To address the challenging requirements of citrus detection in complex orchard environments, this paper proposes ACDNet (Adaptive Citrus Detection Network), a novel deep learning framework specifically designed for automated citrus harvesting. The proposed method introduces three key innovations: (1) Citrus-Adaptive Feature Extraction (CAFE) module that combines fruit-aware partial convolution with illumination-adaptive attention mechanisms to enhance feature representation with improved efficiency; (2) Dynamic Multi-Scale Sampling (DMS) operator that adaptively focuses sampling points on fruit regions while suppressing background interference through content-aware offset generation; and (3) Fruit-Shape Aware IoU (FSA-IoU) loss function that incorporates citrus morphological priors and occlusion patterns to improve localization accuracy. Extensive experiments on our newly constructed CitrusSet dataset, which comprises 2887 images capturing diverse lighting conditions, occlusion levels, and fruit overlapping scenarios, demonstrate that ACDNet achieves superior performance with mAP@0.5 of 97.5%, precision of 92.1%, and recall of 92.8%, while maintaining real-time inference at 55.6 FPS. Compared to the baseline YOLOv8n model, ACDNet achieves improvements of 1.7%, 3.4%, and 3.6% in mAP@0.5, precision, and recall, respectively, while reducing model parameters by 11% (to 2.67 M) and computational cost by 20% (to 6.5 G FLOPs), making it highly suitable for deployment in resource-constrained robotic harvesting systems. However, the current study is primarily validated on citrus fruits, and future work will focus on extending ACDNet to other spherical fruits and exploring its generalization under extreme weather conditions.

With the wide utilization of UAV in agricultural experiment and field management, plant protection UAV became a highly usage equipment for famers. Topdressing for pumpkin is important, when pumpkin fruit are expanding. It is difficult for farmers and other spraying machines to work on the farm, because all the fields is covered with leaves and stalks. A field test were launched to explore UAV working parameters on pumpkin topdressing, and distribution of droplets on face or back leave were measured to reflect the spraying quality and quantity of machine. During filed experiment, parameters of each flight was set by auto-flight system, and flight speed was stable. Through field experiment and data analysis, it was found that when the flying height was 2.5 m and the flying speed was 3 m/s, the total amount of droplet deposition reached the maximum, and the droplet attachment level on the back leaves was the highest. This parameters could be a guidance when using UAV for topdressing in pumpkin or other kinds of crops.