Biology-aware association for identity-consistent leaf tracking in top-down plant phenotyping
- 1School of Mathematics and Computer Science, Wuhan Polytechnic University
- 2School of Electrical and Electronic Engineering, Wuhan Polytechnic University
Abstract
Reliable leaf-level trait trajectories require identity-consistent tracking across growth, overlap, and appearance change. We introduce a biology-aware association module combining one appearance cue and three biological/geometric cues: spatial continuity, area-growth plausibility, and lifecycle plausibility. On CanolaTrack, adaptive weighting reduces ID switches from 228 to 126 ± 5 (44.7%; per-plant paired p = 1.6 × 10 ⁻⁵ , n = 37) and improves HOTA from 88.17 to 89.69 ± 0.10. Difficulty-stratified analysis shows IDSW reductions across all 12 CanolaTrack strata, averaging 40.0% versus Appearance-only and 45.0% versus LeafTrackNet. External association-only Arabidopsis and KOMATSUNA tests identify clean low-displacement GT-box regimes where centroid matching or Fixed bio-constraints are more reliable than zero-shot adaptive-weight transfer. These results provide an operating-envelope recommendation: adaptive weighting is most useful in dense CanolaTrack-like sequences, whereas Fixed bio-constraints or centroid matching are more reliable in clean low-displacement external regimes—where nearest-centroid assignment already resolves most associations, so that even a predictor retrained on the target domain does not surpass it. The limiting factor is thus primarily the association difficulty of the regime rather than dataset size.
Related
- Tracking 3D forest density dynamics in a mixed temperate forestusing occlusion-aware voxel transmittance and consistent multitemporalUAV-LiDAR
- From pose to behavior: SABER integrates identity-resolved multi-animal pose tracking with language-model-based behavioral factor discovery
- Integrating Non-Contact 3D Point Cloud Phenotyping and Multi-Locus Genome-Wide Association Studies to Uncover the Genetic Architecture of Body Size in Pigs
- Multi-biobank genome-wide association study of dermatochalasis implicates genes involved in skin biology and morphology
- Integrated phenotyping reveals coordinated physiological responses to cold, freezing, and recovery in Ramonda resurrection plants
BibTeX
@article{zhou2026biologyaware,
title = {{Biology-aware association for identity-consistent leaf tracking in top-down plant phenotyping}},
author = {Dongze Zhou and Cong Zhang},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1881413},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1881413/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Biology-aware association for identity-consistent leaf tracking in top-down plant phenotyping
AU - Dongze Zhou
AU - Cong Zhang
PY - 2026
DA - 2026/10/14
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1881413
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1881413/full
AB - Reliable leaf-level trait trajectories require identity-consistent tracking across growth, overlap, and appearance change. We introduce a biology-aware association module combining one appearance cue and three biological/geometric cues: spatial continuity, area-growth plausibility, and lifecycle plausibility. On CanolaTrack, adaptive weighting reduces ID switches from 228 to 126 ± 5 (44.7%; per-plant paired p = 1.6 × 10 ⁻⁵ , n = 37) and improves HOTA from 88.17 to 89.69 ± 0.10. Difficulty-stratified analysis shows IDSW reductions across all 12 CanolaTrack strata, averaging 40.0% versus Appearance-only and 45.0% versus LeafTrackNet. External association-only Arabidopsis and KOMATSUNA tests identify clean low-displacement GT-box regimes where centroid matching or Fixed bio-constraints are more reliable than zero-shot adaptive-weight transfer. These results provide an operating-envelope recommendation: adaptive weighting is most useful in dense CanolaTrack-like sequences, whereas Fixed bio-constraints or centroid matching are more reliable in clean low-displacement external regimes—where nearest-centroid assignment already resolves most associations, so that even a predictor retrained on the target domain does not surpass it. The limiting factor is thus primarily the association difficulty of the regime rather than dataset size.
SN - 1664-462X
ER -