Research map / Video / Video segmentation and tracking
Joint Multi-Leaf Segmentation, Alignment, and Tracking for Fluorescence Plant Videos
Xi Peng Yin, Xiaoming Liu, Jin Chen, David Kramer
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use joint alignment and tracking with new leaf generation instead of baseline chamfer matching | Proposed · Fluorescence plant videos | SBD: 61.0 -> 65.2 | Improved |
| use proposed tracking instead of prior tracking work (modified G3, new candidates) | Proposed · Fluorescence plant videos | SBD: 64.4 -> 65.2 | Improved |
| use proposed method instead of prior work in execution time | Proposed · Fluorescence plant videos | time (sec/image): 16.42 -> 2.15 | Improved |
| modified G3 and added candidate generation cost time | Proposed · Fluorescence plant videos | time (sec/image): 1.98 -> 2.15 | Hurt |
| apply method to LSC set A3 instead of prior work | Ours · LSC A3 | SBD: 61.8 -> 76.1 | Improved |
| apply method to LSC set A1 instead of prior work | Ours · LSC A1 | SBD: 74.2 -> 78.5 | Improved |
| apply method to LSC set A2 instead of prior work | Ours · LSC A2 | SBD: 80.6 -> 77.4 | Hurt |
| add J3 term (lambda2 from 0 up to 300) in alignment (ablation) | Alignment · Fluorescence videos (training) | accuracy | Improved |
| add lambda1 term (0 to 4) in alignment (ablation) | Alignment · Fluorescence videos (training) | accuracy | Improved |
| increase number of templates in H, S or R (ablation) | Alignment · Fluorescence videos (training) | accuracy | Improved |
| add tracking terms mu1 and mu2 (ablation) | Tracking · Fluorescence videos (training) | accuracy | Improved |
| increase iterations D between frames up to 300 (ablation) | Tracking · Fluorescence videos (training) | accuracy | Improved |
Closest papers by meaning
- PhenoLeaf-TS: A Time-Series Benchmark for Leaf Instance Segmentation, Tracking, and Growth Stage Classification (ECCV 2026 · similarity 0.90)
- PlantPose: Universal Plant Skeleton Estimation via Tree-constrained Graph Generation (IJCV 2026 · similarity 0.85)
- Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species (CVPR 2026 · similarity 0.84)
- Probabilistic Plant Modeling via Multi-View Image-to-Image Translation (CVPR 2018 · similarity 0.84)
- PlantTraitNet: An Uncertainty-Aware Multimodal Framework for Global-Scale Plant Trait Inference from Citizen Science Data (AAAI 2026 · similarity 0.83)
- Neural Hierarchical Decomposition for Single Image Plant Modeling (CVPR 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
