Deep Learning Method for Height Estimation of Sorghum in the Field Using LiDAR

@article{Waliman2020DeepLM,
  title={Deep Learning Method for Height Estimation of Sorghum in the Field Using LiDAR},
  author={Matthew Waliman and Avideh Zakhor},
  journal={Electronic Imaging},
  year={2020}
}
Automatic tools for plant phenotyping have received increased interest in recent years due to the need to understand the relationship between plant genotype and phenotype. Building upon our previous work, we present a robust, deep learning method to accurately estimate the height of biomass sorghum throughout the entirety of its growing season. We mount a vertically oriented LiDAR sensor onboard an agricultural robot to obtain 3D point clouds of the crop fields. From each of these 3D point… 

References

SHOWING 1-10 OF 15 REFERENCES

Height estimation of biomass sorghum in the field using LiDAR

A robust, LiDAR based approach to estimate the height of biomass sorghum plants, capable of estimating height at all stages of the growing period, from emergence e.g. 10 cm through canopy closure.

Top Down Approach to Height Histogram Estimation of Biomass Sorghum in the Field

An algorithm is proposed to automatically estimate the canopy height of a row of plants in field conditions in a single pass on a moving robot, achieving a height estimation error of approximately 3.3%.

DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning

The 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, and the results for biomass estimation improve upon all previously proposed approaches in the literature.

Deep phenotyping: deep learning for temporal phenotype/genotype classification

This paper proposes a CNN-LSTM framework for plant classification of various genotypes and exploits the power of deep CNNs for automatic joint feature and classifier learning, compared to using hand-crafted features.

Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks

An open-source deep learning tool called Deep Plant Phenomics is introduced, which provides pre-trained neural networks for several common plant phenotyping tasks, as well as an easy platform that can be used by plant scientists to train models for their own Phenotyping applications.

Image Analysis: The New Bottleneck in Plant Phenotyping [Applications Corner]

The rate at which phenotypes are extracted in the field or in the lab is not matching the speed of genotyping and is creating a bottleneck, which needs to be addressed.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Deep Learning on Point Sets for 3 D Classification and Segmentation

  • C. Qi
  • Computer Science
  • 2016
This paper designs a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input, and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Volumetric and Multi-view CNNs for Object Classification on 3D Data

This paper introduces two distinct network architectures of volumetric CNNs and examines multi-view CNNs, providing a better understanding of the space of methods available for object classification on 3D data.

Impacts of breeding on international collaborative wheat improvement

For over 40 years a collaborative network of publicly funded international wheat scientists has made a significant contribution to food security in the developing world, placing great emphasis on genetic control of disease since resource-poor farmers generally lack the means to control diseases chemically.