Automatic detection of intact tomatoes on plants is highly expected for low-cost and optimal management in tomato farming. Mature tomato detection has been wildly studied, while immature tomato detection, especially when occluded with leaves, is difficult to perform using traditional image analysis, which is more important for long-term yield prediction. Therefore, tomato detection that can generalize well in real tomato cultivation scenes and is robust to issues such as fruit occlusion and variable lighting conditions is highly desired. In this study, we build a tomato detection model to automatically detect intact green tomatoes regardless of occlusions or fruit growth stage using deep learning approaches. The tomato detection model used faster region-based convolutional neural network (R-CNN) with Resnet-101 and transfer learned from the Common Objects in Context (COCO) dataset. The detection on test dataset achieved high average precision of 87.83% (intersection over union ≥ 0.5) and showed a high accuracy of tomato counting (R² = 0.87). In addition, all the detected boxes were merged into one image to compile the tomato location map and estimate their size along one row in the greenhouse. By tomato detection, counting, location and size estimation, this method shows great potential for ripeness and yield prediction.

To realize autonomous navigation and intelligent management in orchards, vehicles require real-time positioning and globally consistent mapping of surroundings with sufficient information. However, the unstructured and unstable characteristics of orchards present challenges for accurate and stable localization and mapping. This study proposes a framework fusing LiDAR, visual, and inertial data by using the extended Kalman filter (EKF) to achieve real-time localization and colorful LiDAR point-cloud mapping in orchards. First, the multi-sensor data were integrated into a loosely-coupled framework based on the EKF to improve the pose estimation, with the pose estimation from LiDAR and gyroscope acting as the predictions, while that from visual-inertial odometry acting as the observations. Then, the Loam_Livox algorithm was enhanced by incorporating color from the image into the LiDAR point cloud, enabling the real-time construction of a three-dimensional colorful map of the orchard. The method demonstrates a high accuracy for localization in different motion trajectories (average RMSE: 0.3436) and different scenarios (average RMSE: 0.1230) and clear and efficient construction of three-dimensional colorful mapping, taking only 75.01 ms in localization and mapping for a frame of LiDAR point cloud. This indicates the proposed method has a great potential for the autonomous navigation of agricultural vehicles.

Crop uniformity is a comprehensive indicator used to describe crop growth and is important for assessing crop yield and biomass potential. However, there is still a lack of continuous monitoring of uniformity throughout the growing season to explain their effects on yield and biomass. Therefore, this paper proposed a wheat uniformity quantification method based on unmanned aerial vehicle imaging technology to monitor and analyze the dynamic changes in wheat uniformity. The leaf area index (LAI), soil plant analysis development (SPAD), and fractional vegetation cover were estimated from hyperspectral images, while plant height was estimated by a point cloud model from RGB images. Based on these 4 agronomic parameters, a total of 20 uniformity indices covering multiple growing stages were calculated. The changing trends in the uniformity indices were consistent with the results of visual interpretation. The uniformity indices strongly correlated with yield and biomass were selected to construct multiple linear regression models for estimating yield and biomass. The results showed that Pielou's index of LAI had the strongest correlation with yield and biomass, with correlation coefficients of -0.760 and -0.801, respectively. The accuracies of the yield (coefficient of determination [R ²] = 0.616, root mean square error [RMSE] = 1.189 Mg/ha) and biomass estimation model (R ² = 0.798, RMSE = 1.952 Mg/ha) using uniformity indices were better than those of the models using the mean values of the 4 agronomic parameters. Therefore, the proposed uniformity monitoring method can be used to effectively evaluate the temporal and spatial variations in wheat uniformity and can provide new insights into the prediction of yield and biomass.

