Exploiting Boundary Loss for the Hierarchical Panoptic Segmentation of Plants and Leaves

TL;DR

This paper introduces a hierarchical panoptic segmentation method for precision agriculture that improves leaf and weed segmentation accuracy by using boundary and focal loss, enhancing plant monitoring and resource application.

Contribution

The paper presents a novel hierarchical segmentation approach incorporating boundary loss to improve small instance segmentation and leaf counting in agricultural imagery.

Findings

Achieved a PQ+ of 81.89 on standard dataset

Improved leaf-counting accuracy

Enhanced segmentation of small instances like leaves and weeds

Abstract

Precision agriculture leverages data and machine learning so that farmers can monitor their crops and target interventions precisely. This enables the precision application of herbicide only to weeds, or the precision application of fertilizer only to undernourished crops, rather than to the entire field. The approach promises to maximize yields while minimizing resource use and harm to the surrounding environment. To this end, we propose a hierarchical panoptic segmentation method that simultaneously determines leaf count (as an identifier of plant growth)and locates weeds within an image. In particular, our approach aims to improve the segmentation of smaller instances like the leaves and weeds by incorporating focal loss and boundary loss. Not only does this result in competitive performance, achieving a PQ+ of 81.89 on the standard training set, but we also demonstrate we can improve leaf-counting accuracy with our method. The code is available at https://github.com/madeleinedarbyshire/HierarchicalMask2Former.