ABSTRACT
Field-based high-throughput imaging of agricultural crops has gained prominence for its application to plant breeding research as well as precision agriculture. The scale of data generated requires automated methods to extract plant traits of importance from the image data. However, the variations in the imaging, lighting and environmental conditions make this a challenging task. In this work, we provide an image analysis pipeline developed on field-based image data of maize. The pipeline broadly consists of three sequential steps: automated tassel detection using Faster Region based Convolutional Neural Network, pixel level localization of the tassel structure using color information and adaptive thresholding, and tassel length computation for straight as well as curved tassels by combining piecewise Hough lines. Our results at different stages demonstrate the effectiveness of our overall pipeline.
- Singh Arti, Ganapathysubramanian Baskar, Singh Asheesh Kumar, and Sarkar Soumik. 2015. Machine Learning for High-Throughput Stress Phenotyping in Plants. Trends in Plant Science 21 (2015). https://doi.org/10.1016/j.tplants.2015.10.015Google Scholar
- Yann Chéné, David Rousseau, Philippe Lucidarme, Jessica Bertheloot, Valérie Caffier, Philippe Morel, Étienne Belin, and François Chapeau-Blondeau. 2012. On the use of depth camera for 3D phenotyping of entire plants. Computers and Electronics in Agriculture 82 (2012), 122--127. https://doi.org/10.1016/j.compag.2011.12.007Google ScholarDigital Library
- S. D. Choudhury, S. Goswami, S. Bashyam, T. Awada, and A. Samal. 2017. Automated Stem Angle Determination for Temporal Plant Phenotyping Analysis. In 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/ICCVW.2017.237Google Scholar
- Noah Fahlgren, Malia A Gehan, and Ivan Baxter. 2015. Lights, camera, action: high-throughput plant phenotyping is ready for a close-up. Current Opinion in Plant Biology 24 (2015), 93--99. https://doi.org/10.1016/j.pbi.2015.02.006Google ScholarCross Ref
- Joseph L. Gage, Nathan D. Miller, Edgar P. Spalding, Shawn M. Kaeppler, and Natalia de Leon. 2017. TIPS: a system for automated image-based phenotyping of maize tassels. Plant Methods 13, 1 (2017). https://doi.org/10.1186/s13007-017-0172-8Google Scholar
- Ross Girshick. 2015. Fast R-CNN. In Proceedings of the International Conference on Computer Vision (ICCV).Google Scholar
- Ross B. Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2013. Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR abs/1311.2524 (2013). http://arxiv.org/abs/1311.2524Google Scholar
- Wei Guo, Tokihiro Fukatsu, and Seishi Ninomiya. 2015. Automated characterization of flowering dynamics in rice using field-acquired time-series RGB images. Plant Methods 11 (2015). https://doi.org/10.1186/s13007-015-0047-9Google Scholar
- Lambert R. J. and R. R. Johnson. 1978. Leaf Angle, Tassel Morphology, and the Performance of Maize Hybrids1. Crop Sci. 18 (1978), 499--502. https://doi.org/10.2135/cropsci1978.0011183X001800030037xGoogle ScholarCross Ref
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097--1105. http://papers.nips.cc/paper/4824- imagenet- classification-with-deep-convolutional-neural-networks.pdfGoogle ScholarDigital Library
- Ferhat Kurtulmuş and İsmail Kavdir. 2014. Detecting Corn Tassels Using Computer Vision and Support Vector Machines. Expert Syst. Appl. 41, 16 (Nov. 2014), 7390--7397. https://doi.org/10.1016/j.eswa.2014.06.013Google ScholarDigital Library
- N Lee, Y S Chung, S Srinivasan, P Schnable, and B Ganapathysubramanian. 2016. Fast, automated identification of tassels: Bag-of-features, graph algorithms and high throughput computing. International Conference on Knowledge Discovery and Data Mining, The ACM SIGKDD Conference Series (San Francisco, CA). (2016).Google Scholar
- Lei Li, Qin Zhang, and Danfeng Huang. 2014. A Review of Imaging Techniques for Plant Phenotyping. Sensors 14 (2014). https://doi.org/10.3390/s141120078Google Scholar
