Random Inspection Tree Algorithm in visual inspection with a realistic sensing model and differential constraints
Random Inspection Tree Algorithm in visual inspection with a realistic sensing model and differential constraints
复制标题
视觉检测中的随机检测树算法，具有真实的传感模型和差分约束
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Petr Váňa
中科院分区：
文献类型：
--
作者：
Premysl Kafka;J. Faigl;Petr Váňa
在本文中，我们考虑了覆盖路径计划中现有的渐近最佳检查计划算法，并具有对标准摄像机的可见性约束。尽管现有方法能够提供全向感测和有限的传感范围的最佳解决方案，但对于仅涵盖少数物体和有限的视野的问题而言，它在计算上非常昂贵。基于对基于采样的策略的分析，我们提出了一种启发式方法，以减少限制性观看Frustum问题的计算要求，这是数码相机的更现实的模型。此外，我们还考虑了一个最小的距离和角度，在这些距离和角度下，向前摄像机捕获了要覆盖的物体，以用所需的细节拍摄对象的快照。
In this paper, we consider existing asymptotically optimal inspection planning algorithm in coverage path planning with realistic visibility constraints of standard cameras. Although the existing approach is able to provide an optimal solution with omnidirectional sensing and limited sensing range, it is prohibitively computationally expensive for problems with only few objects to be covered and limited field of view. Based on the analysis of the utilized sampling-based strategy, we propose a heuristic approach to decrease computational requirements in problems with restricted viewing frustum, which is a more realistic model of a digital camera. In addition, we also consider a minimal distance and angle under which the object to be covered is captured by the forward looking camera to make a snapshot of the object with the required details.