ABSTRACT

Registration of TLS data is an important prerequisite to overcome the limitations of occlusion. Most existing registration methods rely on stems to determine the transformation parameters. However, the complexity of the registration problem increases dramatically as the number of stems grows. It is tricky to reduce the stems and determine the valid ones that can provide reliable registration transformation without a knowledge of the two scans. This paper presents an automatic and fast registration of TLS point clouds in forest areas. It reduces stems by selecting from the overlap areas, which are recovered from the mode-based key points that are detected from crowns. The proposed method was tested in a managed forest in Finland, and was compared with the stem-based registration method without reducing stems. The experiments demonstrated that the mean rotation error was 2.09′, and the mean errors in horizontal and vertical translation were 1.13 and 7.21 cm, respectively. Compared with the stem-based method, the proposed method improves the registration efficiency significantly (818 s vs 96 s) and achieves similar results in terms of the mean registration errors (1.94′ for rotation error, 0.83 and 7.38 cm for horizontal and vertical translation error, respectively).

TLS数据的注册是克服遮挡限制的重要前提。现有的大多数注册方法都依赖于词干来确定转换参数。但是，随着词干数量的增加，配准问题的复杂性急剧增加。在不了解两次扫描的情况下，减少茎并确定可以提供可靠配准转换的有效茎是很棘手的。本文介绍了林区中TLS点云的自动快速注册。它通过从重叠区域中进行选择来减少词干，这些重叠区域从从王冠中检测到的基于模式的关键点中恢复。提议的方法在芬兰的人工林中进行了测试，并与基于茎的注册方法进行了比较，但未减少茎。实验表明，平均旋转误差为2.09'，水平和垂直平移的平均误差分别为1.13和7.21 cm。与基于词干的方法相比，该方法显着提高了配准效率（818 s与96 s），并且在平均配准误差（旋转误差为1.94'，水平和垂直平移为0.83和7.38 cm）方面取得了相似的结果错误）。