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, and Alexander C. Berg. 2015. SSD: Single Shot MultiBox Detector. CoRR abs/1512.02325 (2015). http://arxiv.org/abs/1512.02325Google Scholar
- Hao Lu, Zhiguo Cao, Yang Xiao, Zhiwen Fang, and Yanjun Zhu. 2017. Towards fine-grained maize tassel flowering status recognition: Dataset, theory and practice. Applied Soft Computing 56 (2017), 34--45. https://doi.org/10.1016/j.asoc.2017.02.026Google ScholarDigital Library
- Hao Lu, Zhiguo Cao, Yang Xiao, Bohan Zhuang, and Chunhua Shen. 2017. TasselNet: counting maize tassels in the wild via local counts regression network. Plant Methods 13, 1 (01 Nov 2017), 79. https://doi.org/10.1186/s13007-017-0224-0Google Scholar
- Sharada P. Mohanty, David P. Hughes, and Marcel Salathé. 2016. Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in Plant Science 7 (2016), 1419. https://doi.org/10.3389/fpls.2016.01419Google ScholarCross Ref
- Robert L. Nielsen. 2016. Tassel Emergence and Pollen Shed. (2016). https://www.agry.purdue.edu/ext/corn/news/timeless/Tassels.htmlGoogle Scholar
- M. P. Pound, J. A. Atkinson, D. M. Wells, T. P. Pridmore, and A. P. French. 2017. Deep Learning for Multi-task Plant Phenotyping. In 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/ICCVW.2017.241Google Scholar
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28. Curran Associates, Inc. http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdfGoogle Scholar
- Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. CoRR abs/1506.01497 (2015). arXiv:1506.01497 http://arxiv.org/abs/1506.01497Google Scholar
- D. V. S. X. D. Silva, W. A. C. Fernando, H. Kodikaraarachchi, S. T. Worrall, and A. M. Kondoz. 2010. Adaptive sharpening of depth maps for 3D-TV. Electronics Letters 46, 23 (November 2010), 1546--1548. https://doi.org/10.1049/el.2010.2320Google ScholarCross Ref
- Niko Sünderhauf, Christopher McCool, Ben Upcroft, and Tristan Perez. 2014. Fine-grained plant classification using convolutional neural networks for feature extraction. In CLEF 2014 Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, 756--762. https://eprints.qut.edu.au/82381/Google Scholar
- Achimand Walter, Frank Liebisch, and Andreas Hund. 2015. Plant phenotyping: from bean weighing to image analysis. Plant Methods (2015). https://doi.org/10.1186/s13007-015-0056-8Google Scholar
Index Terms
- An automated tassel detection and trait extraction pipeline to support high-throughput field imaging of maize
Recommendations
Fine-grained maize tassel trait characterization with multi-view representations
Display Omitted A novel pipeline is proposed for efficient tassel potential region extraction.We proposed to characterize the maize tassel with a multi-view mechanism.Effective tassel detection is performed for fine-grained trait characterization.Time-...
Enhancing leaf area index and biomass estimation in maize with feature augmentation from unmanned aerial vehicle-based nadir and cross-circling oblique photography
Highlights- CCO photography is more accurate than nadir photography for canopy height estimation.
- Maize phenotype estimation can be improved by combining two UAV photography methods.
- The proposed LRFA algorithm outperforms the conventional ...
AbstractRapid and accurate estimation of plant phenotypes plays a vital role in effective breeding and management of maize crops. Unmanned aerial vehicle (UAV) platforms are emerging as a valuable tool in the assessment of crop phenotypes, offering a ...
Extraction of Summer Maize Using MODIS EVI Time Series in Huang-Huai-Hai
CSSS '12: Proceedings of the 2012 International Conference on Computer Science and Service SystemThis paper explores the feasibility of extracting summer maize using the MODIS EVI time series imagery in Huang-Huai-Hai. We first obtained the spatial distribution of double-season crops based on three-temporal EVI imagery, and then the phenology ...
Comments