Tomato Instance Segmentation Dataset

The current agricultural field faces challenges in crop monitoring and pest and disease identification. Traditional manual detection methods are inefficient and prone to errors. Existing solutions often fail to provide high-precision segmentation when dealing with complex environments and multiple crops. This dataset aims to provide high-quality tomato instance segmentation data to help researchers and developers improve model performance in practical applications. Data collection is mainly carried out using high-resolution cameras in greenhouse and field environments, ensuring coverage of tomato samples at different growth stages and environmental conditions. We use quality control measures such as multiple rounds of annotation and consistency checks to ensure data accuracy and reliability. The data is stored in JPG format for images, with annotation information organized in JSON format, facilitating subsequent model training and evaluation.