Datasets
Lincolnbeet dataset
Object detection, item occlusion, small objects
The lincolnbeet dataset is an object detection dataset designed to encourage research in the identification of items in environments with high levels of occlusion, and in the development of better approaches to evaluate object detection models in practical scenarios. This dataset was introduced in the paper: "Towards practical object detection for weed spraying in precision agriculture".
Riseholme 2021 dataset
Anomaly detection, one-class classification, agriculture
The Riseholme 2021 dataset dataset contains >3.5K images of strawberries at various growth stages along with anomalous instances.Our purpose of sharing this dataset publicly is to encourage more researchers to develop interests in fruit anomaly detection, which is one of the most promising tasks where AI/Robotic systems could help transform agriculture. For better facilitation, we offer not only a large amount of strawberry image data with basic analyses but the link to the written manuscript above that reports the detection performance of state-of-the-art methods based on our experiments as benchmark. This dataset was introduced in the paper: "Self-supervised Representation Learning for Reliable Robotic Monitoring of Fruit Anomalies".