Fast and robust curve skeletonization for real-world elongated objects
This provides a robust solution for agricultural applications like plant structure analysis, though it is incremental as it builds on existing skeletonization methods.
The paper tackles the problem of extracting curve skeletons from noisy 3D elongated objects, such as plants, by presenting an efficient breadth-first search method that automatically detects junctions and spurious segments with one adjustable parameter, achieving run times from hundreds of milliseconds to under four seconds and favorable comparisons to existing algorithms.
We consider the problem of extracting curve skeletons of three-dimensional, elongated objects given a noisy surface, which has applications in agricultural contexts such as extracting the branching structure of plants. We describe an efficient and robust method based on breadth-first search that can determine curve skeletons in these contexts. Our approach is capable of automatically detecting junction points as well as spurious segments and loops. All of that is accomplished with only one user-adjustable parameter. The run time of our method ranges from hundreds of milliseconds to less than four seconds on large, challenging datasets, which makes it appropriate for situations where real-time decision making is needed. Experiments on synthetic models as well as on data from real world objects, some of which were collected in challenging field conditions, show that our approach compares favorably to classical thinning algorithms as well as to recent contributions to the field.