Motion-guided small MAV detection in complex and non-planar scenes

In recent years, there has been a growing interest in the visual detection of micro aerial vehicles (MAVs) due to its importance in numerous applications. However, the existing methods based on either appearance or motion features encounter difficulties when the background is complex or the MAV is too small. In this paper, we propose a novel motion-guided MAV detector that can accurately identify small MAVs in complex and non-planar scenes. This detector first exploits a motion feature enhancement module to capture the motion features of small MAVs. Then it uses multi-object tracking and trajectory filtering to eliminate false positives caused by motion parallax . Finally, an appearance-based classifier and an appearance-based detector that operates on the cropped regions are used to achieve precise detection results. Our proposed method can effectively and efficiently detect extremely small MAVs from dynamic and complex backgrounds because it aggregates pixel-level motion features and eliminates false positives based on the motion and appearance features of MAVs. Experiments on the ARD-MAV dataset demonstrate that the proposed method could achieve high performance in small MAV detection under challenging conditions and outperform other state-of-the-art methods across various metrics. • We proposed a simple but effective method to aggregate pixel-level motion features by frame alignment and multi-frame difference. Compared with existing methods, our proposed method can effectively extract motion features of extremely small MAVs from complex backgrounds. • The false positives generated by motion parallax can be effectively removed by multi-object tracking, trajectory filtering, and appearance-based classification. This is because our proposed method can model the spatial and temporal features of MAVs that are different from false positives. • To validate the effectiveness of our method, we have conducted extensive experiments on the ARD- MAV dataset. The experimental results show that our proposed detector can effectively detect small MAVs under complex and non-planar scenes and outperforms the state-of-the-art algorithms on various metrics.