WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation
This provides a new benchmark for researchers in agricultural computer vision to develop and test algorithms for detecting green walnuts under varying conditions, though it is incremental as it applies existing methods to new data.
The authors tackled the lack of a dataset for green walnuts in agricultural computer vision by creating WalnutData, a UAV remote sensing dataset with 30,240 images and 706,208 instances across four categories based on lighting and occlusion, and established baseline standards by evaluating mainstream algorithms on it.
The UAV technology is gradually maturing and can provide extremely powerful support for smart agriculture and precise monitoring. Currently, there is no dataset related to green walnuts in the field of agricultural computer vision. Thus, in order to promote the algorithm design in the field of agricultural computer vision, we used UAV to collect remote-sensing data from 8 walnut sample plots. Considering that green walnuts are subject to various lighting conditions and occlusion, we constructed a large-scale dataset with a higher-granularity of target features - WalnutData. This dataset contains a total of 30,240 images and 706,208 instances, and there are 4 target categories: being illuminated by frontal light and unoccluded (A1), being backlit and unoccluded (A2), being illuminated by frontal light and occluded (B1), and being backlit and occluded (B2). Subsequently, we evaluated many mainstream algorithms on WalnutData and used these evaluation results as the baseline standard. The dataset and all evaluation results can be obtained at https://github.com/1wuming/WalnutData.