The blessing of Depth Anything: An almost unsupervised approach to crop segmentation with depth-informed pseudo labeling
Authors:
- Songliang CaoSCSongliang Cao
- Binghui XuBXBinghui Xu
- Wei ZhouWZWei Zhou
- Letian ZhouLZLetian Zhou
- Jiafei ZhangJZJiafei Zhang
- Yuhui ZhengYZYuhui Zheng
- Weijuan HuWHWeijuan Hu
- Zhiguo HanZHZhiguo Han
- Hao LuHLHao Lu
Open Access
- 27 February 2025
- journal article
- Published by Elsevier in Plant Phenomics
- Vol. 7 (1)
Abstract
No abstract availableKeywords
Funding Information
- Chinese Academy of Sciences (2024ZY-CGZY-19, XDA24040201)
- Key Technologies Research and Development Program (2023YFF1001502)
- National Key Research and Development Program of China
- National Natural Science Foundation of China (32370435)
This publication has 28 references indexed in Scilit:
- Segmentation algorithm for overlap recognition of seedling lettuce and weeds based on SVM and image blockingComputers and Electronics in Agriculture, 2022
- In-field chlorophyll estimation based on hyperspectral images segmentation and pixel-wise spectra clustering of wheat canopyBiosystems Engineering, 2022
- Deep learning architectures for semantic segmentation and automatic estimation of severity of foliar symptoms caused by diseases or pestsBiosystems Engineering, 2021
- Transfer learning between crop types for semantic segmentation of crops versus weeds in precision agricultureJournal of Field Robotics, 2019
- In-field cotton detection via region-based semantic image segmentationComputers and Electronics in Agriculture, 2016
- Region-based colour modelling for joint crop and maize tassel segmentationBiosystems Engineering, 2016
- Multi-modality imagery database for plant phenotypingMachine Vision and Applications, 2015
- Crop feature extraction from images with probabilistic superpixel Markov random fieldComputers and Electronics in Agriculture, 2015
- Illumination invariant segmentation of vegetation for time series wheat images based on decision tree modelComputers and Electronics in Agriculture, 2013
- Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-leaf stageAgricultural and Forest Meteorology, 2013