Outlier Exposure for Open Set Crop Recognition From Multitemporal Image Sequences

When it comes to technology in agriculture, one of the most important aspects is farmland crop monitoring. However, in most cases, only the main crops are needed to be monitored by satellite images, due to their high territorial extension. Therefore, a semantic segmentation model for identifying plantations should correctly classify the majority classes and also automatically identify other unknown crops. Open set recognition (OSR) aims to embrace both of these causes, so that the model can be more robust in the wild. This work adapts the framework of outlier exposure (OE) for open set image segmentation. OE was evaluated by adding it to three distinct methods for open set segmentation: softmax thresholding, OpenPCS and OpenPCS++. We conducted several experiments to enrich the discussion of the impact of OE on the semantic segmentation of crop imagery. Our methodology achieved a consistent increase for OpenPCS and OpenPCS++ methods, with an improvement of up to 7.5% in terms of area under the receiver operating characteristic (AUROC) curve if compared to previous work.

Automated summary

When it comes to technology in agriculture, crop monitoring is a crucial aspect. A semantic segmentation model is proposed to identify plantations and classify main crops, while also automatically recognizing unknown crops. The framework of outlier exposure is adapted for open set image segmentation, resulting in significant improvement in semantic segmentation of crop imagery.