Robust and real-time pose tracking for augmented reality on mobile devices
Robust and real-time pose tracking for augmented reality on mobile devices
复制标题
DOI：
10.1007/s11042-017-4575-3
复制
发表时间：
2018-03
影响因子：
3.6
通讯作者：
Xin Yang;Jiabin Guo;Tangli Xue;K. Cheng
中科院分区：
文献类型：
--
作者：
Xin Yang;Jiabin Guo;Tangli Xue;K. Cheng
本文讨论了智能手机和小型无人机等移动的设备上的鲁棒超快姿态跟踪。依赖于视觉分析或惯性感测的现有方法要么计算量太大而无法在移动的平台上实现实时性能，要么不足以鲁棒地解决移动的场景中的独特挑战，包括快速相机运动、移动的相机的长曝光时间，本文提出了一种新的混合跟踪系统，利用上-设备惯性传感器，大大加快视觉特征跟踪过程，提高其鲁棒性。特别是，我们的系统自适应调整每个视频帧的惯性传感器数据的基础上，并应用一个高效的二进制特征匹配方法来跟踪每个调整大小的帧中的对象姿态，精度下降很少。通过基于模型的特征跟踪方法（Hare et al. 2012）定期修订该跟踪结果，以减少累积误差。此外，惯性跟踪方法和融合的解决方案，其结果与特征跟踪结果，以进一步提高鲁棒性和效率。我们首先评估我们的混合系统使用的数据集包括16个视频剪辑与同步惯性传感数据，然后评估其性能在移动的增强现实应用。实验结果表明，我们的方法的上级性能优于最先进的特征跟踪方法（Hare et al. 2012），直接跟踪方法（Engel et al. 2014）和Vuforia SDK（Ibañez和Figueras 2013），并且可以在标准智能手机上以超过40 Hz的频率运行。我们将发布源代码与本文的pubilication。
This paper addresses robust and ultrafast pose tracking on mobile devices, such as smartphones and small drones. Existing methods, relying on either vision analysis or inertial sensing, are either too computational heavy to achieve real-time performance on a mobile platform, or not sufficiently robust to address unique challenges in mobile scenarios, including rapid camera motions, long exposure time of mobile cameras, etc. This paper presents a novel hybrid tracking system which utilizes on-device inertial sensors to greatly accelerate the visual feature tracking process and improve its robustness. In particular, our system adaptively resizes each video frame based on inertial sensor data and applies a highly efficient binary feature matching method to track the object pose in each resized frame with little accuracy degradation. This tracking result is revised periodically by a model-based feature tracking method (Hare et al. 2012) to reduce accumulated errors. Furthermore, an inertial tracking method and a solution of fusing its results with the feature tracking results are employed to further improve the robustness and efficiency. We first evaluate our hybrid system using a dataset consisting of 16 video clips with synchronized inertial sensing data and then assess its performance in a mobile augmented reality application. Experimental results demonstrated our method’s superior performance to a state-of-the-art feature tracking method (Hare et al. 2012), a direct tracking method (Engel et al. 2014) and the Vuforia SDK (Ibañez and Figueras 2013), and can run at more than 40 Hz on a standard smartphone. We will release the source code with the pubilication of this paper.