Unmanned aerial vehicles (UAVs) equipped with lightweight sensors, such as RGB cameras and LiDAR, have significant potential in precision agriculture, including object detection. Tassel detection in maize is an essential trait given its relevance as the beginning of the reproductive stage of growth and development of the plants. However, compared with general object detection, tassel detection based on RGB imagery acquired by UAVs is more challenging due to the small size, time-dependent variable shape, and complexity of the objects of interest. A novel algorithm referred to as YOLOv5-tassel is proposed to detect tassels in UAV-based RGB imagery. A bidirectional feature pyramid network is adopted for the path-aggregation neck to effectively fuse cross-scale features. The robust attention module of SimAM is introduced to extract the features of interest before each detection head. An additional detection head is also introduced to improve small-size tassel detection based on the original YOLOv5. Annotation is performed with guidance from center points derived from CenterNet to improve the selection of the bounding boxes for tassels. Finally, to address the issue of limited reference data, transfer learning based on the VisDrone dataset is adopted. Testing results for our proposed YOLOv5-tassel method achieved the mAP value of 44.7%, which is better than well-known object detection approaches, such as FCOS, RetinaNet, and YOLOv5.

Low-cost Unmanned Airborne Vehicles (UAVs) equipped with consumer-grade imaging systems have emerged as a potential remote sensing platform that could satisfy the needs of a wide range of civilian applications. Among these applications, UAV-based agricultural mapping and monitoring have attracted significant attention from both the research and professional communities. The interest in UAV-based remote sensing for agricultural management is motivated by the need to maximize crop yield. Remote sensing-based crop yield prediction and estimation are primarily based on imaging systems with different spectral coverage and resolution (e.g., RGB and hyperspectral imaging systems). Due to the data volume, RGB imaging is based on frame cameras, while hyperspectral sensors are primarily push-broom scanners. To cope with the limited endurance and payload constraints of low-cost UAVs, the agricultural research and professional communities have to rely on consumer-grade and light-weight sensors. However, the geometric fidelity of derived information from push-broom hyperspectral scanners is quite sensitive to the available position and orientation established through a direct geo-referencing unit onboard the imaging platform (i.e., an integrated Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS). This paper presents an automated framework for the integration of frame RGB images, push-broom hyperspectral scanner data and consumer-grade GNSS/INS navigation data for accurate geometric rectification of the hyperspectral scenes. The approach relies on utilizing the navigation data, together with a modified Speeded-Up Robust Feature (SURF) detector and descriptor, for automating the identification of conjugate features in the RGB and hyperspectral imagery. The SURF modification takes into consideration the available direct geo-referencing information to improve the reliability of the matching procedure in the presence of repetitive texture within a mechanized agricultural field. Identified features are then used to improve the geometric fidelity of the previously ortho-rectified hyperspectral data. Experimental results from two real datasets show that the geometric rectification of the hyperspectral data was improved by almost one order of magnitude.

Plant counting and location are essential for both plant breeding experiments and production agriculture. Stand count indicates the overall emergence of plants compared to the number of seeds that were planted, while location provides information on the associated variability within a plot or geographic area of a field. Deep learning has been successfully applied in various application domains, including plant phenotyping. This article proposes the use of deep learning techniques, more specifically, anchor-free detectors, to identify and count maize plants in RGB images acquired from unmanned aerial vehicles. The results were obtained using a modified CenterNet architecture, with validation performed against manual human annotation. Experimental results demonstrated an overall precision $>$95% for examples where training and testing were performed on the same field. Few-shot learning was also explored, where the trained network was 1) directly applied to the fields in other geographic areas and 2) updated using small quantities of training data from the other locations.

A grid-based version of the Soil and Water Assessment Tool (SWAT) model, SWATgrid, was developed to perform simulations on a regularized grid with a modified routing algorithm to allow interaction between grid cells. However, SWATgrid remains largely untested with little understanding of the impact of user-defined grid cell size. Moreover, increases in computation time effectively preclude direct calibration of SWATgrid. To gain insight into defining appropriate strategies for future development and application of SWATgrid, this research considers the simulated differences between commonly-employed hydrologic response unit (HRU)-based and grid-based SWAT models and the implications of resolution on their simulation and calibrated parameter values for a Midwestern, agricultural watershed. Results indicate that: (1) the gridded approach underpredicted simulated streamflow between 5% and 50% relative to the baseline model, depending upon the input spatial resolution and routing algorithm implemented; (2) gridded models generally underpredicted total phosphorous and sediment loads while overpredicting nitrate load; and (3) ranges of values of optimized model parameters remained similar up to 90 m. Results from this analysis should help in defining future applications of the SWATgrid model and the effects of differing spatial resolution of the model input data.

High-throughput phenotyping using high spatial, spectral, and temporal resolution remote sensing (RS) data has become a critical part of the plant breeding chain focused on reducing the time and cost of the selection process for the “best” genotypes with respect to the trait(s) of interest. In this paper, the potential of accurate and reliable sorghum biomass prediction using visible and near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data as well as light detection and ranging (LiDAR) data acquired by sensors mounted on UAV platforms is investigated. Predictive models are developed using classical regression-based machine learning methods for nine experiments conducted during the 2017 and 2018 growing seasons at the Agronomy Center for Research and Education (ACRE) at Purdue University, Indiana, USA. The impact of the regression method, data source, timing of RS and field-based biomass reference data acquisition, and the number of samples on the prediction results are investigated. R² values for end-of-season biomass ranged from 0.64 to 0.89 for different experiments when features from all the data sources were included. Geometry-based features derived from the LiDAR point cloud to characterize plant structure and chemistry-based features extracted from hyperspectral data provided the most accurate predictions. Evaluation of the impact of the time of data acquisition during the growing season on the prediction results indicated that although the most accurate and reliable predictions of final biomass were achieved using remotely sensed data from mid-season to end-of-season, predictions in mid-season provided adequate results to differentiate between promising varieties for selection. The analysis of variance (ANOVA) of the accuracies of the predictive models showed that both the data source and regression method are important factors for a reliable prediction; however, the data source was more important with 69% significance, versus 28% significance for the regression method.