Impact of Architectural Scaling in YOLO11 Models on Object Detection Accuracy and Inference Performance in UAV Systems
Maksym Shepliakov, Andriy Lozynskyy · Energy Engineering and Control Systems · 2026
This paper investigates the impact of architectural scaling in YOLO-family neural object detectors on object detection performance in unmanned aerial vehicle (UAV) systems under CPU-only inference conditions without hardware acceleration. Standard nano and small model configurations are analyzed, along with an intermediate model obtained through controlled width scaling of the network. Experimental evaluation is conducted on an embedded Raspberry Pi 5 platform under fixed hardware and software conditions using ONNX Runtime, ensuring fair comparability of the models. Performance is assessed using detection accuracy metrics ([email protected]; [email protected]:0.95), average inference latency and the coefficient of variation of latency, as well as an integrated efficiency metric. The results demonstrate that increasing model complexity leads to a nonlinear improvement in detection accuracy, accompanied by a growth in inference latency, which limits the applicability of such models in real-time scenarios.