Online citations, reference lists, and bibliographies.

TasselNet: Counting Maize Tassels In The Wild Via Local Counts Regression Network

H. Lu, Z. Cao, Yang Xiao, Bohan Zhuang, Chunhua Shen
Published 2017 · Computer Science, Medicine

Cite This
Download PDF
Analyze on Scholarcy
Share
BackgroundAccurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations.ResultsThis paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel Maize Tassels Counting (MTC) dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed TasselNet is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large margins and achieves the overall best counting performance, with a mean absolute error of 6.6 and a mean squared error of 9.6 averaged over 8 test sequences.ConclusionsTasselNet can achieve robust in-field counting of maize tassels with a relatively high degree of accuracy. Our experimental evaluations also suggest several good practices for practitioners working on maize-tassel-like counting problems. It is worth noting that, though the counting errors have been greatly reduced by TasselNet, in-field counting of maize tassels remains an open and unsolved problem.
This paper references
10.1016/j.patcog.2017.06.010
Two-dimensional subspace alignment for convolutional activations adaptation
H. Lu (2017)
10.1080/21681163.2016.1149104
Microscopy cell counting and detection with fully convolutional regression networks
Weidi Xie (2018)
Advances in Neural Information Processing Systems (NIPS)
H. Tyagi (2014)
10.1109/ICCV.2015.123
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He (2015)
10.1007/978-3-319-10578-9_33
Interactive Object Counting
C. Arteta (2014)
Learning to count with regression forest and structured labels
Luca Fiaschi (2012)
10.1007/978-1-4614-8483-7
Modeling, Simulation and Visual Analysis of Crowds
Saad Ali (2013)
Statistical learning theory, volume
Vladimir Naumovich Vapnik (1998)
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan (2015)
10.3390/s17040905
Deep Count: Fruit Counting Based on Deep Simulated Learning
M. Rahnemoonfar (2017)
10.1016/j.compag.2015.08.027
Fine-grained maize tassel trait characterization with multi-view representations
H. Lu (2015)
10.1109/5.726791
Gradient-based learning applied to document recognition
Y. LeCun (1998)
10.1117/12.2031024
An image-based approach for automatic detecting tasseling stage of maize using spatio-temporal saliency
M. Ye (2013)
10.1016/J.BIOSYSTEMSENG.2016.04.007
Region-based colour modelling for joint crop and maize tassel segmentation
Hao Lu (2016)
10.1007/978-3-319-46478-7_30
Counting in the Wild
C. Arteta (2016)
10.1109/MSP.2015.2405111
Image Analysis: The New Bottleneck in Plant Phenotyping [Applications Corner]
M. Minervini (2015)
10.1109/ICCVW.2017.236
Computer Vision Problems in Plant Phenotyping, CVPPP 2017: Introduction to the CVPPP 2017 Workshop Papers
H. Scharr (2017)
10.1109/ICCVW.2017.9
Count-ception: Counting by Fully Convolutional Redundant Counting
Joseph Paul Cohen (2017)
10.1109/ICPR.2008.4761705
Estimating the number of people in crowded scenes by MID based foreground segmentation and head-shoulder detection
M. Li (2008)
10.1109/CVPR.2006.92
Counting Crowded Moving Objects
V. Rabaud (2006)
10.5244/C.29.CVPPP.1
Learning to Count Leaves in Rosette Plants
M. Giuffrida (2015)
10.1145/2733373.2807412
MatConvNet: Convolutional Neural Networks for MATLAB
A. Vedaldi (2015)
10.1007/978-1-4614-8483-7_14
Crowd Counting and Profiling: Methodology and Evaluation
Chen Change Loy (2013)
10.1145/3065386
ImageNet classification with deep convolutional neural networks
A. Krizhevsky (2017)
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
S. Ioffe (2015)
10.1109/cvpr.2016.90
Deep Residual Learning for Image Recognition
Kaiming He (2016)
10.1109/CVPR.2008.4587569
Privacy preserving crowd monitoring: Counting people without people models or tracking
Antoni B. Chan (2008)
10.1007/978-1-4614-8483-7_1
Modeling, Simulation and Visual Analysis of Crowds: A Multidisciplinary Perspective
Saad Ali (2013)
10.2307/1271368
Statistical learning theory
V. Vapnik (1998)
10.1109/CVPR.2016.70
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Yingying Zhang (2016)
10.1109/TPAMI.2009.167
Object Detection with Discriminatively Trained Part Based Models
Pedro F. Felzenszwalb (2009)
10.1061/(ASCE)GT.1943-5606.0001284
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky (2012)
10.1038/ncomms6087
Combining high-throughput phenotyping and genome-wide association studies to reveal natural genetic variation in rice
Wanneng Yang (2014)
10.5244/C.26.21
Feature Mining for Localised Crowd Counting
Ke Chen (2012)
10.1146/annurev-arplant-050312-120137
Future scenarios for plant phenotyping.
F. Fiorani (2013)
Counting in Dense Crowds using Deep Features
Karunya Tota (2015)
10.1186/s13007-015-0047-9
Automated characterization of flowering dynamics in rice using field-acquired time-series RGB images
W. Guo (2015)
Learning To Count Objects in Images
V. Lempitsky (2010)
10.1109/TPAMI.2011.155
Pedestrian Detection: An Evaluation of the State of the Art
P. Dollár (2012)
10.1109/TASE.2016.2616485
Toward Good Practices for Fine-Grained Maize Cultivar Identification With Filter-Specific Convolutional Activations
H. Lu (2018)
10.1186/s13007-017-0172-8
TIPS: a system for automated image-based phenotyping of maize tassels
Joseph L. Gage (2017)
Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition
G Huang (2016)
10.1007/978-3-319-46478-7_38
Towards Perspective-Free Object Counting with Deep Learning
Daniel Oñoro-Rubio (2016)
10.1109/CVPR.2017.243
Densely Connected Convolutional Networks
Gao Huang (2017)
10.1016/j.patrec.2017.07.007
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
Vishwanath Sindagi (2018)
10.1109/CVPR.2015.7298684
Cross-scene crowd counting via deep convolutional neural networks
Cong Zhang (2015)



