse Computing worked with a European defense technology organization to further optimize EdgeTAM for onboard computer vision on tactical drone platforms. Building on an earlier compression phase focused on the Mask Decoder and Memory Attention modules, the second phase expanded the optimization scope to include the Vision Encoder and Memory Encoder/Fuser, enabling a deeper reduction in model size while preserving most of the model's segmentation quality.

The Challenge

The client required a deeper compression of EdgeTAM to bring real-time segmentation and object tracking onto tactical UAV platforms with tight memory and compute budgets. A previous compression phase had targeted the Mask Decoder and Memory Attention modules. The challenge for this second phase was to expand the optimization scope to the heavier Vision Encoder and Memory Encoder/Fuser, while preserving most of the model's segmentation quality and improving inference performance on CPU.

Our Solution

Read the full story

Add your email to unlock all the content

By continuing, you agree to Multiverse Computing's Terms and Privacy Policy