Literature DB >> 29209408

Panicle-SEG: a robust image segmentation method for rice panicles in the field based on deep learning and superpixel optimization.

Xiong Xiong1, Lingfeng Duan2, Lingbo Liu1, Haifu Tu2, Peng Yang2, Dan Wu2, Guoxing Chen2, Lizhong Xiong2, Wanneng Yang2, Qian Liu1.   

Abstract

BACKGROUND: Rice panicle phenotyping is important in rice breeding, and rice panicle segmentation is the first and key step for image-based panicle phenotyping. Because of the challenge of illumination differentials, panicle shape deformations, rice accession variations, different reproductive stages and the field's complex background, rice panicle segmentation in the field is a very large challenge.
RESULTS: In this paper, we propose a rice panicle segmentation algorithm called Panicle-SEG, which is based on simple linear iterative clustering superpixel regions generation, convolutional neural network classification and entropy rate superpixel optimization. To build the Panicle-SEG-CNN model and test the segmentation effects, 684 training images and 48 testing images were randomly selected, respectively. Six indicators, including Qseg, Sr, SSIM, Precision, Recall and F-measure, are employed to evaluate the segmentation effects, and the average segmentation results for the 48 testing samples are 0.626, 0.730, 0.891, 0.821, 0.730, and 76.73%, respectively. Compared with other segmentation approaches, including HSeg, i2 hysteresis thresholding and jointSeg, the proposed Panicle-SEG algorithm has better performance on segmentation accuracy. Meanwhile, the executing speed is also improved when combined with multithreading and CUDA parallel acceleration. Moreover, Panicle-SEG was demonstrated to be a robust segmentation algorithm, which can be expanded for different rice accessions, different field environments, different camera angles, different reproductive stages, and indoor rice images. The testing dataset and segmentation software are available online.
CONCLUSIONS: In conclusion, the results demonstrate that Panicle-SEG is a robust method for panicle segmentation, and it creates a new opportunity for nondestructive yield estimation.

Entities:  

Keywords:  Convolutional neural network; Deep learning; Image segmentation; Rice (O. sativa) panicles; Superpixel

Year:  2017        PMID: 29209408      PMCID: PMC5704426          DOI: 10.1186/s13007-017-0254-7

Source DB:  PubMed          Journal:  Plant Methods        ISSN: 1746-4811            Impact factor:   4.993


  7 in total

1.  Image quality assessment: from error visibility to structural similarity.

Authors:  Zhou Wang; Alan Conrad Bovik; Hamid Rahim Sheikh; Eero P Simoncelli
Journal:  IEEE Trans Image Process       Date:  2004-04       Impact factor: 10.856

2.  SLIC superpixels compared to state-of-the-art superpixel methods.

Authors:  Radhakrishna Achanta; Appu Shaji; Kevin Smith; Aurelien Lucchi; Pascal Fua; Sabine Süsstrunk
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2012-11       Impact factor: 6.226

3.  An evolutionarily conserved gene, FUWA, plays a role in determining panicle architecture, grain shape and grain weight in rice.

Authors:  Jun Chen; He Gao; Xiao-Ming Zheng; Mingna Jin; Jian-Feng Weng; Jin Ma; Yulong Ren; Kunneng Zhou; Qi Wang; Jie Wang; Jiu-Lin Wang; Xin Zhang; Zhijun Cheng; Chuanyin Wu; Haiyang Wang; Jian-Min Wan
Journal:  Plant J       Date:  2015-08       Impact factor: 6.417

4.  Strategies for developing Green Super Rice.

Authors:  Qifa Zhang
Journal:  Proc Natl Acad Sci U S A       Date:  2007-10-08       Impact factor: 11.205

5.  High-Resolution Inflorescence Phenotyping Using a Novel Image-Analysis Pipeline, PANorama.

Authors:  Samuel Crowell; Alexandre X Falcão; Ankur Shah; Zachary Wilson; Anthony J Greenberg; Susan R McCouch
Journal:  Plant Physiol       Date:  2014-04-02       Impact factor: 8.340

Review 6.  Plant phenomics and high-throughput phenotyping: accelerating rice functional genomics using multidisciplinary technologies.

