The accurate and rapid acquisition of fruit tree canopy parameters is fundamental for achieving precision operations in orchard robotics, including accurate spraying and precise fertilization. In response to the issue of inaccurate citrus tree canopy segmentation in complex orchard backgrounds, this paper proposes an improved DeepLabv3+ model for fruit tree canopy segmentation, facilitating canopy parameter calculation. The model takes the RGB-D (Red, Green, Blue, Depth) image segmented canopy foreground as input, introducing Dilated Spatial Convolution in Atrous Spatial Pyramid Pooling to reduce computational load and integrating Convolutional Block Attention Module and Coordinate Attention for enhanced edge feature extraction. MobileNetV3-Small is utilized as the backbone network, making the model suitable for embedded platforms. A citrus tree canopy image dataset was collected from two orchards in distinct regions. Data from Orchard A was divided into training, validation, and test set A, while data from Orchard B was designated as test set B, collectively employed for model training and testing. The model achieves a detection speed of 32.69 FPS on Jetson Xavier NX, which is six times faster than the traditional DeepLabv3+. On test set A, the mIoU is 95.62%, and on test set B, the mIoU is 92.29%, showing a 1.12% improvement over the traditional DeepLabv3+. These results demonstrate the outstanding performance of the improved DeepLabv3+ model in segmenting fruit tree canopies under different conditions, thus enabling precise spraying by orchard spraying robots.

This study presents a systematic optimization framework of 3HW36 Mountain Orchard Rail-Mounted Wind-Driven Plant Protection Equipment through integrated computational fluid dynamics (CFD), wind field validation, and field experiments. The CFD model demonstrated high fidelity with experimental measurements, achieving a mean absolute percentage error of 9.2% across 15 sampling points and resolving critical airflow–canopy interactions through a novel porous media approach. Field trials in Fujian citrus orchards quantified the following optimal operational parameters: 29 m/s airflow velocity (23% velocity attenuation through mid-canopy), 15° blower pitch angles (89.6% upper-middle canopy coverage), and 0.5 m/s railcar speed. The equipment’s terrain adaptability was validated through sustained post-canopy velocities (>6.4 m/s) and 62% momentum retention at 4.2 m downstream, addressing critical limitations in mountainous pesticide application. These findings establish a replicable protocol for precision canopy management, balancing agrochemical efficacy with environmental stewardship in complex orchard ecosystems.