TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios

Abstract: Designing efficient neural networks for embedded devices is a critical challenge, particularly in applications requiring real-time performance, such as aerial imaging with drones and UAVs for emergency responses. In this work, we introduce TakuNet, a novel light-weight architecture which employs techniques such as depth-wise convolutions and an early downsampling stem to reduce computational complexity while maintaining high accuracy. It leverages dense connections for fast convergence during training and uses 16-bit floating-point precision for optimization on embedded hardware accelerators. Experimental evaluation on two public datasets shows that TakuNet achieves near-state-of-the-art accuracy in classifying aerial images of emergency situations, despite its minimal parameter count. Real-world tests on embedded devices, namely Jetson Orin Nano and Raspberry Pi, confirm TakuNet's efficiency, achieving more than 650 fps on the 15W Jetson board, making it suitable for real-time AI processing on resource-constrained platforms and advancing the applicability of drones in emergency scenarios. The code and implementation details are publicly released.

Citation:

Rossi, Daniel; Borghi, Guido; Vezzani, Roberto "TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios" In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Tucson (Arizona), pp. 376 -385 , 28/02/2025, 2025

 @InProceedings{Rossi_2025_WACV,
    author    = {Rossi, Daniel and Borghi, Guido and Vezzani, Roberto},
    title     = {TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios},
    booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops},
    month     = {February},
    year      = {2025},
    pages     = {376-385}
}

Paper download:

• Author version: