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

TL;DR

TakuNet is a lightweight, energy-efficient CNN designed for real-time aerial image classification on embedded UAV systems, enabling fast emergency response applications with minimal hardware resources.

Contribution

The paper introduces TakuNet, a novel neural network architecture optimized for embedded UAVs, combining depth-wise convolutions and dense connections for high accuracy and efficiency.

Findings

Achieves over 650 fps on Jetson Orin Nano

Maintains near-state-of-the-art accuracy with minimal parameters

Demonstrates real-time performance on resource-constrained devices

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.