2019/09/02 by Shiva Azimi, Azimi, Shiva, Tapan Kumar Gandhi +1
Agricultural and Biological Sciences · Environmental Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Remote Sensing and LiDAR Applications #Remote Sensing in Agriculture #Smart Agriculture and AI
paper · pdf · doi:10.48550/arxiv.1909.00866
openalex publication_date 2019/09/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Plant Phenomics can be used to monitor the health and the growth of plants.\nComputer vision applications like stereo reconstruction, image retrieval,\nobject tracking, and object recognition play an important role in imaging based\nplant phenotyping. This paper offers a comparative evaluation of some popular\n3D correspondence grouping algorithms, motivated by the important role that\nthey can play in tasks such as model creation, plant recognition and\nidentifying plant parts. Another contribution of this paper is the extension of\n2D maximum likelihood matching to 3D Maximum Likelihood Estimation Sample\nConsensus (MLEASAC). MLESAC is efficient and is computationally less intense\nthan 3D random sample consensus (RANSAC). We test these algorithms on 3D point\nclouds of plants along with two standard benchmarks addressing shape retrieval\nand point cloud registration scenarios. The performance is evaluated in terms\nof precision and recall.\n