This paper is referenced by
10.3390/rs11091128
DisCountNet: Discriminating and Counting Network for Real-Time Counting and Localization of Sparse Objects in High-Resolution UAV Imagery
M. Rahnemoonfar (2019)
10.1016/j.compag.2019.105159
Segmenting ears of winter wheat at flowering stage using digital images and deep learning
Juncheng Ma (2020)
10.34133/2020/7481687
A High-Throughput Phenotyping Pipeline for Image Processing and Functional Growth Curve Analysis
Ronghao Wang (2020)
10.34133/2020/5801869
Latent Space Phenotyping: Automatic Image-Based Phenotyping for Treatment Studies
Jordan Ubbens (2020)
10.1109/ACCESS.2020.2998678
Cascaded Multi-Task Learning of Head Segmentation and Density Regression for RGBD Crowd Counting
Desen Zhou (2020)
Everything counts: a Taxonomy of Deep Learning Approaches for Object Counting
K. Heinrich (2019)
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Vishwanath Sindagi (2020)
Unsupervised Domain Adaptation For Plant Organ Counting
T. Ayalew (2020)
Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
Liang Liu (2020)
10.1109/DSAA.2018.00052
Detecting and Counting Panicles in Sorghum Images
P. Olsen (2018)
AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images
Jordan Ubbens (2020)
Counting and Segmenting Sorghum Heads
Min-hwan Oh (2019)
10.1016/j.compag.2020.105504
Extracting apple tree crown information from remote imagery using deep learning
J. Wu (2020)
10.3390/rs11060691
Automatic Counting of in situ Rice Seedlings from UAV Images Based on a Deep Fully Convolutional Neural Network
Jintao Wu (2019)
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting
Haipeng Xiong (2020)
10.1016/j.inpa.2020.03.002
In-field automatic detection of maize tassels using computer vision
Mingqiang Ji (2020)
10.34133/2020/1375957
High-Throughput Rice Density Estimation from Transplantation to Tillering Stages Using Deep Networks
L. Liu (2020)
UAV Based Remote Sensing for Tassel Detection and Growth Stage Estimation of Maize Crop using F-RCNN
A. Kumar (2019)
10.34133/2020/4152816
Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review
Y. Jiang (2020)
DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
Saeed Khaki (2020)
CNN-based Density Estimation and Crowd Counting: A Survey
Guangshuai Gao (2020)
10.1016/J.AGRFORMET.2018.10.013
Ear density estimation from high resolution RGB imagery using deep learning technique
Simon Madec (2019)
10.1016/j.compag.2020.105519
UAV and a deep convolutional neural network for monitoring invasive alien plants in the wild
W. Qian (2020)
10.1186/s13007-018-0287-6
Estimation of vegetation indices for high-throughput phenotyping of wheat using aerial imaging
Zohaib Khan (2018)
10.1109/ICCV.2019.00109
Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting
Vishwanath Sindagi (2019)
Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
X. Liu (2020)
10.1186/s13007-018-0366-8
Detection and analysis of wheat spikes using Convolutional Neural Networks
Md Mehedi Hasan (2018)
Leaf counting: Multiple scale regression and detection using deep CNNs
Yotam Itzhaky (2018)
10.1016/j.fcr.2020.107793
An automatic method based on daily in situ images and deep learning to date wheat heading stage
Kaaviya Velumani (2020)
Learning to Count in the Crowd from Limited Labeled Data
Vishwanath A. Sindagi (2020)
10.1093/gigascience/giy153
Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective
K. Mochida (2019)
10.3390/rs11242939
A Deep Learning Semantic Segmentation-Based Approach for Field-Level Sorghum Panicle Counting
Lonesome Malambo (2019)
See more
Semantic Scholar Logo Some data provided by SemanticScholar