SimD3: A Synthetic drone Dataset with Payload and Bird Distractor Modeling for Robust Detection

TL;DR

SimD3 is a comprehensive synthetic drone dataset with realistic distractors and environmental variability, enabling improved training and evaluation of robust drone detection models.

Contribution

This paper introduces SimD3, a novel high-fidelity synthetic dataset modeling payloads and bird distractors, enhancing drone detection robustness and generalization.

Findings

Yolov5m+C3b outperforms baseline models in detection accuracy.

SimD3 improves small-object drone detection in diverse conditions.

Models trained on SimD3 generalize well to real-world benchmarks.

Abstract

Reliable drone detection is challenging due to limited annotated real-world data, large appearance variability, and the presence of visually similar distractors such as birds. To address these challenges, this paper introduces SimD3, a large-scale high-fidelity synthetic dataset designed for robust drone detection in complex aerial environments. Unlike existing synthetic drone datasets, SimD3 explicitly models drones with heterogeneous payloads, incorporates multiple bird species as realistic distractors, and leverages diverse Unreal Engine 5 environments with controlled weather, lighting, and flight trajectories captured using a 360 six-camera rig. Using SimD3, we conduct an extensive experimental evaluation within the YOLOv5 detection framework, including an attention-enhanced variant termed Yolov5m+C3b, where standard bottleneck-based C3 blocks are replaced with C3b modules. Models are evaluated on synthetic data, combined synthetic and real data, and multiple unseen real-world benchmarks to assess robustness and generalization. Experimental results show that SimD3 provides effective supervision for small-object drone detection and that Yolov5m+C3b consistently outperforms the baseline across in-domain and cross-dataset evaluations. These findings highlight the utility of SimD3 for training and benchmarking robust drone detection models under diverse and challenging conditions.