# hemanthreddykunduru/obj_detection_live_pc_screen architecture

> Architecture diagram of the GitHub repository hemanthreddykunduru/obj_detection_live_pc_screen, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/hemanthreddykunduru/obj_detection_live_pc_screen
- Repository: https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen

## Overview

A small Windows desktop app captures the live screen, runs YOLO oriented-box detection, draws labeled annotations, and presents them in a transparent always-on-top Tkinter overlay. All repository behavior is in one file; the graph separates its runtime stages, but source does not establish further subsystem boundaries.

Main entry points: [`detect_live_screen.py`](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py) (Detection loop)

## Diagram (Mermaid)

```mermaid
flowchart TD

node_desktop(("Live desktop"))
node_loop["Detection loop"]
node_capture["Screen capture"]
node_yolo["YOLO inference"]
node_draw["Annotation renderer"]
node_overlay["Tk overlay"]

node_loop -->|"captures frame"| node_capture
node_desktop -->|"provides pixels"| node_capture
node_loop -->|"runs inference"| node_yolo
node_loop -->|"draws detections"| node_draw
node_loop -->|"schedules updates"| node_overlay
node_draw -->|"supplies image"| node_overlay

click node_loop "https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py"
click node_capture "https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py"
click node_yolo "https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py"
click node_draw "https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py"
click node_overlay "https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.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_desktop,node_yolo toneIndigo
class node_loop,node_draw,node_overlay toneTeal
class node_capture toneBlue
```

## Components

### Other components

- **Live desktop**
- [Detection loop](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py): `detect_live_screen.py`
- [Screen capture](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py): `detect_live_screen.py`
- [YOLO inference](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py): `detect_live_screen.py`
- [Annotation renderer](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py): `detect_live_screen.py`
- [Tk overlay](https://github.com/hemanthreddykunduru/obj_detection_live_pc_screen/blob/main/detect_live_screen.py): `detect_live_screen.py`

## Connections

- Detection loop → Screen capture: captures frame
- Live desktop → Screen capture: provides pixels
- Detection loop → YOLO inference: runs inference
- Detection loop → Annotation renderer: draws detections
- Detection loop → Tk overlay: schedules updates
- Annotation renderer → Tk overlay: supplies image