Three-Dimensional Modeling of Weed Plants Using Low-Cost Photogrammetry

Abstract

Sensing advances in plant phenotyping are of vital importance in basic and applied plant research. Plant phenotyping enables the modeling of complex shapes, which is useful, for example, in decision-making for agronomic management. In this sense, 3D processing algorithms for plant modeling is expanding rapidly with the emergence of new sensors and techniques designed to morphologically characterize. However, there are still some technical aspects to be improved, such as an accurate reconstruction of end-details. This study adapted low-cost techniques, Structure from Motion (SfM) and MultiView Stereo (MVS), to create 3D models for reconstructing plants of three weed species with contrasting shape and plant structures. Plant reconstruction was developed by applying SfM algorithms to an input set of digital images acquired sequentially following a track that was concentric and equidistant with respect to the plant axis and using three different angles, from a perpendicular to top view, which guaranteed the necessary overlap between images to obtain high precision 3D models. With this information, a dense point cloud was created using MVS, from which a 3D polygon mesh representing every plants’ shape and geometry was generated. These 3D models were validated with ground truth values (e.g., plant height, leaf area (LA) and plant dry biomass) using regression methods. The results showed, in general, a good consistency in the correlation equations between the estimated values in the models and the actual values measured in the weed plants. Indeed, 3D modeling using SfM algorithms proved to be a valuable methodology for weed phenotyping, since it accurately estimated the actual values of plant height and LA. Additionally, image processing using the SfM method was relatively fast. Consequently, our results indicate the potential of this budget system for plant reconstruction at high detail, which may be usable in several scenarios, including outdoor conditions. Future research should address other issues, such as the time-cost relationship and the need for detail in the different approaches.

Performances Evaluation of a Low-Cost Platform for High-Resolution Plant Phenotyping

“…Indeed, differently from SfM imagery analysis based on a manual acquisition system [25,54], our platform is able to automatically acquire images and, thus, gather a pre-defined number of overlapped images, avoiding human mistakes (i.e., images out of focus and lack of scene features) [55]. Although the SfM methodology has been widely adopted for low-cost and accurate 3D plant modelling [33,34], only a few studies have focused on optimization of the reconstruction process in relation to different canopy architectures, even if they have been mainly fed with a fixed number of images of the same quality [40,56]. However, this approach prevented investigating the best input combination for an efficient modelling of each species, which is an essential reference for a practical application of SfM in agronomic and breeding programs.…”

“…However, some technical aspects need to be improved to resolve the uncertainties in the estimation of traits (i.e., stem diameters and leaf area) when increases in images' quantity and quality are not enough. In this context, low distances between sensor and plant [56] coupled with an increase in height and inclination of the camera, could be a cost-effective solution for reducing errors in canopy disclosure, keeping the potential of the zenith-point-of-view image acquisition system in vertical measurements unchanged. Nevertheless, errors can also be attributable to a manual and non-automatic extraction of the traits.…”

Three-Dimensional Point Cloud Reconstruction and Morphology Measurement Method for Greenhouse Plants Based on the Kinect Sensor Self-Calibration

“…Based on multiview RGB-D 3D reconstruction, the change of the initial reference point cloud would affect the projection morphology of the canopy point cloud on the XOY and YOZ planes, but the projection of the tomato canopy on the XOZ horizontal plane was not affected by the initial point cloud view. The XOZ horizontal plane projection boundary enclosing area is an invariant feature quantity, and the projection boundary enclosing area was calculated as shown in Equation (12). The 3D shape of a tomato canopy is complex.…”

“…Thus, monocular vision has relatively low applicability. Multiview reconstruction techniques based on monocular vision mainly include space carving [9], visual structure from motion system techniques [10,11], multiview photogrammetry [12,13], and multicamera synchronous reconstruction [14]. However, these techniques require many angles of view (AOVs) for measurement and are unable to meet the reconstruction efficiency requirement for high-throughput plant phenotyping.…”

Novel and Automatic Rice Thickness Extraction Based on Photogrammetry Using Rice Edge Features

“…According to the principle of stereo vision [30,31], it is necessary to match the corresponding points from two images in order to obtain the 3D thickness information from 2D images [32]. But due to the fact that the shape of rice is similar to each other and the surface texture is scarce, it is impossible to realize matching directly using the traditional matching algorithm [33], which greatly increases the difficulty of extracting rice thickness from images.…”