Optimizing YOLOv11s for Precision Dashboard Detection in UAV-Based Inspection Tasks

With the rapid development of drone technology, UAV-based inspection tasks have become increasingly popular in various fields. However, the accuracy and efficiency of dashboard feature detection in these inspections remain a significant challenge, especially in complex environments with varying conditions. To address this challenge, this paper proposes an enhanced object detection algorithm based on the YOLOv11s model, incorporating the ADNet and SEAM attention mechanisms. The YOLOv11s model serves as the backbone for real-time detection of dashboard features, while the integration of ADNet and SEAM attention mechanisms boosts the model's feature representation and sensitivity. This improvement results in enhanced accuracy, particularly in complex and dynamic environments. Experimental results demonstrate that the proposed algorithm outperforms existing methods in terms of detection accuracy and real-time performance, significantly enhancing dashboard feature recognition and providing stronger support for UAV autonomous inspection systems. The findings highlight the potential of this approach in improving the overall effectiveness of UAV inspections.