Applying Deep Learning in Augmented Reality Tracking

作者：Ömer Akgül, H. Ibrahim Penekli, Yakup Genç · 年份：2016 · DOI：10.1109/sitis.2016.17 · 被引用次数：36 · 研究领域：Robotics and Sensor-Based Localization、Video Surveillance and Tracking Methods、Advanced Image and Video Retrieval Techniques

An existing deep learning architecture has been adapted to solve the detection problem in camera-based tracking for augmented reality (AR). A known target, in this case a planar object, is rendered under various viewing conditions including varying orientation, scale, illumination and sensor noise. The resulting corpus is used to train a convolutional neural network to match given patches in an incoming image. The results show comparable or better performance compared to state of art methods. Timing performance of the detector needs improvement but when considered in conjunction with the robust pose estimation process promising results are shown.