Grape is one of the major fruit crops in agricultural production. Manual cultivation cannot fully meet the large-scale production in recent years, due to its labor intensity, high costs, and low efficiency. Mechanical harvesting is often required for grape harvesting in the sustainable industry. Therefore, mechanization and intelligent automation can be very crucial to accelerate the cultivation. Point cloud semantic segmentation can be expected to serve as the unmanned harvesting, accurate fruit localization, and precise cutting in the context of agricultural intelligent production. However, the dense point cloud data has been widely used in the semantic segmentation in agricultural scenarios, which is difficult and costly to acquire. Sparse point cloud data can often lead to suboptimal segmentation in the practical implementation of intelligent harvesting. In this study, the point cloud semantic segmentation (called SP-Transformer) was introduced to incorporate the PointNet algorithm with a transformer multi-head self-attention mechanism. The sparse data was also selected. The SP-Transformer divided the point cloud into multi-level windows, enabling the attention mechanism to focus on the local features within each window. A multi-scale fusion strategy was employed to combine the dense and sparse features in the receptive field, and then capture the long-range contextual dependencies. Additionally, the high-level feature embedding was applied at the initial stage of the attention in order to enhance the segmentation performance of the sparse point clouds. Specifically, the three-dimensional space was first partitioned into non-overlapping cubic windows, with the points distributed across different cubic windows. Each query point was considered only the neighboring points within the same cubic window. The independent multi-head self-attention operations were performed within each window. Since the point cloud was divided into small windows, the receptive field of each query point was limited inherently. The cross-window communication was introduced to shift the window between two consecutive Transformer blocks by half the window size, thereby increasing the contextual connections for the receptive field. The input point cloud was divided into non-overlapping cubic windows using a predefined window size (WS). The data set of points (KDEN) within the same cubic window was identified in each query point (QI). Simultaneously, the input point cloud was downsampled to construct a sparse sampling window, thus dividing the downsampled space into non-overlapping cubic windows with a size of twice the WS. The set of points (KSPA) was the larger cubic window of the QI. Finally, the two sampling sets were combined to form the final sampling point set, which was used for further processing. Both local and global features were effectively captured, even in the sparse point cloud data. Experimental results on a grape dataset demonstrated the effectiveness of the SP-Transformer, with an average accuracy of 89.9%, which was 4.4 percentage points higher than PointNet++ and 1.5 percentage points higher than Point Transformer. The segmentation accuracy reached 81.1% for the grape classes, with an average intersection over union (IoU) of 82.8%. To validate the robustness of the model, the point cloud completion algorithm (PENet) was employed to densify the point cloud. The point cloud density increased from approximately 60 000 points to around 500 000 points. A comparison was performed on the dense and sparse data. The SP-Transformer was trained to evaluate the real-time performance and segmentation accuracy. The results indicate that the SP-Transformer maintained the robust segmentation performance, even for the low-density point clouds, thus outperforming traditional PointNet++ in terms of both accuracy and efficiency. The SP-Transformer represented a significant advancement in the point cloud semantic segmentation, particularly in the agricultural applications where sparse point cloud data was prevalent. The multi-head self-attention mechanism and multi-scale fusion strategy effectively solved the challenges posed by sparse data, enabling more accurate and efficient segmentation. As such, the intelligent harvesting was enhanced to accurately locate and segment the fruits, thereby reducing the labor costs for high operational efficiency. Moreover, the SP-Transformer also shared the broad implications beyond agricultural applications, particularly on the sparse point cloud data in autonomous driving, robotics, and environmental monitoring. The cross-window communication and high-level feature embedding can provide a robust framework to capture both local and global features. A versatile tool can also be used in various tasks of computer vision. In conclusion, the SP-Transformer can be expected to serve as a powerful and efficient solution for the point cloud semantic segmentation in agricultural intelligent harvesting. The sparse data can be utilized to capture the long-range contextual dependencies for more accurate and reliable intelligent harvesting. The high accuracy of the segmentation on the sparse point cloud data can greatly contribute to the advancement of computer vision in the field of precision agriculture.

