# muhammad-zainal-muttaqin/project-expertise architecture

> Architecture diagram of the GitHub repository muhammad-zainal-muttaqin/project-expertise, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/muhammad-zainal-muttaqin/project-expertise
- Repository: https://github.com/muhammad-zainal-muttaqin/project-expertise

## Overview

This repository is an empirical oil-palm bunch detection and counting research project. Its principal result path is detector proposals, cross-view fusion/linking, bunch-level maturity classification, and per-tree counting, with evaluation of localization and counting quality. It also contains a separate multi-view bunch association and classification subproject. The graph emphasizes these product stages and the newer remote pipeline; evidence is limited to README statements and the supplied source excerpts/index, so unsampled implementations are represented only where the tree or documentation supports them.

Main entry points: [`pipeline-pertandan/scripts/eval_endtoend.py`](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/eval_endtoend.py) (End-to-End Evaluation), [`results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py`](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py) (Four-View Pipeline), [`pipeline-pertandan/scripts/penaut_pertandan.py`](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/penaut_pertandan.py) (View Linker), [`scripts/train_yolo_4ch_screening.py`](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/train_yolo_4ch_screening.py) (Detector Training)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data and Detection"]
  node_rgbd["RGB+D Preparation"]
  node_detector_training["Detector Training"]
  node_detector_inference["Detector Inference"]
  node_prediction_dump["Prediction Evaluation"]
end

subgraph group_remote["Remote Pipeline"]
  node_remote_fusion["Proposal Fusion"]
  node_linker_training["Edge Linker Training"]
  node_remote_pipeline["Four-View Pipeline<br/>[pipeline_v2.py]"]
  node_class_head["Cluster Class Head<br/>[member_head.py]"]
  node_pipeline_harness["Pipeline Harness<br/>[harness.py]"]
  node_count_reconcile["Count Reconciliation"]
  node_rank_emit["Rank and Emit<br/>[rank_and_emit.py]"]
end

subgraph group_pertandan["Bunch Association"]
  node_pertandan_classifier["Proposal Classifier"]
  node_pertandan_linker["View Linker"]
  node_reid["Bunch Re-identification<br/>[reid_pertandan.py]"]
  node_global_linker["Global Linker"]
  node_bunch_counting["Per-Tree Counting"]
end

subgraph group_evaluation["Evaluation"]
  node_endtoend_eval["End-to-End Evaluation<br/>[eval_endtoend.py]"]
  node_remote_test["Locked Remote Evaluation<br/>[run_test_locked.py]"]
end

node_researcher(("Researcher"))

node_researcher -->|"prepares data"| node_rgbd
node_researcher -->|"runs experiments"| node_detector_training
node_detector_training -.->|"trains detectors"| node_detector_inference
node_detector_inference -.->|"produces predictions"| node_prediction_dump
node_prediction_dump -->|"provides detector dumps"| node_remote_fusion
node_linker_training -->|"trains cross-view linker"| node_remote_pipeline
node_remote_pipeline -.->|"classifies clusters"| node_class_head
node_remote_pipeline -->|"reconciles counts"| node_count_reconcile
node_remote_pipeline -->|"builds payloads"| node_pipeline_harness
node_remote_test -->|"runs evaluation"| node_rank_emit
node_pertandan_classifier -->|"evaluates classification"| node_endtoend_eval
node_pertandan_linker -->|"supports re-identification"| node_reid
node_reid -->|"evaluates association"| node_endtoend_eval
node_pertandan_linker -->|"evaluates linking"| node_endtoend_eval
node_global_linker -->|"supports evaluation"| node_endtoend_eval
node_bunch_counting -.->|"evaluates counting"| node_endtoend_eval

