ST-DETrack: Identity-Preserving Branch Tracking in Entangled Plant Canopies via Dual Spatiotemporal Evidence

TL;DR

ST-DETrack is a novel dual-decoder neural network that preserves individual plant branch identities over time in complex, entangled canopies, improving high-throughput phenotyping accuracy.

Contribution

The paper introduces a dual-decoder architecture with adaptive gating and biological constraints to enhance branch tracking in entangled plant canopies.

Findings

Achieves 93.6% Branch Matching Accuracy on Brassica napus dataset

Outperforms spatial and temporal baselines by 28.9 and 3.3 percentage points

Demonstrates robustness in maintaining identity over complex plant growth stages

Abstract

Automated extraction of individual plant branches from time-series imagery is essential for high-throughput phenotyping, yet it remains computationally challenging due to non-rigid growth dynamics and severe identity fragmentation within entangled canopies. To overcome these stage-dependent ambiguities, we propose ST-DETrack, a spatiotemporal-fusion dual-decoder network designed to preserve branch identity from budding to flowering. Our architecture integrates a spatial decoder, which leverages geometric priors such as position and angle for early-stage tracking, with a temporal decoder that exploits motion consistency to resolve late-stage occlusions. Crucially, an adaptive gating mechanism dynamically shifts reliance between these spatial and temporal cues, while a biological constraint based on negative gravitropism mitigates vertical growth ambiguities. Validated on a Brassica napus dataset, ST-DETrack achieves a Branch Matching Accuracy (BMA) of 93.6%, significantly outperforming spatial and temporal baselines by 28.9 and 3.3 percentage points, respectively. These results demonstrate the method's robustness in maintaining long-term identity consistency amidst complex, dynamic plant architectures.