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" Proceedings - 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2025, Tucson (Arizona), USA, pp. 339 -348 , 28 February - 4 March 2025, 2025 DOI: 10.1109/WACVW65960.2025.00044

 not available

Paper download:

• Author version:
• DOI: 10.1109/WACVW65960.2025.00044