---
title: 'CanolaTrack: Canola Phenotyping Benchmark'
url: https://www.emergentmind.com/topics/canolatrack
type: topic
---

# CanolaTrack: Canola Phenotyping Benchmark

Taken together, recent papers suggest that **CanolaTrack** has a dual status in current canola phenotyping literature. In its most specific sense, it denotes a domain-specific benchmark for **leaf-level multi-object tracking** in top-down RGB imagery of *Brassica napus*. In a broader, task-oriented sense, the name is also used for canola-centric tracking pipelines spanning **branch identity preservation**, **row-wise plant MOTS for precision spraying**, **growth-stage estimation**, **plot-scale canopy reconstruction**, **clubroot diagnosis**, and **multitemporal crop mapping**. Across these usages, the common technical problem is longitudinal estimation under non-rigid growth, occlusion, temporal sparsity, and biologically driven appearance change rather than rigid-body motion alone [2512.13130, 2512.15445, 2306.13518, 2606.11966, 2506.18292, 2601.13069, 2306.00114].

## 1. Conceptual scope and phenotyping motivation

Canola tracking is motivated by the agronomic value of persistent, organ-resolved measurements over time. Leaf-level phenotyping captures emergence, growth, morphological change, occlusion, and senescence; branch-level tracking supports longitudinal traits such as elongation rate, angle trajectories, and flowering duration; plot-scale reconstruction enables canopy architectural indicators and yield-related proxies. These targets are biologically meaningful because developmental and stress responses are expressed as temporally evolving structures rather than isolated snapshots [2512.13130, 2512.15445, 2506.18292].

The central technical difficulty is that canola violates the assumptions underlying many generic tracking systems. In top-down rosette imagery, leaves exhibit large intra-plant similarity, non-rigid deformation due to growth, frequent self-occlusions, and occasional global pot rotations that break geometric continuity. In side-view canopy imagery, branches become entangled, stage-dependent ambiguity increases, and identities fragment as the canopy densifies. In field-scale sensing, cloud cover, temporal gaps, and mixed pixels complicate multitemporal classification. This suggests that CanolaTrack-style systems are defined less by a single sensor or architecture than by a shared requirement: maintaining biological identity or state through realistic, non-ideal imaging regimes [2512.13130, 2512.15445, 2306.00114].

## 2. The leaf-level CanolaTrack benchmark

The most concrete and fully specified instantiation of CanolaTrack is the benchmark introduced with LeafTrackNet. It comprises **5,704 top-down RGB images** at **1200×1200** resolution, collected **daily over 31 consecutive days** for **184 individual canola plants**, yielding **184 sequences** with **31 frames** each and **$\Delta t = 24$ hours**. The dataset contains **31,840 annotated leaf instances** in total, each linked to a persistent identity maintained across the sequence. The reported dynamics include leaf birth, non-uniform expansion, overlap, occlusion, disappearance through death or senescence, re-appearance after occlusion, and occasional whole-pot rotation [2512.13130].

| Component | Value | Notes |
|---|---:|---|
| Images | 5,704 | Top-down RGB, 1200×1200 |
| Plants / sequences | 184 | 31 daily frames per plant |
| Leaf instances | 31,840 | Persistent identity annotations |
| Train split | 147 plants | 4,557 images; 25,485 leaves |
| Test split | 37 plants | 1,147 images; 6,355 leaves |

The benchmark is explicitly positioned against prior plant datasets such as **LeTra**, **KOMATSUNA**, and **MSU-PID**. It is described as a substantially larger, high-resolution, RGB-only corpus captured under realistic, temporally sparse conditions, and as **the largest dataset for leaf tracking in agriculture crops** [2512.13130]. The intended tasks are **leaf detection** in top-down RGB imagery and **multi-object leaf tracking with persistent identities across days**. Annotation is bounding-box based using **top-left, width, height**; masks and keypoints are not provided. Identities are maintained across frames within a plant sequence, but annotation tools, inter-annotator agreement, and quality-control procedures are not reported; annotation was performed by one of the authors (**S.L.**) [2512.13130].

Benchmarking follows standard MOT practice via **TrackEval**, with **HOTA**, **DetA**, **AssA**, **MOTA**, and **IDF1**. The benchmark defines
$$
\mathrm{HOTA} = \sqrt{\mathrm{DetA} \times \mathrm{AssA}}
$$
and
$$
\mathrm{DetA} = \frac{\mathrm{TP}}{\mathrm{TP} + \mathrm{FP} + \mathrm{FN}}.
$$
This metric set is significant because the dataset is designed not merely to reward accurate per-frame detection but to measure long-horizon identity preservation under daily sampling and strong non-rigid change [2512.13130].

