DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning

被引：37

作者：

Aich, Shubhra ^{[1
]}

Josuttes, Anique ^{[2
]}

Ovsyannikov, Ilya ^{[1
]}

Strueby, Keegan ^{[2
]}

Ahmed, Imran ^{[1
]}

Duddu, Hema Sudhakar ^{[2
]}

Pozniak, Curtis ^{[2
,3
]}

Shirtliffe, Steve ^{[2
]}

Stavness, Ian ^{[1
]}

机构：

[1] Univ Saskatchewan, Dept Comp Sci, Saskatoon, SK, Canada

[2] Univ Saskatchewan, Dept Plant Sci, Saskatoon, SK, Canada

[3] Univ Saskatchewan, Crop Dev Ctr, Saskatoon, SK, Canada

来源：

2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018) | 2018年

基金：

加拿大自然科学与工程研究理事会;

关键词：

GROUND BIOMASS; PLANT-DENSITY; EMERGENCE; LIDAR;

D O I：

10.1109/WACV.2018.00042

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we investigate estimating emergence and biomass traits from color images and elevation maps of wheat field plots. We employ a state-of-the-art deconvolutional network for segmentation and convolutional architectures, with residual and Inception-like layers, to estimate traits via high dimensional nonlinear regression. Evaluation was performed on two different species of wheat, grown in field plots for an experimental plant breeding study. Our framework achieves satisfactory performance with mean and standard deviation of absolute difference of 1.05 and 1.40 counts for emergence and 1.45 and 2.05 for biomass estimation. Our results for counting wheat plants from field images are better than the accuracy reported for the similar, but arguably less difficult, task of counting leaves from indoor images of rosette plants. Our results for biomass estimation, even with a very small dataset, improve upon all previously proposed approaches in the literature.

引用

页码：323 / 332

页数：10

共 50 条

[1] Estimating Fruit Crop Yield through Deep Learning
Yu, Huaqing
Song, Shining
Ma, Shaoxi
Sinnott, Richard O.
[J]. BDCAT'19: PROCEEDINGS OF THE 6TH IEEE/ACM INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING, APPLICATIONS AND TECHNOLOGIES, 2019, : 145 - 148
[2] ESTIMATING CROP YIELDS WITH REMOTE SENSING AND DEEP LEARNING
de Freitas Cunha, Renato Luiz
Silva, Bruno
[J]. 2020 IEEE LATIN AMERICAN GRSS & ISPRS REMOTE SENSING CONFERENCE (LAGIRS), 2020, : 273 - 278
[3] Deep Learning Model for Enhanced Crop Identification From Landsat 8 Images
Sucithra, B.
Gladston, Angelin
[J]. INTERNATIONAL JOURNAL OF INFORMATION RETRIEVAL RESEARCH, 2022, 12 (01)
[4] ESTIMATING THE DISTANCE TO AN OBJECT FROM GRAYSCALE STEREO IMAGES USING DEEP LEARNING
Kulawik, Joanna
[J]. JOURNAL OF APPLIED MATHEMATICS AND COMPUTATIONAL MECHANICS, 2022, 21 (04) : 60 - 72
[5] ESTIMATING CROP YIELDS WITH DEEP LEARNING AND REMOTELY SENSED DATA
Kuwata, Kentaro
Shibasaki, Ryosuke
[J]. 2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 858 - 861
[6] An Approximation for A Relative Crop Yield Estimate from Field Images Using Deep Learning
Yalcin, Hulya
[J]. 2019 8TH INTERNATIONAL CONFERENCE ON AGRO-GEOINFORMATICS (AGRO-GEOINFORMATICS), 2019,
[7] Automated detection of sugarcane crop lines from UAV images using deep learning
Ribeiro, Joao Batista
da Silva, Renato Rodrigues
Dias, Jocival Dantas
Escarpinati, Mauricio Cunha
Backes, Andre Ricardo
[J]. INFORMATION PROCESSING IN AGRICULTURE, 2024, 11 (03): : 385 - 396
[8] Deep neural networks with transfer learning in millet crop images
Coulibaly, Solemane
Kamsu-Foguem, Bernard
Kamissoko, Dantouma
Traore, Daouda
[J]. COMPUTERS IN INDUSTRY, 2019, 108 : 115 - 120
[9] The phenotype and the components of phenotypic variance of crop traits
Sadras, V. O.
Rebetzke, G. J.
Edmeades, G. O.
[J]. FIELD CROPS RESEARCH, 2013, 154 : 255 - 259
[10] In Vino Veritas: Estimating Vineyard Grape Yield from Images Using Deep Learning
Silver, Daniel L.
Monga, Tanya
[J]. ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 11489 : 212 - 224

← 1 2 3 4 5 →