Field Cucumber Picking Scene Recognition Dataset

Current agriculture faces challenges such as low production efficiency and high manual picking costs, especially in the picking process of economic crops like cucumbers. Traditional methods bear issues like high labor intensity and low efficiency. Existing solutions mostly focus on simple image processing and manual annotation, lacking systematic and comprehensive approaches, resulting in insufficient accuracy and practicality of target detection. To address these technical issues, this dataset aims to provide a high-quality, high-annotation-accuracy image collection of cucumber picking scenes, supporting automated target detection and intelligent analysis. Data collection was conducted using drones and high-definition cameras under different lighting and climate conditions, ensuring data diversity and representativeness. We implemented multiple rounds of annotation and expert review to ensure consistency and accuracy, with the final data stored in JPG format, organized by image ID for easy subsequent use and analysis. The core advantage of this dataset is its high annotation accuracy and consistency of up to 95%. In terms of technological innovation, novel image enhancement techniques were adopted, significantly improving the model's generalization capability. The application value lies in the intelligent picking scheme, expected to improve picking efficiency by over 30% while reducing labor costs, thus providing smarter and more efficient solutions for agricultural production.