作者:
关键词:
摘要: Abstract. In crop production systems, weed management is vitally important. But both manual weeding and herbicide-based controlling are problematic due to concerns in cost, operator health, emergence of herbicide-resistant species, environment impact. Automated robotic offers a possibility weeds precise fashion, particularly for growing near crops or within rows. However, identification localization plants have not yet been fully automated. The goal this reported project develop high-throughput plant recognition algorithm by fusing 2D color textural data with 3D point cloud data. Plant morphological models were developed applied against different species at growth stages.