The leaf phenotypic traits of plants have a significant impact on the efficiency of canopy photosynthesis. However, traditional methods such as destructive sampling will hinder the continuous monitoring of plant growth, while manual measurements in the field are both time-consuming and laborious. Nondestructive and accurate measurements of leaf phenotypic parameters can be achieved through the use of 3D canopy models and object segmentation techniques. This paper proposed an automatic branch–leaf segmentation pipeline based on lidar point cloud and conducted the automatic measurement of leaf inclination angle, length, width, and area, using pear canopy as an example. Firstly, a three-dimensional model using a lidar point cloud was established using SCENE software. Next, 305 pear tree branches were manually divided into branch points and leaf points, and 45 branch samples were selected as test data. Leaf points were further marked as 572 leaf instances on these test data. The PointNet++ model was used, with 260 point clouds as training input to carry out semantic segmentation of branches and leaves. Using the leaf point clouds in the test dataset as input, a single leaf instance was extracted by means of a mean shift clustering algorithm. Finally, based on the single leaf point cloud, the leaf inclination angle was calculated by plane fitting, while the leaf length, width, and area were calculated by midrib fitting and triangulation. The semantic segmentation model was tested on 45 branches, with a mean Precision_sem, mean Recall_sem, mean F1-score, and mean Intersection over Union (IoU) of branches and leaves of 0.93, 0.94, 0.93, and 0.88, respectively. For single leaf extraction, the Precision_ins, Recall_ins, and mean coverage (mCoV) were 0.89, 0.92, and 0.87, respectively. Using the proposed method, the estimated leaf inclination, length, width, and area of pear leaves showed a high correlation with manual measurements, with correlation coefficients of 0.94 (root mean squared error: 4.44°), 0.94 (root mean squared error: 0.43 cm), 0.91 (root mean squared error: 0.39 cm), and 0.93 (root mean squared error: 5.21 cm²), respectively. These results demonstrate that the method can automatically and accurately measure the phenotypic parameters of pear leaves. This has great significance for monitoring pear tree growth, simulating canopy photosynthesis, and optimizing orchard management.

Summary: Orchard fruits such as pear and apple are important for ensuring global food security and agricultural economy as they not only provide essential nutrients, but also support biodiversity and ecosystem services. Breeders, growers and plant researchers constantly study desirable tree morphological features and floral characteristics to ensure fruit production and quality. Still, traditional orchard phenotyping is often laborious, limited in scale and prone‐to‐error, resulting in many attempts to develop reliable and scalable toolkits to address this challenge. Here, we present OrchardQuant‐3D, an analytic pipeline for automating tree‐level analysis of key canopy and floral traits for different types of fruit orchards. We first built a data fusion algorithm to register 3D point clouds collected by both drones (for colour signals) and Light Detection And Ranging (LiDAR, for precise spatial properties), reconstructing high‐quality 3D orchard models at different growth stages. Then, we utilised precise global navigation satellite system signals to position trees in orchards with millimetre‐level accuracy, enabling tree‐level analysis of key canopy (e.g. crown volume and the number or branches) and floral traits (e.g. blossom clusters and volumes) using 3D computer vision, complex graph theory and feature engineering techniques. Equipped with the OrchardQuant‐3D pipeline, we successfully measured varietal differences of four pear cultivars from a small pear orchard in Nanjing China, followed by a scale‐up study that surveyed 3D tree morphologies, key floral and fruit traits from 1104 apple trees in an orchard in East Malling, United Kingdom. To the best of our knowledge, such a multi‐source, comprehensive and expandable methodology has not yet been introduced to this important research domain. Hence, we believe that our work demonstrates a step change in our ability to conduct scalable 3D orchard phenotyping, which is highly valuable to advance orchard breeding, precise tree management and orchard research greatly to sustain fruit tree production in a rapidly changing climate.

Detailed observation of the phenotypic changes in rice panicle substantially helps us to understand the yield formation. In recent studies, phenotyping of rice panicles during the heading–flowering stage still lacks comprehensive analysis, especially of panicle development under different nitrogen treatments. In this work, we proposed a pipeline to automatically acquire the detailed panicle traits based on time-series images by using the YOLO v5, ResNet50, and DeepSORT models. Combined with field observation data, the proposed method was used to test whether it has an ability to identify subtle differences in panicle developments under different nitrogen treatments. The result shows that panicle counting throughout the heading–flowering stage achieved high accuracy (R² = 0.96 and RMSE = 1.73), and heading date was estimated with an absolute error of 0.25 days. In addition, by identical panicle tracking based on the time-series images, we analyzed detailed flowering phenotypic changes of a single panicle, such as flowering duration and individual panicle flowering time. For rice population, with an increase in the nitrogen application: panicle number increased, heading date changed little, but the duration was slightly extended; cumulative flowering panicle number increased, rice flowering initiation date arrived earlier while the ending date was later; thus, the flowering duration became longer. For a single panicle, identical panicle tracking revealed that higher nitrogen application led to earlier flowering initiation date, significantly longer flowering days, and significantly longer total duration from vigorous flowering beginning to the end (total DBE). However, the vigorous flowering beginning time showed no significant differences and there was a slight decrease in daily DBE.