No abstract

No abstract

In this paper, an onboard vision-based system for the autonomous landing of a low-cost quadrotor is presented. A novel landing pad with different optical markers sizes is carefully designed to be robustly recognized at different distances. To provide reliable pose information in a GPS (Global Positioning System)-denied environment, a vision algorithm for real-time landing pad recognition and pose estimation is implemented. The dynamic model of the quadrotor is established and a system scheme for autonomous landing control is presented. A series of autonomous flights have been successfully performed, and a video of the experiment is available online. The efficiency and accuracy of the presented vision-based system is demonstrated by using its position and attitude estimates as control inputs for the autonomous landing of a self-customized quadrotor.

Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a labelscarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to reduce the distribution mismatch, however, access to the source domain samples may not always be feasible in the real world applications due to different problems (e.g., storage, transmission, and privacy issues). In this work, we deal with the source data-free unsupervised domain adaptation problem, and propose a novel approach referred to as Virtual Domain Modeling (VDM-DA). The virtual domain acts as a bridge between the source and target domains. On one hand, we generate virtual domain samples based on an approximated Gaussian Mixture Model (GMM) in the feature space with the pre-trained source model, such that the virtual domain maintains a similar distribution with the source domain without accessing to the original source data. On the other hand, we also design an effective distribution alignment method to reduce the distribution divergence between the virtual domain and the target domain by gradually improving the compactness of the target domain distribution through model learning.In this way, we successfully achieve the goal of distribution alignment between the source and target domains by training deep networks without accessing to the source domain data. We conduct extensive experiments on benchmark datasets for both 2D image-based and 3D point cloudbased cross-domain object recognition tasks, where the proposed method referred to Domain Adaptation with Virtual Domain Modeling (VDM-DA) achieves the state-of-the-art performances on all datasets.

No abstract