Search

Light plays a crucial role in the growth of fruit trees, influencing not only nutrient absorption but also fruit appearance. Therefore, understanding fruit tree canopy light transmittance is essential for agricultural and forestry practices. However, traditional measurement methods, such as using a canopy analyzer, are time-consuming, labor-intensive, and susceptible to external influences, lacking convenience and automation. To address this issue, we propose a novel method based on point clouds to estimate light transmittance, with the Leaf Area Index (LAI) serving as the central link. Focusing on apple trees, we utilized handheld LiDAR for three-dimensional scanning of the canopy, acquiring point cloud data. Determining the optimal voxel size at 0.015 m via standardized point cloud mean spacing, we applied the Voxel-based Canopy Profile method (VCP) to estimate LAI. Subsequently, we established a function model between LAI and canopy light transmittance using a deep neural network (DNN), achieving an overall correlation coefficient R2 of 0.94. This model was then employed to estimate canopy light transmittance in dwarfed and densely planted apple trees. This approach not only provides an evaluation standard for pruning effects in apple trees but also represents a critical step towards visualizing and intelligentizing light transmittance.

The identification of branches and bud points is the key to intelligent pruning of dormant grapevine branches and precise positioning of the pruning point on the branch is an important prerequisite for robotic arm pruning. This study takes Cabernet Sauvignon wine grapes as the experimental object and proposes a depth image-based pruning point localization algorithm based on pruning rules. In order to solve the problem of bud recognition in complex backgrounds, this study adopts a detection method that combines semantic segmentation and target detection. Firstly, the semantic segmentation algorithm PSP-net is used to separate the branches and the main stem from the background and the separated image undergoes two kinds of processing: one is to skeletonize it using the Zhang–Suen thinning algorithm and the other is to identify the buds and obtain the center coordinates of the buds using the target-detection method YOLOv5; finally, combining with the depth information of the depth image, we use the coordinates of the buds to determine the location of the pruning point located on the skeleton image. The results show that PSP-net has better results in segmentation performance with mIoU reaching 83.73%. YOLOv5 performs better in target detection with mAP reaching 81.06% and F1 reaching 0.80. The accuracy of this method in determining the location of pruning points reaches 82.35%. It can provide a method for fruit tree pruning robots to determine the location of pruning points.

Aiming at the problem that the color of tea buds is highly similar to the background in complex scenes and it is difficult to identify the buds, this study proposed an improved YOLOv7 algorithm by replacing the original convolution blocks with Depth Separable Convolution (DS Conv) blocks, and adding Convolutional Block Attention Modules (CBAM) and Coordinate Attention (CA) modules. The method improved mean Average Precision (mAP) by 1.28% and mean Recall (mR) rate by 2.92%, the final mAP and mR reached 96.70% and 93.88%, respectively, and 30.62 Frame Per Second (FPS) of the improved model meets the requirements of real-time detection. The results show that the detection accuracy of the improved YOLOv7 algorithm for tea buds was higher than that of other target detection algorithms, and the detecting performance is not significantly affected by the light conditions, and the recognition accuracy of tea buds at each growing period was excellent and balanced. This study provides experience for the realization of intelligent tea picking.

Caragana korshinskii (C.K.) flat stubble residue is an abundant biomass energy source in China. Because branch cutting is closely related to the harvesting of forest biomass, it is practical for forestry production and ecological development to investigate the effects of cutting parameters on the peak cutting force and cutting energy consumption of C.K. branches. In this study, the effect of cutting parameters on the peak cutting force and cutting power consumption of branches was investigated by single-factor and multi-factor tests using an independently developed reciprocating cutting test bench, and an optimization model was established. The interaction term of average cutting speed and tool cutting edge inclination angle significantly affected the peak cutting force, while the interaction term of cutting clearance and wedge angle had a significant effect on the cutting energy consumption. The optimal combination of cutting parameters was an average cutting speed of 0.5 m/s, cutting clearance of 1.4 mm, wedge angle of 25°, and tool cutting edge inclination angle of 20°. With this combination of parameters, the corresponding peak cutting force was 644.38 N, and the cutting energy consumption was 5.90 J, which was less than 5% relative error between each performance index and the theoretical optimized value.