## 3. LeafTrackNet: architecture, association mechanism, and reported performance

LeafTrackNet is the benchmark’s reference framework. It decouples detection from identity association and replaces explicit motion modeling with memory-based embedding association. The detector is a **YOLOv10** model fine-tuned on CanolaTrack; at inference, detections with confidence **$< 0.5$** are filtered. Each detection is cropped and resized via
$$
x_{k,i}^t = \psi(I_k^t, b_{k,i}^t) \in \mathbb{R}^{3 \times W \times H},
$$
with **$W = H = 224$** in all experiments. The embedding network uses a **MobileNetV3** backbone **$N_\theta$**, pretrained on ImageNet and truncated before classification, followed by a linear projection **$F_\phi$**:
$$
E(x) = F_\phi(N_\theta(x)) \in \mathbb{R}^D.
$$
The paper does not specify **$D$** [2512.13130].

Embedding learning is organized by leaf-level triplets. For anchor **$x_a = x_{k,i}^{t_a}$**, the positive is **$x_p = x_{k,i}^{t_p}$** with **$t_p \ne t_a$**, and the negative is **$x_n = x_{k,j}^{t_n}$** with **$j \ne i$**, taken from a different leaf of the same plant. The triplet margin loss uses **$m = 0.3$**:
$$
L(x_a, x_p, x_n) = \max\{0,\|e_a-e_p\|_2^2 - \|e_a-e_n\|_2^2 + m\}.
$$
Training uses **Adam** with **lr $1e^{-4}$**, **weight decay $1e^{-5}$**, **batch size 48**, up to **80 epochs** with early stopping, on **four NVIDIA Tesla V100S GPUs**. Data augmentation is not described [2512.13130].

At inference, identity is preserved purely through embedding similarity and temporal smoothing. At **$t=1$**, each detection initializes a prototype in a memory bank. At later times, LeafTrackNet computes cosine similarities
$$
S_{\ell j} = (p_\ell^{t-1})^T e_j^t,
$$
forms **$C = 1 - S$**, and solves one-to-one assignment with the **Hungarian algorithm**. Matches are accepted when **$S_{\ell,\pi^*(\ell)} \ge \tau_s$** with default **$\tau_s = 0.4$**. Prototypes are updated by exponential moving average,
$$
p_\ell^t = \alpha p_\ell^{t-1} + (1-\alpha)e_{\pi^*(\ell)}^t,
$$
with **$\alpha = 0.5$**; unmatched tracks age and are removed when **$a_\ell^t > \tau_a$** with default **$\tau_a = 5$**. No motion model or IoU gating is used [2512.13130].

The reported benchmark outcome is unambiguous. LeafTrackNet surpasses both plant-specific trackers and state-of-the-art MOT baselines on CanolaTrack, achieving **HOTA 88.03**, compared with **78.30** for the best baseline **MOTRv2**; **DetA 92.25** versus **91.94** for **ByteTrack**; **AssA 84.07** versus **79.36** for **MOTRv2**; **MOTA 93.64** versus **82.09** for **LeTra**; and **IDF1 92.90** versus **83.78** for **MOTRv2**. The abstract summarizes this as a **9% HOTA improvement**. The general-purpose baselines **BoT-SORT** and **ByteTrack** show high **DetA** near **92** but weak **AssA** near **12**, indicating that geometric association and rigid-motion models fail under occlusion, growth-induced deformation, and rotation [2512.13130].

Ablations reinforce the design logic. Replacing **MobileNetV3** with **ResNet-18/34/50/101** or **ViT-B/16** does not improve identity preservation; MobileNetV3 gives the best or near-best **HOTA/AssA/IDF1** while remaining the most efficient at approximately **2.97M parameters** and **0.23G MACs**. HOTA remains stable for **$\tau_s \in [0.4, 0.6]$**, and moderate EMA smoothing around **$\alpha \approx 0.5$** works best. Qualitative analyses show robustness to dense occlusions of small leaves and to large, non-physical motions such as **90° pot rotations** between days. The reported failure modes of IoU/Kalman trackers and orientation-sensitive ReID systems are therefore not incidental but structural consequences of the imaging regime [2512.13130].

## 4. Branch identity and plant-instance tracking variants

A second usage treats CanolaTrack as a **branch identity tracking** pipeline, operationalized by **ST-DETrack**. Here the task is to assign each floral bud **$f_i^t$** to its originating branch point **$b_j^t$** and preserve that mapping from budding through flowering and pod fill. The method uses a shared **ViT-B/16** encoder with two specialized decoders: a **spatial decoder** that leverages position and angle, and a **temporal decoder** that exploits motion consistency. Their outputs are fused by an adaptive gate **$g_j \in [0,1]$**, with a negative gravitropism prior penalizing implausible downward matches [2512.15445].

