Precise canopy management is critical in vineyards for premium wine production because maximum crop load does not guarantee the best economic return for wine producers. The growers keep track of the number of grape bunches during the entire growing season for optimizing crop load per vine. Manual counting of grape bunches can be highly labor-intensive and error prone. Thus, an integrated, novel detection model, Swin-transformer-YOLOv5, was proposed for real-time wine grape bunch detection. The research was conducted on two varieties of Chardonnay and Merlot from July to September 2019. The performance of Swin-T-YOLOv5 was compared against commonly used detectors. All models were comprehensively tested under different conditions, including two weather conditions, two berry maturity stages, and three sunlight intensities. The proposed Swin-T-YOLOv5 outperformed others for grape bunch detection, with mean average precision (mAP) of up to 97% and F1-score of 0.89 on cloudy days. This mAP was ~44%, 18%, 14%, and 4% greater than Faster R-CNN, YOLOv3, YOLOv4, and YOLOv5, respectively. Swin-T-YOLOv5 achieved an R² of 0.91 and RMSE of 2.4 (number of grape bunches) compared with the ground truth on Chardonnay. Swin-T-YOLOv5 can serve as a reliable digital tool to help growers perform precision canopy management in vineyards.

Real-time detection of fruits in orchard environments is one of crucial techniques for many precision agriculture applications, including yield estimation and automatic harvesting. Due to the complex conditions, such as different growth periods and occlusion among leaves and fruits, detecting fruits in natural environments is a considerable challenge. A rapid citrus recognition method by improving the state-of-the-art You Only Look Once version 4 (YOLOv4) detector is proposed in this paper. Kinect V2 camera was used to collect RGB images of citrus trees. The Canopy algorithm and the K-Means++ algorithm were then used to automatically select the number and size of the prior frames from these RGB images. An improved YOLOv4 network structure was proposed to better detect smaller citrus under complex backgrounds. Finally, the trained network model was used for sparse training, pruning unimportant channels or network layers in the network, and fine-tuning the parameters of the pruned model to restore some of the recognition accuracy. The experimental results show that the improved YOLOv4 detector works well for detecting different growth periods of citrus in a natural environment, with an average increase in accuracy of 3.15% (from 92.89% to 96.04%). This result is superior to the original YOLOv4, YOLOv3, and Faster R-CNN. The average detection time of this model is 0.06 s per frame at 1920 × 1080 resolution. The proposed method is suitable for the rapid detection of the type and location of citrus in natural environments and can be applied to the application of citrus picking and yield evaluation in actual orchards.

The accuracy detection of individual citrus fruits in a citrus orchard environments is one of the key steps in realizing precision agriculture applications such as yield estimation, fruit thinning, and mechanical harvesting. This study proposes an improved object detection YOLOv5 model to achieve accurate the identification and counting of citrus fruits in an orchard environment. First, the latest visual attention mechanism coordinated attention module (CA) was inserted into an improved backbone network to focus on fruit-dense regions to recognize small target fruits. Second, an efficient two-way cross-scale connection and weighted feature fusion BiFPN in the neck network were used to replace the PANet multiscale feature fusion network, giving effective feature corresponding weights to fully fuse the high-level and bottom-level features. Finally, the varifocal loss function was used to calculate the model loss for better model training results. The results of the experiments on four varieties of citrus trees showed that our improved model proposed to this study could effectively identify dense small citrus fruits. Specifically, the recognized AP (average precision) reached 98.4%, and the average recognition time was 0.019 s per image. Compared with the original YOLOv5 (including deferent variants of n, s, m, l, and x), the increase in the average accuracy precision of the improved YOLOv5 ranged from 7.5% to 0.8% while maintaining similar average inference time. Four different citrus varieties were also tested to evaluate the generalization performance of the improved model. The method can be further used as a part in a vision system to provide technical support for the real-time and accurate detection of multiple fruit targets during mechanical picking in citrus orchards.

The leaf is the organ that is crucial for photosynthesis and the production of nutrients in plants; as such, the number of leaves is one of the key indicators with which to describe the development and growth of a canopy. The irregular shape and distribution of the blades, as well as the effect of natural light, make the segmentation and detection process of the blades difficult. The inaccurate acquisition of plant phenotypic parameters may affect the subsequent judgment of crop growth status and crop yield. To address the challenge in counting dense and overlapped plant leaves under natural environments, we proposed an improved deep-learning-based object detection algorithm by merging a space-to-depth module, a Convolutional Block Attention Module (CBAM) and Atrous Spatial Pyramid Pooling (ASPP) into the network, and applying the smooth_L1 function to improve the loss function of object prediction. We evaluated our method on images of five different plant species collected under indoor and outdoor environments. The experimental results demonstrated that our algorithm which counts dense leaves improved average detection accuracy of 85% to 96%. Our algorithm also showed better performance in both detection accuracy and time consumption compared to other state-of-the-art object detection algorithms.

Plant photosynthesis and biomass production are associated with the amount of intercepted light, especially the light distribution inside the canopy. Three virtual canopies (n = 80, 3.25 plants/m²) were constructed based on average leaf size of the digitized plant structures: ‘small leaf’ (98.1 cm²), ‘medium leaf’ (163.0 cm²) and ‘big leaf’ (241.6 cm²). The ratios of diffuse light were set in three gradients (27.8%, 48.7%, 89.6%). The simulations of light interception were conducted under different ratios of diffuse light, before and after the normalization of incident radiation. With 226.1% more diffuse light, the result of light interception could increase by 34.4%. However, the 56.8% of reduced radiation caused by the increased proportion of diffuse light inhibited the advantage of diffuse light in terms of a 26.8% reduction in light interception. The big-leaf canopy had more mutual shading effects, but its larger leaf area intercepted 56.2% more light than the small-leaf canopy under the same light conditions. The small-leaf canopy showed higher efficiency in light penetration and higher light interception per unit of leaf area. The study implied the 3D structural model, an effective tool for quantitative analysis of the interaction between light and plant canopy structure.