Computer Vision Systems - 12th International Conference, ICVS 2019, Thessaloniki, Greece, September 23-25, 2019, Proceedings
Computer Vision Systems - 12th International Conference, ICVS 2019, Thessaloniki, Greece, September 23-25, 2019, Proceedings
复制标题
计算机视觉系统 - 第十二届国际会议，ICVS 2019，希腊塞萨洛尼基，2019 年 9 月 23-25 日，会议记录
DOI：
10.1007/978-3-030-34995-0_35
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Bauer D
中科院分区：
文献类型：
--
作者：
Bauer D
可靠的物体姿态估计是机器人视觉系统的一个组成部分，因为它使机器人能够操纵他们的周围环境。存在从RGB和RGB-D图像估计对象姿态的强大方法，从而产生每个对象的一组假设。然而，从一组可能的组合中确定最佳假设是一项具有挑战性的任务。我们应用MCTS这个问题，在有限的时间内找到一个最佳的解决方案，并建议在树搜索过程中出现的等价对象组合之间共享信息，所谓的换位。因此，需要考虑的组合的数量减少，并且搜索在单个统计中收集关于这些换位的信息。我们评估所得到的验证方法的YCB-VIDEO数据集和显示更可靠的检测的最佳解决方案相比，最先进的。此外，我们报告了一个显着的速度相比，以前的基于MCTS的方法进行对象姿态验证。
Reliable object pose estimation is an integral part of robotic vision systems as it enables robots to manipulate their surroundings. Powerful methods exist that estimate object poses from RGB and RGB-D images, yielding a set of hypotheses per object. However, determining the best hypotheses from the set of possible combinations is a challenging task. We apply MCTS to this problem to find an optimal solution in limited time and propose to share information between equivalent object combinations that emerge during the tree search, so-called transpositions. Thereby, the number of combinations that need to be considered is reduced and the search gathers information on these transpositions in a single statistic. We evaluate the resulting verification method on the YCB-VIDEO dataset and show more reliable detection of the best solution as compared to state of the art. In addition, we report a significant speed-up compared to previous MCTS-based methods for object pose verification.