Finding Berries: Segmentation and Counting of Cranberries using Point Supervision and Shape Priors
This work addresses yield estimation for cranberry farmers, but it is incremental as it builds on existing segmentation and counting techniques with domain-specific adaptations.
The paper tackles the problem of cranberry yield estimation and sun exposure prediction by developing a deep learning method for simultaneous segmentation and counting using low-cost point supervision and shape priors, achieving improvements of over 6.74% in segmentation and 22.91% in counting compared to state-of-the-art methods.
Precision agriculture has become a key factor for increasing crop yields by providing essential information to decision makers. In this work, we present a deep learning method for simultaneous segmentation and counting of cranberries to aid in yield estimation and sun exposure predictions. Notably, supervision is done using low cost center point annotations. The approach, named Triple-S Network, incorporates a three-part loss with shape priors to promote better fitting to objects of known shape typical in agricultural scenes. Our results improve overall segmentation performance by more than 6.74% and counting results by 22.91% when compared to state-of-the-art. To train and evaluate the network, we have collected the CRanberry Aerial Imagery Dataset (CRAID), the largest dataset of aerial drone imagery from cranberry fields. This dataset will be made publicly available.