Authors:  Wanneng Yang; Lingfeng Duan; Guoxing Chen; Lizhong Xiong; Qian Liu
Journal:  Curr Opin Plant Biol       Date:  2013-04-08       Impact factor: 7.834

7.  Automated characterization of flowering dynamics in rice using field-acquired time-series RGB images.

Authors:  Wei Guo; Tokihiro Fukatsu; Seishi Ninomiya
Journal:  Plant Methods       Date:  2015-02-13       Impact factor: 4.993

  7 in total
  29 in total

1.  Growth monitoring of greenhouse lettuce based on a convolutional neural network.

Authors:  Lingxian Zhang; Zanyu Xu; Dan Xu; Juncheng Ma; Yingyi Chen; Zetian Fu
Journal:  Hortic Res       Date:  2020-08-01       Impact factor: 6.793

2.  Leaf to panicle ratio (LPR): a new physiological trait indicative of source and sink relation in japonica rice based on deep learning.

Authors:  Zongfeng Yang; Shang Gao; Feng Xiao; Ganghua Li; Yangfeng Ding; Qinghua Guo; Matthew J Paul; Zhenghui Liu
Journal:  Plant Methods       Date:  2020-08-26       Impact factor: 4.993

3.  SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging.

Authors:  Tanuj Misra; Alka Arora; Sudeep Marwaha; Viswanathan Chinnusamy; Atmakuri Ramakrishna Rao; Rajni Jain; Rabi Narayan Sahoo; Mrinmoy Ray; Sudhir Kumar; Dhandapani Raju; Ranjeet Ranjan Jha; Aditya Nigam; Swati Goel
Journal:  Plant Methods       Date:  2020-03-18       Impact factor: 4.993

Review 4.  Crop breeding for a changing climate: integrating phenomics and genomics with bioinformatics.

Authors:  Jacob I Marsh; Haifei Hu; Mitchell Gill; Jacqueline Batley; David Edwards
Journal:  Theor Appl Genet       Date:  2021-04-14       Impact factor: 5.699

5.  Bottlenecks and opportunities in field-based high-throughput phenotyping for heat and drought stress.

Authors:  Nathan T Hein; Ignacio A Ciampitti; S V Krishna Jagadish
Journal:  J Exp Bot       Date:  2021-07-10       Impact factor: 6.992

6.  Estimation of vegetation indices for high-throughput phenotyping of wheat using aerial imaging.

Authors:  Zohaib Khan; Vahid Rahimi-Eichi; Stephan Haefele; Trevor Garnett; Stanley J Miklavcic
Journal:  Plant Methods       Date:  2018-03-14       Impact factor: 4.993

7.  Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM.

Authors:  Chengquan Zhou; Dong Liang; Xiaodong Yang; Hao Yang; Jibo Yue; Guijun Yang
Journal:  Front Plant Sci       Date:  2018-07-13       Impact factor: 5.753

Review 8.  Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm.

Authors:  Giao N Nguyen; Sally L Norton
Journal:  Plants (Basel)       Date:  2020-06-29

9.  Identification and Analysis of Rice Yield-Related Candidate Genes by Walking on the Functional Network.

Authors:  Jing Jiang; Fei Xing; Chunyu Wang; Xiangxiang Zeng
Journal:  Front Plant Sci       Date:  2018-11-20       Impact factor: 5.753

10.  Rapeseed Seedling Stand Counting and Seeding Performance Evaluation at Two Early Growth Stages Based on Unmanned Aerial Vehicle Imagery.

Authors:  Biquan Zhao; Jian Zhang; Chenghai Yang; Guangsheng Zhou; Youchun Ding; Yeyin Shi; Dongyan Zhang; Jing Xie; Qingxi Liao
Journal:  Front Plant Sci       Date:  2018-09-21       Impact factor: 5.753

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.