Search

• A new oblique imaging scheme was devised for lettuce fresh weight estimation. • A position-guided network was customized to extract oblique view image features. • Our model exhibited better performances versus to other approaches. Fresh weight is a crucial indicator for assessing crop growth in plant factory. To date, the majority of non-destructive techniques employed for estimating crop fresh weight rely on the top view images. Nevertheless, these approaches are limited in performance due to the constrained and non-open environment of plant factories. In this paper, we propose a novel position-guided network (PosNet) to estimate the fresh weight of crop using oblique view images. Precisely, we first build the crop (i.e., lettuce) dataset by positioning the camera vertically in an oblique angle, with the Mask R-CNN framework trained for individual lettuces segmentation from the background. The segmented lettuce images are then fed into the PosNet for network training and testing purpose. By integrating the shallow feature extraction module and the position information extraction module, the proposed PosNet attains superior performance on assessing the lettuce fresh weight from oblique view images against other models. We further conducted the ablation studies and generalization testing to verify the efficacy and robustness of the proposed network model. Moreover, by comparing three variations (i.e., position, growth stage and posture orientation) of the lettuce separately and the sensitivity analysis of oblique shooting angles, our method demonstrates plausible adaptability for lettuce fresh weight estimation. Taking the accuracy, robustness, generalization capability, and adaptability into account, the integration of PosNet with oblique images not only enjoys great potentials in assessing the fresh weight, but also provides a practical support for agronomic management of crops cultivated in plant factories. [ABSTRACT FROM AUTHOR]

• The tensile strength and the Young's modulus of tobacco leaf were measured. • A discrete element model of tobacco leaf sample was developed. • The relationships between model outputs and the two most sensitive model parameters were well described using two equations. • The calibrated model was able to predict the tensile strength and Young's modulus of tobacco leaf with relative errors of less than 2%. The mechanical properties of tobacco leaf are very important for the research and design of tobacco harvesting machines. A numerical model was developed to simulate the tension behavior of tobacco leaf samples using the Discrete Element Method (DEM). The model was constructed with spherical particles bonded together. The model outputs were tensile strength (σ macro) and Young's modulus (E macro) of the leaf. Tensile tests were conducted to measure the same tensile properties of tobacco mesophyll samples obtained from different locations of the plant and at different sampling orientations. The model was calibrated and verified by comparing simulation results with the test data. Testing results showed that sampling location and orientation had marginal effects on the tensile properties of tobacco leaf. The average tensile strength was 0.57 MPa and the average Young's modulus was 3.50 MPa. The relationships between model outputs (σ macro and E macro) and the two most sensitive model parameters, Young's modulus of particles (E micro) and the critical tensile stress of bonds (σ micro) were well described using two equations. The calibrated values of σ micro and E micro were 8.02 and 23.07 MPa respectively using the equations and measured values of tensile strength and Young's modulus. The calibrated model was able to predict the tensile strength and Young's modulus of tobacco leaf with relative errors of less than 2 %. The proposed DEM model and method can be applied to other plant leaves in simulating their tensile behaviors and properties. [ABSTRACT FROM AUTHOR]