Rapid and precise tree Diameter at Breast Height (DBH) measurement is pivotal in forest inventories. While the recent advancements in LiDAR and Structure from Motion (SFM) technologies have paved the way for automated DBH measurements, the significant equipment costs and the complexity of operational procedures continue to constrain the ubiquitous adoption of these technologies for real-time DBH assessments. In this research, we introduce KAN-Forest, a real-time DBH measurement and key point localization algorithm utilizing RGB-D (Red, Green, Blue-Depth) imaging technology. Firstly, we improved the YOLOv5-seg segmentation module with a Channel and Spatial Attention (CBAM) module, augmenting its efficiency in extracting the tree’s edge features in intricate forest scenarios. Subsequently, we devised an image processing algorithm for real-time key point localization and DBH measurement, leveraging historical data to fine-tune current frame assessments. This system facilitates real-time image data upload via wireless LAN for immediate host computer processing. We validated our approach on seven sample plots, achieving bbAP50 and segAP50 scores of: 90.0%(+3.0%), 90.9%(+0.9%), respectively with the improved YOLOv5-seg model. The method exhibited a DBH estimation RMSE of 17.61∼54.96 mm (R2=0.937), and secured 78% valid DBH samples at a 59 FPS. Our system stands as a cost-effective, portable, and user-friendly alternative to conventional forest survey techniques, maintaining accuracy in real-time measurements compared to SFM- and LiDAR-based algorithms. The integration of WLAN and its inherent scalability facilitates deployment on Unmanned Ground Vehicles (UGVs) to improve the efficiency of forest inventory. We have shared the algorithms and datasets on Github for peer evaluations.

The tea industry is one of China’s most important industries. The picking of famous tea still relies on manual methods, with low efficiency, labor shortages and high labor costs, which restrict the development of the tea industry. These labor-intensive picking methods urgently need to be transformed into intelligent and automated picking. In response to difficulties in identification of tea buds and positioning of picking points, this study took the one bud with one leaf grade of the Fuyun 6 tea species under complex background as the research object, and proposed a method based on deep learning, combining object detection and semantic segmentation networks, to first detect the tea buds, then segment the picking area from the tea bud detection box, and then obtain the picking point from the picking area. An improved YOLOX-tiny model and an improved PSP-net model were used to detect tea buds and their picking areas, respectively; the two models were combined at the inference end, and the centroid of the picking area was taken as the picking point. The YOLOX-tiny model for tea bud detection was modified by replacing its activation function with the Mish function and using a content-aware reassembly of feature module to implement the upsampling operation. The detection effects of the YOLOX-tiny model were improved, and the mean average precision and recall rate of the improved model reached 97.42% and 95.09%, respectively. This study also proposed an improved PSP-net semantic segmentation model for segmenting the picking area inside a detection box. The PSP-net was modified by replacing its backbone network with the lightweight network MobileNetV2 and by replacing conventional convolution in its feature fusion part with Omni-Dimensional Dynamic Convolution. The model’s lightweight characteristics were significantly improved and its segmentation accuracy for the picking area was also improved. The mean intersection over union and mean pixel accuracy of the improved PSP-net model are 88.83% and 92.96%, respectively, while its computation and parameter amounts are reduced by 95.71% and 96.10%, respectively, compared to the original PSP-net. The method proposed in this study achieves a mean intersection over union and mean pixel accuracy of 83.27% and 86.51% for the overall picking area segmentation, respectively, and the detecting rate of picking point identification reaches 95.6%. Moreover, its detection speed satisfies the requirements of real-time detection, providing a theoretical basis for the automated picking of famous tea.

In order to improve the obstacle avoidance and endurance capability of quadrotor UAVs performing tasks such as forest inspection and rescue search, this paper proposes improvements to address the problems of too many traversed nodes, too many redundant corners, too-large turning angles and unsmooth generated paths in the traditional A* algorithm in path planning. The traditional A* algorithm is improved by using a segmented evaluation function with dynamic heuristic and weighting processing, a steering cost heuristic function based on heading angle deviation control, a redundant turning points removal strategy, and a quasi-uniform cubic b-spline. Through the test comparison of different complexity map scenarios, it is found that the improved A* algorithm reduces the number of traversed nodes by 64.87% on average, the total turning angle by 54.53% on average, the path search time by 49.64% on average, and the path length by 12.52% on average compared to the traditional A* algorithm, and there is no obvious turning point in the path. The real-world applicability of the improved A* algorithm is confirmed by comparing the effect of different algorithms on obstacle avoidance in a map of a real plantation forest environment.

