A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
This work addresses UAV detection for defense systems, but it is incremental as it builds on existing YOLOv5 with simulation data and fusion techniques.
The paper tackled the problem of limited datasets and small scale for UAV object detection by proposing a comprehensive approach using simulation-based transfer learning and adaptive fusion, achieving a 7.1% performance improvement over the original YOLOv5 model.
Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small scale of UAV. To tackle these problems, a novel comprehensive approach that combines transfer learning based on simulation data and adaptive fusion is proposed. Firstly, the open-source plugin AirSim proposed by Microsoft is used to generate mass realistic simulation data. Secondly, transfer learning is applied to obtain a pre-trained YOLOv5 model on the simulated dataset and fine-tuned model on the real-world dataset. Finally, an adaptive fusion mechanism is proposed to further improve small object detection performance. Experiment results demonstrate the effectiveness of simulation-based transfer learning which leads to a 2.7% performance increase on UAV object detection. Furthermore, with transfer learning and adaptive fusion mechanism, 7.1% improvement is achieved compared to the original YOLO v5 model.