The branch-tracking dataset comprises **360 plants**, **three side views (0°, 45°, 90°)**, **4,877 frames**, **22,911 annotated branch points**, and **38,187 annotated buds**. Images are standardized by cropping background and resizing to **640×640** and then **224×224**; a binary plant mask generated via **Li’s minimum cross-entropy thresholding** is concatenated with RGB. Identities are maintained using **order-based semantic indices**, and temporal models consume an **8-channel tensor** formed by previous and current **RGB+mask** frames. Reported performance is **BMA = 93.6%**, **MOTA = 0.980**, **IDF1 = 0.993**, **FP = 0**, and **FN = 5**. Relative to the spatial-only baseline (**BMA 64.7%**), ST-DETrack improves by **28.9 percentage points**; relative to the temporal-only baseline (**BMA 90.3%**), it improves by **3.3 points** [2512.15445].

The score fusion is explicitly stage-dependent:
$$
M^{fusion}_{ij} = g_j \cdot \frac{M^{spatial}_{ij}}{\tau_{spatial}} + (1-g_j) \cdot \frac{M^{temporal\to branch}_{ij}}{\tau_{temporal}},
$$
with **$\tau_{spatial}=1.0$** and **$\tau_{temporal}=1.2$**. This formalizes the observation that early sparse stages are primarily resolvable by geometry, whereas late dense stages require temporal continuity. The paper also reports **LIoU = 0.9617** and **BTC = 0**, indicating robust longitudinal skeleton fidelity [2512.15445].

A different branch of the literature addresses plant-instance tracking for robotic precision spraying. The MOTS method in **"Segmentation and Tracking of Vegetable Plants by Exploiting Vegetable Shape Feature for Precision Spray of Agricultural Robots"** was tested on lettuce, but the authors state that it can be applied to similar vegetables such as **broccoli and canola**. Its association logic combines **contour Fourier descriptors**, **ellipse blob features**, a **Kalman filter** with state
$$
x_k = [c_x, c_y, v_x, v_y, w, h]^T,
$$
and Hungarian assignment with cost
$$
\delta = \delta_s (1 + \alpha \delta_p),
$$
where **$\delta_s$** is cosine distance between shape features and **$\delta_p$** is a **GIoU**-based position cost. On the LettuceMOTS test sequences, the method reports **HOTA 71.99**, **72.08**, and **70.10**, with end-to-end runtime around **34 ms per frame** or approximately **29 FPS** on **NVIDIA RTX 2080Ti + Intel i7-10700K** [2306.13518].

These branch and plant-instance variants show that CanolaTrack is not reducible to one canonical architecture. In side-view branch tracking, explicit geometric priors and stage-adaptive fusion are central. In row-wise MOTS, contour shape and local motion remain important. In top-down leaf tracking, by contrast, memory-based appearance embeddings outperform rigid-motion association. This suggests that the relevant inductive bias is view- and organ-specific rather than universal [2512.15445, 2306.13518, 2512.13130].

## 5. Developmental, pathological, and 3D phenotyping extensions

One developmental extension treats CanolaTrack as **growth-stage estimation**. In **"Feature extraction for plant growth estimation"**, canola and radish are classified into **background** plus **four growth stages** using indoor, top-mounted imagery from the **bccr-segset** dataset. For canola, the total count is **5,378** images, with **4,831** for training and **547** for testing; imaging resolution is **228×228** pixels. Two feature pipelines are compared: a **Gabor filter bank + morphological operations** pipeline and a **CNN feature extraction** pipeline using **VGG-16**, **VGG-19**, or **ResNet-50**. The best reported system, **VGG-19 features + RBF SVM**, achieves **98.4%** accuracy for canola and processes an image in **0.08 seconds**. Misclassifications are concentrated between **stages 1 and 2**, while background and stage 4 are clearly separable [2606.11966]. A plausible implication is that growth-stage labels can be appended to identity trajectories in a longitudinal CanolaTrack system, but the paper does not report temporal smoothing or sequence-level tracking.

A structurally different extension is **plot-scale 3D canopy reconstruction** via **RP-PCN**. This work addresses rapeseed population point cloud completion from **seedling**, **bolting**, **flowering**, and **silique** stages using multi-view imaging, **virtual-real integration (VRI)**, automated occlusion annotation via ray tracing, and a GAN-based completion network with a **Multi-Resolution Dynamic Graph encoder (MRDG)**, **Dynamic Graph Convolutional Feature Extractor (DGCFE)**, and **Point Pyramid Decoder (PPD)**. Field plots comprise **300 accessions**, **3 replicates**, or **900 plots**, with oblique imaging from one circular UAV flight at **−60°** and **36 images per plot** at **8000×6000** pixels. RP-PCN reports **Chamfer Distance** values of **3.35 cm**, **3.46 cm**, **4.32 cm**, and **4.51 cm** at seedling, bolting, flowering, and silique, respectively. Ablations show that MRDG reduces CD by **10%** and DGCFE by **23%**. At silique stage, the **silique efficiency index (SEI)** derived from completed point clouds improves yield prediction, increasing **$R^2$ from 0.81 to 0.90** and improving overall prediction accuracy by **11.2%** [2506.18292].