click node_rgbd "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/build_4ch_dataset.py"
click node_detector_training "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/train_yolo_4ch_screening.py"
click node_detector_inference "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/infer_detektor_damimas.py"
click node_prediction_dump "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/eval_dump_damimas.py"
click node_remote_fusion "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/eval_remote_pipeline_postprocess.py"
click node_linker_training "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/train_detection_edge_linker.py"
click node_remote_pipeline "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py"
click node_class_head "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/member_head.py"
click node_pipeline_harness "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/harness.py"
click node_count_reconcile "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/evaluate_remote_count_reconciled.py"
click node_rank_emit "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/scripts/rank_and_emit.py"
click node_pertandan_classifier "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/classifier_hibrida_damimas.py"
click node_pertandan_linker "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/penaut_pertandan.py"
click node_reid "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/reid_pertandan.py"
click node_global_linker "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/linker_global_damimas.py"
click node_bunch_counting "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/counting_damimas.py"
click node_endtoend_eval "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/eval_endtoend.py"
click node_remote_test "https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/scripts/run_test_locked.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_rgbd,node_detector_training,node_detector_inference,node_prediction_dump toneBlue
class node_remote_fusion,node_linker_training,node_remote_pipeline,node_class_head,node_pipeline_harness,node_count_reconcile,node_rank_emit toneAmber
class node_pertandan_classifier,node_pertandan_linker,node_reid,node_global_linker,node_bunch_counting toneMint
class node_endtoend_eval,node_remote_test toneRose
class node_researcher toneIndigo
```

## Components

### Data and Detection

- [RGB+D Preparation](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/build_4ch_dataset.py): `scripts/build_4ch_dataset.py`
- [Detector Training](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/train_yolo_4ch_screening.py): `scripts/train_yolo_4ch_screening.py`
- [Detector Inference](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/infer_detektor_damimas.py): `scripts/infer_detektor_damimas.py`
- [Prediction Evaluation](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/eval_dump_damimas.py): `scripts/eval_dump_damimas.py`

### Remote Pipeline

- [Proposal Fusion](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/eval_remote_pipeline_postprocess.py): `scripts/eval_remote_pipeline_postprocess.py`
- [Edge Linker Training](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/train_detection_edge_linker.py): `scripts/train_detection_edge_linker.py`
- [Four-View Pipeline](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py): `results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py`
- [Cluster Class Head](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/member_head.py): `results/remote_eval_2026-08-28/validation_wave/scripts/member_head.py`
- [Pipeline Harness](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/validation_wave/scripts/harness.py): `results/remote_eval_2026-08-28/validation_wave/scripts/harness.py`
- [Count Reconciliation](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/scripts/evaluate_remote_count_reconciled.py): `scripts/evaluate_remote_count_reconciled.py`
- [Rank and Emit](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/scripts/rank_and_emit.py): `results/remote_eval_2026-08-28/scripts/rank_and_emit.py`

### Bunch Association

- [Proposal Classifier](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/classifier_hibrida_damimas.py): `pipeline-pertandan/scripts/classifier_hibrida_damimas.py`
- [View Linker](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/penaut_pertandan.py): `pipeline-pertandan/scripts/penaut_pertandan.py`
- [Bunch Re-identification](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/reid_pertandan.py): `pipeline-pertandan/scripts/reid_pertandan.py`
- [Global Linker](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/linker_global_damimas.py): `pipeline-pertandan/scripts/linker_global_damimas.py`
- [Per-Tree Counting](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/counting_damimas.py): `pipeline-pertandan/scripts/counting_damimas.py`

### Evaluation

- [End-to-End Evaluation](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/pipeline-pertandan/scripts/eval_endtoend.py): `pipeline-pertandan/scripts/eval_endtoend.py`
- [Locked Remote Evaluation](https://github.com/muhammad-zainal-muttaqin/project-expertise/blob/main/results/remote_eval_2026-08-28/scripts/run_test_locked.py): `results/remote_eval_2026-08-28/scripts/run_test_locked.py`

### Other components

- **Researcher**

## Connections

- Researcher → RGB+D Preparation: prepares data
- Researcher → Detector Training: runs experiments
- Detector Training → Detector Inference: trains detectors
- Detector Inference → Prediction Evaluation: produces predictions
- Prediction Evaluation → Proposal Fusion: provides detector dumps (evidence: `scripts/eval_remote_pipeline_postprocess.py`)
- Edge Linker Training → Four-View Pipeline: trains cross-view linker (evidence: `results/remote_eval_2026-08-28/validation_wave/scripts/pipeline_v2.py`)
- Four-View Pipeline → Cluster Class Head: classifies clusters
- Four-View Pipeline → Count Reconciliation: reconciles counts (evidence: `scripts/evaluate_remote_count_reconciled.py`)
- Four-View Pipeline → Pipeline Harness: builds payloads (evidence: `results/remote_eval_2026-08-28/validation_wave/scripts/harness.py`)
- Locked Remote Evaluation → Rank and Emit: runs evaluation (evidence: `results/remote_eval_2026-08-28/scripts/run_test_locked.py`)
- Proposal Classifier → End-to-End Evaluation: evaluates classification (evidence: `pipeline-pertandan/scripts/eval_endtoend.py`)
- View Linker → Bunch Re-identification: supports re-identification (evidence: `pipeline-pertandan/scripts/reid_pertandan.py`)
- Bunch Re-identification → End-to-End Evaluation: evaluates association (evidence: `pipeline-pertandan/scripts/eval_endtoend.py`)
- View Linker → End-to-End Evaluation: evaluates linking (evidence: `pipeline-pertandan/scripts/eval_endtoend.py`)
- Global Linker → End-to-End Evaluation: supports evaluation (evidence: `pipeline-pertandan/scripts/linker_global_damimas.py`)
- Per-Tree Counting → End-to-End Evaluation: evaluates counting
