Learning to Detect Keypoints of Muti-type UAVs with OpenPose Network

Keypoint detection is mainly a single-type target detection. In this paper, we present an approach for multi-type target keypoints detection. To allow for a learning-based approach, we developed large scale-dataset of multiple-type of UAVs and customized the OpenPose network architecture. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. The proposed approach learns from three different (Skylark fixed-wing, the Phantom 4 multi-rotor, and aggregated) UAVs datasets. Furthermore, to evaluate our approach, we conduct an extensive experiment on all three datasets. The results show the effectiveness of the proposed approach with respect to accuracy and dramatically improves the speed compared to other state-of-the-art methods.