用时空双路追踪解决植物枝条纠缠中的身份混淆问题
ST-DETrack: Identity-Preserving Branch Tracking in Entangled Plant Canopies via Dual Spatiotemporal Evidence
- 融合空间几何与时间运动信息，动态调整追踪权重
- 在油菜数据集上分支匹配准确率达93.6%，领先基线28.9个百分点
- 适合长期跟踪复杂生长的植物个体，尤其适用于高通量表型分析
从时序影像中自动提取单个植物枝条对高通量表型分析至关重要，但因非刚性生长动态和枝条严重纠缠导致的身份碎片化而面临计算挑战。为克服阶段依赖性歧义，我们提出ST-DETrack，一种基于时空融合的双解码器网络，旨在从萌芽到开花阶段保持枝条身份一致性。该架构结合空间解码器（利用位置、角度等几何先验进行早期追踪）与时间解码器（通过运动一致性解决晚期遮挡），并通过自适应门控机制动态调节二者依赖关系，同时引入基于负向重力性的生物约束以缓解垂直生长带来的歧义。在油菜（Brassica napus）数据集上验证，ST-DETrack实现93.6%的分支匹配准确率（BMA），显著优于仅用空间或时间方法的基线，分别提升28.9和3.3个百分点。结果表明该方法在复杂动态植物结构中具备强健的身份持续追踪能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。