Performance comparison of 3D correspondence grouping algorithm for 3D plant point clouds
This work addresses the problem of improving 3D plant phenotyping for agricultural monitoring, but it is incremental as it primarily compares and extends existing methods.
The paper compared several 3D correspondence grouping algorithms for plant point clouds, finding that the extended 3D MLESAC method is more efficient and less computationally intense than 3D RANSAC, with performance evaluated using precision and recall metrics on standard benchmarks.
Plant Phenomics can be used to monitor the health and the growth of plants. Computer vision applications like stereo reconstruction, image retrieval, object tracking, and object recognition play an important role in imaging based plant phenotyping. This paper offers a comparative evaluation of some popular 3D correspondence grouping algorithms, motivated by the important role that they can play in tasks such as model creation, plant recognition and identifying plant parts. Another contribution of this paper is the extension of 2D maximum likelihood matching to 3D Maximum Likelihood Estimation Sample Consensus (MLEASAC). MLESAC is efficient and is computationally less intense than 3D random sample consensus (RANSAC). We test these algorithms on 3D point clouds of plants along with two standard benchmarks addressing shape retrieval and point cloud registration scenarios. The performance is evaluated in terms of precision and recall.