Branch identification is key to the robotic pruning system for apple trees. High identification accuracy and the positioning of junction points between branch and trunk are important prerequisites for pruning with a robotic arm. Recently, with the development of deep learning, Transformer has been gradually applied to the field of computer vision and achieved good results. However, the effect of branch identification based on Transformer has not been verified so far. Taking Swin-T and Resnet50 as a backbone, this study detected and segmented the trunk, primary branch and support of apple trees on the basis of Mask R-CNN and Cascade Mask R-CNN. The results show that, when Intersection over Union (IoU) is 0.5, the bbox mAP and segm mAP of Cascade Mask R-CNN Swin-T are the highest, which are 0.943 and 0.940; as for the each category identification, Cascade Mask R-CNN Swin-T shows no significant difference with the other three algorithms in trunk and primary branch; when the identified object is a support, the bbox AP and segm AP of Cascade Mask R-CNN Swin-T is significantly higher than that of other algorithms, which are 0.879 and 0.893. Next, Cascade Mask R-CNN SW-T is combined with Zhang & Suen to obtain the junction point. Compared with the direct application of Zhang & Suen algorithm, the skeleton obtained by this method is advantaged by trunk diameter information, and its shape and junction points position are closer to the actual apple trees. This model and method can be applied to follow-up research and offer a new solution to the robotic pruning system for apple trees.

In order to investigate the cutting mechanical characteristics of Caragana korshinskii (C.k.) branches and explore the optimal combination of cutting parameters to support the subsequent equipment development, this paper explores the relationship between branch diameter D, average cutting speed v, wedge angle β, slip cutting angle α, cutting height h, cutting gap t, moisture content M and peak cutting force by using a homemade swing-cut branch cutting test bench with peak cutting force of branches as the target value under unsupported and supported cutting methods, respectively, through single-factor tests. Based on the single-factor test, v, β, α and t were selected as the test factors, and a multi-factor test was conducted with the peak cutting force as the target. Test result: The best combination of unsupported cutting in the range of multi-factor test is v for 3.315 m·s−1, β for 20°, α for 20°, when the peak cutting force is 95.690 N. Supported cutting multi-factor test range to get the best combination of v for 3.36 m·s−1, β for 20°, α for 20°, t for 1.38 mm, when the peak cutting force is 53.082 N. The errors of the predicted peak cutting force and the measured peak cutting force of the obtained model were 1.3% and 3.9%, respectively, which prove that the cutting parameters were optimized reliably. This research can provide a theoretical basis for subsequent development the C.k. harvesting equipment.

In order to reduce the labor intensity and improve the efficiency of pruning, this study designed a multi-section luffing apple pruning equipment suitable for apple orchards in hilly and mountainous areas of China. In the essay, the structure and working principle of the equipment are expounded, the cutter was analyzed, and the parameters were determined. Using the self-made test bench to simulate the field experiment, this study selected the ratio of cutting speed to feeding speed and feeding speed as the influencing factors and took the cut-off rate, cutting efficiency and cutting power as the objectives to carry out single factor experiment and quadratic regression orthogonal experiment. The test results show that the cutting power increases with the increase of ratio of cutting speed to feeding speed, and the cut-off rate and cutting efficiency first increase and then decrease. As the feeding speed increases, the cutting efficiency and power increase, and the cut-off rate decreases. When the cutoff rate was greater than 80%, the optimal combination of operating parameters was the feeding speed of 0.55 m/s and ratio of cutting speed to feeding speed of 1.29. Under this combination, the cut-off rate was 84.9%, the cutting efficiency was 13.1, and the cutting power was 175.7 W. The error between the predicted target value of the model and the average measured target value was less than 7%, so the test results are reliable. According to the obtained optimal operating parameters, the actual cutting experiment of the pruning equipment in the field was carried out, and the cutting rate was 96.3%, which meet the design requirements. This study can also meet the needs of mechanized pruning of fruit trees with different crown shapes, improve the applicability of pruning equipment, and provide support for the development of mechanized pruning equipment in China. [ABSTRACT FROM AUTHOR]