Plant phenotyping has been widely used to quantitatively describe the plant's anatomical, ontogenetical, physiological, and biochemical properties. However, traditional measurement can often pose some challenges in recent years, due to the destructive nature, subjectivity, high costs, and operational complexities, particularly with three-dimensional measurement equipment. In this study, an advanced measurement approach was introduced for plant phenotypic parameters using an improved version of the Neural Radiance Field (NeRF), termed L-NeRF. Capturing image data from a multitude of perspectives and harnessing the prowess of L-NeRF technology for three-dimensional reconstruction has unlocked a new paradigm in the non-destructive acquisition of essential plant phenotypic parameters. This method has illuminated the path to obtaining critical measurements such as plant height, leaf width, and leaf length with unprecedented accuracy. The Prosopis juliflora, serving as a case study within a meticulously controlled indoor experimental environment, has yielded results that are a testament to the method's precision. The determination coefficients (R²) for leaf width, leaf length, and plant height are nothing short of remarkable, with values of 0.9037, 0.7827, and 0.8516, respectively. These high R² values are a clear indication of the strong correlation between the measured parameters and their true values, highlighting the method's reliability and accuracy. In stark contrast to the traditional Structure from Motion (SFM) visual reconstruction techniques, the L-NeRF technology has demonstrated a significant acceleration in the reconstruction process, reducing the time by an average of 30%. Moreover, it has substantially improved model accuracy, evidenced by a nearly 45% reduction in the standard deviation of model precision. These enhancements are not just quantitative—they represent a qualitative leap forward in the efficiency and precision of plant phenotyping. The experimental outcomes not only validate the efficacy and practicality of L-NeRF technology in measuring plant phenotypic parameters but also highlight its potential to significantly augment research efficiency and precision. The implications of these findings are far-reaching, opening the door to future studies that will explore a wider array of plant species, thereby expanding the method's applicability and versatility. The significance of this research extends beyond the immediate context of the study. It heralds the potential to revolutionize phenotyping in plant biology. By streamlining data acquisition and enhancing the accuracy of measurements, L-NeRF technology is poised to elevate the standards of plant phenotyping research. The pursuit of a more comprehensive dataset will contribute to a deeper understanding of plant phenotypic diversity, paving the way for innovative approaches in agricultural and botanical studies. Furthermore, the application of L-NeRF technology could extend to other domains of biological research, such as zoology, medical imaging, and environmental science. Its ability to provide high-resolution, three-dimensional data sets could prove invaluable in these fields, offering new insights and possibilities for research and application. In conclusion, the advent of L-NeRF technology for 3D reconstruction in plant phenotyping is a significant milestone. It represents a paradigm shift towards more efficient and accurate data acquisition methods, which will undoubtedly contribute to the advancement of scientific knowledge and the development of innovative solutions in agriculture and beyond. The non-destructive plant phenotyping techniques have promising potential for future innovations in the field of agricultural science and technology. The finding can also offer a novel approach to transforming plant phenotypic studies into breeding programs.

Accurate and rapid estimation of spatial posture is crucial to monitoring the behavior in group-housed livestock. Among them, 3D posture estimation can offer precise spatial data in the conditions of occlusion, compared with the traditional 2D. The current techniques of 3D posture estimation are primarily applied in human and autonomous driving fields, thus depending mainly on expensive measurement equipment and datasets. However, it is still challenging for animal behavior and management at present. Therefore, it is urgently needed for the low-cost and efficient measurement of animal behavior posture. In this study, a general approach was proposed to estimate the 3D posture of livestock using binocular stereo matching. Firstly, a modified model of stereo matching was employed to obtain the depth information using deep learning. Then, a top-down 2D posture model was used to extract the target bounding boxes and then detect the key points. Finally, the locations of key points were mapped back to the image space and then fused with the stereo-matching model for the 3D posture information. Since the matching accuracy depended on the precise depth information, the main challenges in stereo matching were attributed to the thin structure and weak texture matching. ACLNet stereo matching model was constructed using attention mechanism and ConvGRU iterative refinement. The relative depth layers of image textures were encoded to restrict the attention of the model to the areas near the true disparity. The high-precision depth information was gradually recovered in a residual manner. Ablation experiments and generalization tests were carried out on the Scene Flow dataset and the Middlebury dataset, respectively, in order to validate the effectiveness of the ACLNet model. The results show that the ACLNet model was achieved in an endpoint error (EPE) of 0.45 on the Scene Flow dataset, with a reduction of 0.37 pixels, compared with the baseline model without attention and ConvGRU mechanisms. Better generalization was also performed on real-world datasets, such as Middlebury. The EPE was 0.56 on the goat depth dataset; The mean per joint position error (MPJPE) on the goat 3D posture test set reached 45.7 mm in the improved model. There was a decrease of 21.1 mm, compared with the baseline. Strong generalization and versatility were obtained to accurately estimate the livestock 3D posture without additional training. The 3D posture estimation experiments were also verified to take the goats as test subjects. Binocular images were only required to accurately obtain the 3D posture. The feasibility of high-precision 3D posture estimation on livestock was then validated using a simple binocular system. The finding can provide a viable solution to accurate 3D posture estimation using low-cost stereo cameras.