# tjubiit/tju-dhd architecture

> Architecture diagram of the GitHub repository tjubiit/tju-dhd, 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/tjubiit/tju-dhd
- Repository: https://github.com/tjubiit/tju-dhd

## Overview

This repository presents the TJU-DHD research dataset, not a software runtime. The documented user workflow is to choose a scene and task, obtain the corresponding images and annotations from the listed hosts, then evaluate detectors using the benchmark protocols and tools. The README also describes high-resolution, diverse data and pedestrian same-scene and cross-scene evaluation. No source excerpts are available, so links reflect documented capabilities only.

Main entry points: [`README.md`](https://github.com/tjubiit/tju-dhd/blob/master/README.md) (Dataset guide)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Dataset collections"]
  node_readme["Dataset guide<br/>[README.md]"]
  node_object_data[("Object detection data<br/>[README.md]")]
  node_ped_data[("Pedestrian data<br/>[README.md]")]
  node_traffic["Traffic scene<br/>[README.md]"]
  node_campus["Campus scene<br/>[README.md]"]
  node_images[("Images<br/>[README.md]")]
  node_annotations["Annotations<br/>[README.md]"]
end

subgraph group_bench["Evaluation benchmarks"]
  node_benchmark["Detection benchmarks<br/>[README.md]"]
  node_ped_eval["Pedestrian evaluation<br/>[README.md]"]
  node_cocoapi["COCO evaluation tools"]
end

subgraph group_distribution["Dataset distribution"]
  node_onedrive["OneDrive"]
  node_baidu["Baidu Netdisk"]
end

node_researcher(("Dataset user"))

node_researcher -->|"consults"| node_readme
node_readme -->|"documents"| node_object_data
node_readme -->|"documents"| node_ped_data
node_object_data -->|"covers"| node_traffic
node_object_data -->|"covers"| node_campus
node_ped_data -->|"covers"| node_traffic
node_ped_data -->|"covers"| node_campus
node_object_data -->|"includes"| node_images
node_object_data -->|"includes"| node_annotations
node_readme -->|"describes"| node_benchmark
node_readme -->|"describes"| node_ped_eval
node_benchmark -.->|"uses"| node_cocoapi
node_readme -->|"links downloads"| node_onedrive
node_readme -->|"links downloads"| node_baidu
node_ped_eval -->|"supports cross-scene"| node_benchmark

click node_readme "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_object_data "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_ped_data "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_traffic "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_campus "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_images "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_annotations "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_benchmark "https://github.com/tjubiit/tju-dhd/blob/master/README.md"
click node_ped_eval "https://github.com/tjubiit/tju-dhd/blob/master/README.md"

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_readme,node_object_data,node_ped_data,node_traffic,node_campus,node_images,node_annotations,node_researcher toneBlue
class node_benchmark,node_ped_eval,node_cocoapi toneAmber
class node_onedrive,node_baidu toneMint
```

## Components

### Dataset collections

- [Dataset guide](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Object detection data](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Pedestrian data](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Traffic scene](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Campus scene](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Images](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Annotations](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`

### Evaluation benchmarks

- [Detection benchmarks](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- [Pedestrian evaluation](https://github.com/tjubiit/tju-dhd/blob/master/README.md): `README.md`
- **COCO evaluation tools**

### Dataset distribution

- **OneDrive**
- **Baidu Netdisk**

### Other components

- **Dataset user**

## Connections

- Dataset user → Dataset guide: consults (evidence: `README.md`)
- Dataset guide → Object detection data: documents (evidence: `README.md`)
- Dataset guide → Pedestrian data: documents (evidence: `README.md`)
- Object detection data → Traffic scene: covers (evidence: `README.md`)
- Object detection data → Campus scene: covers (evidence: `README.md`)
- Pedestrian data → Traffic scene: covers (evidence: `README.md`)
- Pedestrian data → Campus scene: covers (evidence: `README.md`)
- Object detection data → Images: includes (evidence: `README.md`)
- Object detection data → Annotations: includes (evidence: `README.md`)
- Dataset guide → Detection benchmarks: describes (evidence: `README.md`)
- Dataset guide → Pedestrian evaluation: describes (evidence: `README.md`)
- Detection benchmarks → COCO evaluation tools: uses (evidence: `README.md`)
- Dataset guide → OneDrive: links downloads (evidence: `README.md`)
- Dataset guide → Baidu Netdisk: links downloads (evidence: `README.md`)
- Pedestrian evaluation → Detection benchmarks: supports cross-scene (evidence: `README.md`)