University of Twente Student Theses

Login

Wheat ear detection in plots by segmenting mobile laser scanner data

Velumani, Kaaviya (2017) Wheat ear detection in plots by segmenting mobile laser scanner data.

[img] PDF
9MB
Abstract:The use of Light Detection and Ranging (LiDAR) to study agricultural crop traits is becomingpopular. This is due to LiDAR’s capability to render accurate 3-dimensional representation of theplant architecture. Wheat plant traits such as crop height, biomass fractions and plant populationare of interest to agronomists and biologists for the assessment of a genotype’s performance in theenvironment. Among these performance indicators, plant population in the field is still widelyestimated through manual counting which is a tedious and labour intensive task. Thus, the goalof this study is to explore the suitability of LiDAR observations to automate the counting processby the individual detection of wheat ears in the agricultural field. However, this is a challengingtask owing to the random cropping pattern and noisy returns present in the point cloud. The goalis achieved by first segmenting the 3D point cloud followed by the classification of segments intoears and non-ears. In this study, two segmentation techniques: a) voxel-based segmentation andb) mean shift segmentation were adapted to suit the segmentation of plant point clouds. A novelstrategy was developed to distinguish the ear segments from leaves, stem and other plant organs.Finally, the ears extracted by the automatic methods were compared with reference ear segmentsprepared by manual segmentation.The manual segmentation tests carried out with 6 operators revealed that it is hard even forhumans to identify individual wheat ears from the point cloud. Also, the robustness of the twosegmentation methods for detecting wheat ears over different crop developmental stages, wheatvarieties and point densities was evaluated and compared. Both the methods had an average detec-tion rate of 85%, aggregated over different flowering stages. The voxel-based approach performedwell for late flowering stages (wheat crops aged 210 days or more) with a mean percentage accu-racy of 94% and takes less than 20 seconds to process 50,000 points. Meanwhile, the mean shiftapproach showed comparatively better counting accuracy of 95% for early flowering stage (cropsaged below 225 days) and takes approximately 4 minutes to process 50,000 points. Even thoughboth the ear extraction approaches are dependent on point density, their performance was foundto be consistent for up to 75% of the original point density of16points/cm2. Thus, two ear detec-tion methods, that use only the 3D coordinates of the plant canopy, have been developed. Theycan be extended to suit crops such as barley, millets, etc. that are structurally similar to wheat
Item Type:Essay (Master)
Faculty:ITC: Faculty of Geo-information Science and Earth Observation
Programme:Geoinformation Science and Earth Observation MSc (75014)
Link to this item:https://purl.utwente.nl/essays/85857
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page