Self-Supervised Leaf Segmentation under Complex Lighting Conditions

TL;DR

This paper introduces a novel self-supervised framework for leaf segmentation in plant images, effectively handling complex lighting conditions and improving segmentation accuracy without requiring labeled data.

Contribution

It presents a combined self-supervised semantic segmentation, color correction, and leaf segmentation approach, advancing plant phenotyping methods with minimal supervision.

Findings

Effective leaf segmentation across different plant species

Robust performance under complex lighting conditions

Demonstrated generalizability of the self-supervised framework

Abstract

As an essential prerequisite task in image-based plant phenotyping, leaf segmentation has garnered increasing attention in recent years. While self-supervised learning is emerging as an effective alternative to various computer vision tasks, its adaptation for image-based plant phenotyping remains rather unexplored. In this work, we present a self-supervised leaf segmentation framework consisting of a self-supervised semantic segmentation model, a color-based leaf segmentation algorithm, and a self-supervised color correction model. The self-supervised semantic segmentation model groups the semantically similar pixels by iteratively referring to the self-contained information, allowing the pixels of the same semantic object to be jointly considered by the color-based leaf segmentation algorithm for identifying the leaf regions. Additionally, we propose to use a self-supervised color correction model for images taken under complex illumination conditions. Experimental results on datasets of different plant species demonstrate the potential of the proposed self-supervised framework in achieving effective and generalizable leaf segmentation.