Research Status and Prospects on Plant Canopy Structure Measurement Using Visual Sensors Based on Three-Dimensional Reconstruction

Wang, Jizhang; Zhang, Yun; Gu, Rongrong

doi:10.3390/agriculture10100462

Cited by 23 publications

(6 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fluorescence sensors adopt an active measurement method while facing some difficulties in fluorescence excitation, so their in situ application is limited [57]. Depth-sensing cameras can output the depth, amplitude, and intensity images and have been widely applied to crop phenotype monitoring to solve problems arising from leaf occlusion [58][59][60][61][62]. Lidar scanners, characterized by high precision and strong anti-jamming capability, acquire the 3D point cloud data by scanning the crop canopy or plants and obtain parameters including the canopy height [63] and so on [64,65] by analyzing point cloud data.…”

Section: Common Phenotyping Sensors For Cropsmentioning

confidence: 99%

Field Phenotyping Monitoring Systems for High-Throughput: A Survey of Enabling Technologies, Equipment, and Research Challenges

Yuan,

Song,

Liu

et al. 2023

Agronomy

View full text Add to dashboard Cite

High-throughput phenotype monitoring systems for field crops can not only accelerate the breeding process but also provide important data support for precision agricultural monitoring. Traditional phenotype monitoring methods for field crops relying on artificial sampling and measurement have some disadvantages including low efficiency, strong subjectivity, and single characteristics. To solve these problems, the rapid monitoring, acquisition, and analysis of phenotyping information of field crops have become the focus of current research. The research explores the systematic framing of phenotype monitoring systems for field crops. Focusing on four aspects, namely phenotyping sensors, mobile platforms, control systems, and phenotyping data preprocessing algorithms, the application of the sensor technology, structural design technology of mobile carriers, intelligent control technology, and data processing algorithms to phenotype monitoring systems was assessed. The research status of multi-scale phenotype monitoring products was summarized, and the merits and demerits of various phenotype monitoring systems for field crops in application were discussed. In the meantime, development trends related to phenotype monitoring systems for field crops in aspects including sensor integration, platform optimization, standard unification, and algorithm improvement were proposed.

show abstract

Section: Common Phenotyping Sensors For Cropsmentioning

confidence: 99%

Field Phenotyping Monitoring Systems for High-Throughput: A Survey of Enabling Technologies, Equipment, and Research Challenges

Yuan,

Song,

Liu

et al. 2023

Agronomy

View full text Add to dashboard Cite

show abstract

“…The 3D image processing techniques are vital for reconstructing 3D structure from the raw data before extracting targeted crop features. However, one of the significant factors for the process is the quality of the input data (Wang et al, 2020). For 3D data collection, optical systems built on three basic principles for depth measurement, i.e., triangulation, time of flight (ToF), and interferometry, are preferred over other techniques, such as sound detection and ranging (SONAR) and radio detection and ranging (RADAR), due to faster 3D acquisition, higher lateral resolution, safety, and common operating systems (Schwarte et al, 1999;Büttgen et al, 2005;Vázquez-Arellano et al, 2016;Iglhaut et al, 2019).…”

Section: Sensor-based Techniques 3d Data Generating Techniquesmentioning

confidence: 99%

Phenotyping Architecture Traits of Tree Species Using Remote Sensing Techniques

Sangjan¹,

Sankaran²

2021

Transactions of the ASABE

View full text Add to dashboard Cite

HighlightsTree canopy architecture traits are associated with its productivity and management.Understanding these traits is important for both precision agriculture and phenomics applications.Remote sensing platforms (satellite, UAV, etc.) and multiple approaches (SfM, LiDAR) have been used to assess these traits.3D reconstruction of tree canopies allows the measurement of tree height, crown area, and canopy volume.Abstract. Tree canopy architecture is associated with light use efficiency and thus productivity. Given the modern training systems in orchard tree fruit systems, modification of tree architecture is becoming important for easier management of crops (e.g., pruning, thinning, chemical application, harvesting, etc.) while maintaining fruit quality and quantity. Similarly, in forest environments, architecture can influence the competitiveness and balance between tree species in the ecosystem. This article reviews the literature related to sensing approaches used for assessing architecture traits and the factors that influence such evaluation processes. Digital imagery integrated with structure from motion analysis and both terrestrial and aerial light detection and ranging (LiDAR) systems have been commonly used. In addition, satellite imagery and other techniques have been explored. Some of the major findings and some critical considerations for such measurement methods are summarized here. Keywords: Canopy volume, LiDAR system, Structure from motion, Tree height, UAV.

show abstract

“…However, because of the limitation of imaging dimensions, factors such as inclination and curling of plant leaves, mutual occlusion between plant leaves and other organs or canopy, and plant–illumination interaction could greatly affect the integrity and accuracy of spectral imaging for plants. Three-dimensional (3D) data, describing the spatial information of the target, is widely used for plant phenotyping [ 4 ]. 3D data can be acquired through time-of-flight techniques, such as lidar, laser scanners, and depth cameras, or stereo vision techniques, such as binocular cameras and multiview cameras [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

Xie

et al. 2023

Plant Phenomics

View full text Add to dashboard Cite

Accurate and high-throughput plant phenotyping is important for accelerating crop breeding. Spectral imaging that can acquire both spectral and spatial information of plants related to structural, biochemical, and physiological traits becomes one of the popular phenotyping techniques. However, close-range spectral imaging of plants could be highly affected by the complex plant structure and illumination conditions, which becomes one of the main challenges for close-range plant phenotyping. In this study, we proposed a new method for generating high-quality plant 3-dimensional multispectral point clouds. Speeded-Up Robust Features and Demons was used for fusing depth and snapshot spectral images acquired at close range. A reflectance correction method for plant spectral images based on hemisphere references combined with artificial neural network was developed for eliminating the illumination effects. The proposed Speeded-Up Robust Features and Demons achieved an average structural similarity index measure of 0.931, outperforming the classic approaches with an average structural similarity index measure of 0.889 in RGB and snapshot spectral image registration. The distribution of digital number values of the references at different positions and orientations was simulated using artificial neural network with the determination coefficient ( R 2 ) of 0.962 and root mean squared error of 0.036. Compared with the ground truth measured by ASD spectrometer, the average root mean squared error of the reflectance spectra before and after reflectance correction at different leaf positions decreased by 78.0%. For the same leaf position, the average Euclidean distances between the multiview reflectance spectra decreased by 60.7%. Our results indicate that the proposed method achieves a good performance in generating plant 3-dimensional multispectral point clouds, which is promising for close-range plant phenotyping.

show abstract

Research Status and Prospects on Plant Canopy Structure Measurement Using Visual Sensors Based on Three-Dimensional Reconstruction

Cited by 23 publications

References 105 publications

Field Phenotyping Monitoring Systems for High-Throughput: A Survey of Enabling Technologies, Equipment, and Research Challenges

Field Phenotyping Monitoring Systems for High-Throughput: A Survey of Enabling Technologies, Equipment, and Research Challenges

Phenotyping Architecture Traits of Tree Species Using Remote Sensing Techniques

Generating 3D Multispectral Point Clouds of Plants with Fusion of Snapshot Spectral and RGB-D Images

Contact Info

Product

Resources

About