Scholarlink

<p>The acquisition of phenotype parameters with computer vision is crucial for smart breeding, cultivation management, and automated harvesting. However, occlusion in <i>Oudemansiella raphanipies</i> hinders accurate segmentation and phenotype information collection. This study proposes ORP-extractor (<i>Oudemansiella raphanipies</i> phenotype extractor), a deep learning model designed to address the above-mentioned challenges. Initially, to realize instance segmentation of individual <i>Oudemansiella raphanipies</i> and acquired its complete shape<i>,</i> a newly improved Mask R-CNN networks (named OR R-CNN) was designed, which integrated the advantages of the Cross-Criss attention module and PointNet. Furthermore, with the shape prior of the cap-stem contour, an automatic measurement-position search method was proposed to assist in phenotype parameter extraction. Finally, four phenotypic parameters (cap diameter, cap height, stem diameter and stem length) were calculated combining the measurement positions with depth image. In addition, to increase the accuracy of annotation and save cost, a novel occlusion image synthesis strategy for ORP-extractor training also introduced. The segmentation results showed an AP of 86.58%, while the size estimation results showed that the ORP-extractor achieved a MAPE of 4%, 3%, 7% and 4% for cap diameter, cap height, stem diameter, and stem length, respectively. The advantages of the present methodology are its robustness for segmenting and estimating the size of occluded <i>Oudemansiella raphanipies</i>, which can be used to help accelerate development of intelligent breeding, optimized management and robotic harvesting of <i>Oudemansiella raphanipies</i>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ORP-extractor: A novel pipeline for extracting the phenotypic parameters of growing Oudemansiella raphanipies based on synthetic dataset

  • 期刊论文

  • 发表日期：

    2025年6月9日

查看全文
  • Hua Yin,
  • Lisi Wu,
  • Quan Wei,
  • Chaohui Guo,
  • Minghui Chen,
  • Long Xue,
  • Chunqin Chen,
  • Yinglong Wang

摘要

The acquisition of phenotype parameters with computer vision is crucial for smart breeding, cultivation management, and automated harvesting. However, occlusion in Oudemansiella raphanipies hinders accurate segmentation and phenotype information collection. This study proposes ORP-extractor (Oudemansiella raphanipies phenotype extractor), a deep learning model designed to address the above-mentioned challenges. Initially, to realize instance segmentation of individual Oudemansiella raphanipies and acquired its complete shape, a newly improved Mask R-CNN networks (named OR R-CNN) was designed, which integrated the advantages of the Cross-Criss attention module and PointNet. Furthermore, with the shape prior of the cap-stem contour, an automatic measurement-position search method was proposed to assist in phenotype parameter extraction. Finally, four phenotypic parameters (cap diameter, cap height, stem diameter and stem length) were calculated combining the measurement positions with depth image. In addition, to increase the accuracy of annotation and save cost, a novel occlusion image synthesis strategy for ORP-extractor training also introduced. The segmentation results showed an AP of 86.58%, while the size estimation results showed that the ORP-extractor achieved a MAPE of 4%, 3%, 7% and 4% for cap diameter, cap height, stem diameter, and stem length, respectively. The advantages of the present methodology are its robustness for segmenting and estimating the size of occluded Oudemansiella raphanipies, which can be used to help accelerate development of intelligent breeding, optimized management and robotic harvesting of Oudemansiella raphanipies.