PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification

Abstract

Image-based high-throughput plant phenotyping leverages instance-level understanding of individual leaves growth over experimental time, yet existing datasets lack temporal depth and annotation consistency to jointly benchmark segmentation, tracking, and growth stage classification. We introduce PhenoLeaf-TS, a time-series dataset of 17,082 top-down RGB images spanning 21 Arabidopsis thaliana genotypes, totalling 318 plant replicates, each annotated with colour-coded leaf instance masks that maintain consistent identity throughout the growth sequence. We define three benchmark computer vision tasks with standardised protocols and evaluate 21 distinct models: 9 instance segmentation architect..