Exploring 2D projection and 3D spatial information for aircraft 6D pose

The 6D pose estimation is important for the safe take-off and landing of the aircraft using a single RGB image. Due to the large scene and large depth, the exiting pose estimation methods have unstratified performance on the accuracy. To achieve precise 6D pose estimation of the aircraft, an end-to-end method using an RGB image is proposed. In the proposed method, the 2D and 3D information of the keypoints of the aircraft is used as the intermediate supervision, and 6D pose information of the aircraft in this intermediate information will be explored. Specifically, an off-the-shelf object detector is utilized to detect the Region of the Interest (RoI) of the aircraft to eliminate background distractions. The 2D projection and 3D spatial information of the pre-designed keypoints of the aircraft is predicted by the keypoint coordinate estimator (KpNet). The proposed method is trained in an end-to-end fashion. In addition, to deal with the lack of the related datasets, this paper builds the Aircraft 6D Pose dataset to train and test, which captures the take-off and landing process of three types of aircraft from 11 views. Compared with the latest Wide-Depth-Range method on this dataset, our proposed method improves the average 3D distance of model points metric (ADD) and 5° and 5 m metric by 86.8% and 30.1%, respectively. Furthermore, the proposed method gets 9.30 ms, 61.0% faster than YOLO6D with 23.86 ms.