Online crop height and density estimation in grain fields using LiDAR

Blanquart, Jean-Edouard; Sirignano, Emilio; Lenaerts, Bart; Saeys, Wouter

doi:10.1016/j.biosystemseng.2020.06.014

Cited by 24 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…characteriz. Robotic Operating System (ROS) + Velodyne data acquisition [ 71 ]-2020 wheat, barley SICK LMS111 Terrestrial/Mobile/Tractor Param. characteriz.…”

Section: Table A1mentioning

confidence: 99%

Methods and Applications of 3D Ground Crop Analysis Using LiDAR Technology: A Survey

Micheletto

Chesñevar

Santos

2023

Sensors

View full text Add to dashboard Cite

Light Detection and Ranging (LiDAR) technology is positioning itself as one of the most effective non-destructive methods to collect accurate information on ground crop fields, as the analysis of the three-dimensional models that can be generated with it allows for quickly measuring several key parameters (such as yield estimations, aboveground biomass, vegetation indexes estimation, perform plant phenotyping, and automatic control of agriculture robots or machinery, among others). In this survey, we systematically analyze 53 research papers published between 2005 and 2022 that involve significant use of the LiDAR technology applied to the three-dimensional analysis of ground crops. Different dimensions are identified for classifying the surveyed papers (including application areas, crop species under study, LiDAR scanner technologies, mounting platform technologies, and the use of additional instrumentation and software tools). From our survey, we draw relevant conclusions about the use of LiDAR technologies, such as identifying a hierarchy of different scanning platforms and their frequency of use as well as establishing the trade-off between the economic costs of deploying LiDAR and the agronomically relevant information that effectively can be acquired. We also conclude that none of the approaches under analysis tackles the problem associated with working with multiple species with the same setup and configuration, which shows the need for instrument calibration and algorithmic fine tuning for an effective application of this technology.

show abstract

“…characteriz. Robotic Operating System (ROS) + Velodyne data acquisition [ 71 ]-2020 wheat, barley SICK LMS111 Terrestrial/Mobile/Tractor Param. characteriz.…”

Section: Table A1mentioning

confidence: 99%

Methods and Applications of 3D Ground Crop Analysis Using LiDAR Technology: A Survey

Micheletto

Chesñevar

Santos

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This is consistent with the conclusion proposed by Swayes [17], who applied LiDAR sensors to estimate wheat density, that the crop properties are relative to rice to some extent. The literature shows that accuracy of wheat density estimation could reach an R 2 of 0.8, according to Blanquart [33], who also analyzed the different installment angle of LiDAR sensor. However, as the wheat panicles have less leaves, the separation of wheat earheads is more obvious; moreover, the estimation based on point-cloud data becomes more convenient, compared with the mature rice plants with bent and intersected earheads.…”

Section: Rice-density Estimationmentioning

confidence: 99%

Double-Threshold Segmentation of Panicle and Clustering Adaptive Density Estimation for Mature Rice Plants Based on 3D Point Cloud

et al. 2021

View full text Add to dashboard Cite

Crop density estimation ahead of the combine harvester provides a valuable reference for operators to keep the feeding amount stable in agriculture production, and, as a consequence, guaranteeing the working stability and improving the operation efficiency. For the current method depending on LiDAR, it is difficult to extract individual plants for mature rice plants with luxuriant branches and leaves, as well as bent and intersected panicles. Therefore, this paper proposes a clustering adaptive density estimation method based on the constructed LiDAR measurement system and double-threshold segmentation. The Otsu algorithm is adopted to construct a double-threshold according to elevation and inflection intensity in different parts of the rice plant, after reducing noise through the statistical outlier removal (SOR) algorithm. For adaptively parameter adjustment of supervoxel clustering and mean-shift clustering during density estimation, the calculation relationship between influencing factors (including seed-point size and kernel-bandwidth size) and number of points are, respectively, deduced by analysis. The experiment result of density estimation proved the two clustering methods effective, with a Root Mean Square Error (RMSE) of 9.968 and 5.877, and a Mean Absolute Percent Error (MAPE) of 5.67% and 3.37%, and the average accuracy was more than 90% and 95%, respectively. This estimation method is of positive significance for crop density measurement and could lay the foundation for intelligent harvest.

show abstract

“…Those parameters are most effectively captured by techniques that enable the extraction of spatial depth information about an object. Notable examples of such techniques are Light Detection and Ranging (LiDAR), e.g., [9,10], Structure-from-Motion (SfM), which is the three-dimensional reconstruction of structures using a series of two-dimensional RGB images captured from multiple viewpoints, e.g., [11][12][13], the combination of RGB cameras with depth sensors for the simultaneous capturing of color and depth information, e.g., [14,15], or the combination of several of the above-mentioned methods and carrier platforms, e.g., [16,17]. An approach that utilizes two RGB cameras installed in a stereo-capable orientation is referred to as binocular vision or stereoscopic vision, which closely resembles the depth perception of the human eye.…”

Section: Introductionmentioning

confidence: 99%

Automated Workflow for High-Resolution 4D Vegetation Monitoring Using Stereo Vision

Kobe,

Elias,

Merbach

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Precision agriculture relies on understanding crop growth dynamics and plant responses to short-term changes in abiotic factors. In this technical note, we present and discuss a technical approach for cost-effective, non-invasive, time-lapse crop monitoring that automates the process of deriving further plant parameters, such as biomass, from 3D object information obtained via stereo images in the red, green, and blue (RGB) color space. The novelty of our approach lies in the automated workflow, which includes a reliable automated data pipeline for 3D point cloud reconstruction from dynamic scenes of RGB images with high spatio-temporal resolution. The setup is based on a permanent rigid and calibrated stereo camera installation and was tested over an entire growing season of winter barley at the Global Change Experimental Facility (GCEF) in Bad Lauchstädt, Germany. For this study, radiometrically aligned image pairs were captured several times per day from 3 November 2021 to 28 June 2022. We performed image preselection using a random forest (RF) classifier with a prediction accuracy of 94.2% to eliminate unsuitable, e.g., shadowed, images in advance and obtained 3D object information for 86 records of the time series using the 4D processing option of the Agisoft Metashape software package, achieving mean standard deviations (STDs) of 17.3–30.4 mm. Finally, we determined vegetation heights by calculating cloud-to-cloud (C2C) distances between a reference point cloud, computed at the beginning of the time-lapse observation, and the respective point clouds measured in succession with an absolute error of 24.9–35.6 mm in depth direction. The calculated growth rates derived from RGB stereo images match the corresponding reference measurements, demonstrating the adequacy of our method in monitoring geometric plant traits, such as vegetation heights and growth spurts during the stand development using automated workflows.

show abstract

Online crop height and density estimation in grain fields using LiDAR

Cited by 24 publications

References 12 publications

Methods and Applications of 3D Ground Crop Analysis Using LiDAR Technology: A Survey

Methods and Applications of 3D Ground Crop Analysis Using LiDAR Technology: A Survey

Double-Threshold Segmentation of Panicle and Clustering Adaptive Density Estimation for Mature Rice Plants Based on 3D Point Cloud

Automated Workflow for High-Resolution 4D Vegetation Monitoring Using Stereo Vision

Contact Info

Product

Resources

About