Sweet Potato Automatic Counting Dataset

In the agricultural sector, sweet potatoes, as one of the important crops, face challenges such as low efficiency in yield monitoring and management. Traditional manual counting methods are not only time-consuming and labor-intensive but also prone to errors. Existing automatic counting technologies largely rely on simple image processing algorithms, which fail to meet the demands for high precision and efficiency. This dataset aims to provide a rich sweet potato image dataset to promote the application of object detection algorithms in sweet potato counting, addressing the issues of low automation and insufficient counting accuracy. The dataset contains 5000 annotated sweet potato images collected using high-resolution cameras under various lighting and environmental conditions, ensuring data diversity and completeness. For quality control, a multi-round annotation and expert review mechanism is adopted to ensure the consistency and accuracy of data annotations. The data is stored in JPEG format and organized by image ID for convenient retrieval and use.