ST-DETrack: Identity-Preserving Branch Tracking in Entangled Plant Canopies via Dual Spatiotemporal Evidence
This addresses the challenge of high-throughput phenotyping for plant researchers, though it is incremental as it builds on existing tracking methods with specific enhancements.
The paper tackled the problem of tracking individual plant branches in time-series imagery within entangled canopies, achieving a Branch Matching Accuracy of 93.6%, which significantly outperformed baselines by up to 28.9 percentage points.
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.