Pathological monitoring introduces yet another modality. In **"Non-Invasive Diagnosis for Clubroot Using Terahertz Time-Domain Spectroscopy and Physics-Constrained Neural Networks"**, THz-TDS is applied to canola leaves and roots as a non-contact, non-destructive, preparation-free diagnosis tool. The system uses a transmission-mode THz-TDS spectrometer with bandwidth **exceeding 6 THz**, dynamic range **>100 dB** and up to **110 dB**, spectral resolution **<0.6 GHz**, and lateral scan step **0.5 mm**. Refractive index and absorption coefficient are extracted as
$$
n(\omega) = 1 + \frac{c}{2\pi \omega d}\,\big(\phi_{\mathrm{sam}(\omega)}-\phi_{\mathrm{ref}(\omega)}\big)
$$
and
$$
\alpha(\omega) = -\frac{1}{d}\ln\left[r(\omega)\frac{(n(\omega)+1)^2}{4n(\omega)}\right].
$$
Infected canola leaves exhibit a clearer low-frequency refractive-index blue shift than Arabidopsis leaves, while infected roots show a strong absorption band around **0.4 THz** and consistently lower **$n(\omega)$** across the measured band. A **physics-constrained neural network** with encoder channels **1→16→32→64→128**, latent dimension **32**, batch size **32**, and **50 epochs** is used for self-supervised feature extraction. The paper reports improved latent-feature contrast relative to PCA and a conventional autoencoder, but does **not** report accuracy, sensitivity, specificity, or ROC/AUC [2601.13069].

## 6. Field-scale monitoring, limitations, and future directions

At the largest spatial scale, CanolaTrack intersects with multitemporal remote sensing. The **Canadian Cropland Dataset** contains **78,536** geo-referenced Sentinel-2 instances from **2017–2020** and **June–October**, with canola as one of **10 classes** and **11,366** canola-labeled patches. Each instance covers **640×640 m** at **10 m/pixel** and includes **12 spectral bands**, **RGB**, and five vegetation indices: **NDVI**, **NDVI45**, **GNDVI**, **PSRI**, and **OSAVI**. Sequence models outperform static image models: on the 2019 subset, **LRCN-64 (RGB)** reaches **Accuracy 0.774**, **Precision 0.610**, **Recall 0.637**, **F1 0.617**, and **3D-CNN (RGB)** reaches **Accuracy 0.773**, while the best static model, **ResNet-50 (RGB)**, reports **Accuracy 0.667** [2306.00114]. This indicates that temporal context remains decisive even when tracking is reframed as crop-class persistence across months rather than organ identity across days.

Across the literature, several limitations are explicit. The leaf-level CanolaTrack benchmark is confined to **early growth stages**, **top-down RGB imaging**, and **daily temporal sparsity**; it does not include segmentation masks, depth, or physiological modalities, and it does not report cross-species generalization [2512.13130]. ST-DETrack addresses only the reported Brassica napus side-view setting, and the paper does not provide a public code repository link or licensing terms [2512.15445]. The THz-TDS study emphasizes feature extraction and contrast enhancement rather than supervised diagnosis, so operational detection thresholds and classification metrics remain unspecified [2601.13069]. The Canadian cropland benchmark does not provide per-class canola precision, recall, or confusion matrices, and label quality is bounded by the **AAFC Canadian Annual Crop Inventory** and the 10 m/30 m resolution mismatch [2306.00114].

The forward trajectory is correspondingly multi-scale. The leaf-tracking benchmark identifies **cross-species transfer**, **field-level deployment**, **real-time decision support**, and extensions with **denser temporal sampling**, **segmentation masks**, and **complementary sensing such as depth or fluorescence** as natural next steps [2512.13130]. Branch tracking points toward **3D/multi-view fusion**, **end-to-end joint detection + tracking**, and plant topology priors [2512.15445]. Plot-scale reconstruction highlights **sensor fusion**, **uncertainty estimation**, and **plot-scale mapping** with SLAM or odometry [2506.18292]. The most defensible synthesis is therefore that CanolaTrack names an emerging canola phenotyping agenda: persistent, biologically faithful estimation across organs, stages, sensing modalities, and spatial scales, with identity preservation as its recurring methodological core.

Source: https://www.emergentmind.com/topics/canolatrack