beta3 commited on
Commit
abdfcac
Β·
verified Β·
1 Parent(s): 710d3b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -5
README.md CHANGED
@@ -1,14 +1,99 @@
1
  ---
2
  title: Pose Estimation MediaPipe
3
- emoji: πŸ‘
4
- colorFrom: indigo
5
- colorTo: blue
6
  sdk: gradio
7
  sdk_version: 5.49.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
- short_description: Pose Estimation MediaPipe for Human Movements
12
  ---
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: Pose Estimation MediaPipe
3
+ emoji: 🧍
4
+ colorFrom: purple
5
+ colorTo: gray
6
  sdk: gradio
7
  sdk_version: 5.49.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ short_description: Pose Estimation App for Human Movement
12
  ---
13
 
14
+ <h1 align="center">🎯 Pose Estimation - MediaPipe (CPU Optimized)</h1>
15
+
16
+ <center>
17
+ A lightweight Gradio web app for performing human pose estimation using [MediaPipe].
18
+ Optimized for CPU-only environments.
19
+ </center>
20
+
21
+ ---
22
+
23
+ ## ⚠️ Important Warnings
24
+
25
+ - ⚠️ **Maximum video size:** 5 MB (due to CPU processing limits).
26
+ - ⚠️ **Processing time:** Long videos may take several minutes to process.
27
+
28
+ ---
29
+
30
+ ## 🧠 Description
31
+
32
+ This project provides an easy-to-use interface to run human pose estimation on videos.
33
+ It uses **MediaPipe Pose** to detect and visualize human body landmarks frame by frame.
34
+
35
+ You can choose between:
36
+ 1. **Pose on original video** β€” overlays pose landmarks directly on the original video.
37
+ 2. **Pose only (black background)** β€” displays only the pose skeleton on a dark background.
38
+
39
+ ---
40
+
41
+ ## βš™οΈ Parameters
42
+
43
+ | Parameter | Description |
44
+ |------------|--------------|
45
+ | **min_detection_confidence** | Minimum confidence threshold for the model to detect a pose. |
46
+ | **min_tracking_confidence** | Minimum confidence for the model to track poses across frames. |
47
+
48
+ Both values range from **0.0 to 1.0**.
49
+ Higher values increase accuracy but may slow down performance on CPU.
50
+
51
+ ---
52
+
53
+ ## 🧩 Project Structure
54
+
55
+ ```
56
+ πŸ“‚ Projects_Repository/
57
+ β”œβ”€β”€ pose_estimation_app.py # Main Gradio app
58
+ β”œβ”€β”€ requirements.txt # Python dependencies
59
+ β”œβ”€β”€ README.md # Project documentation
60
+ ```
61
+
62
+ ---
63
+
64
+ ## πŸ§‘β€πŸ’» Tech Stack
65
+
66
+ - [**MediaPipe Pose**](https://mediapipe.dev/) – Pose detection and tracking
67
+ - [**OpenCV**](https://opencv.org/) – Video processing and frame manipulation
68
+ - [**NumPy**](https://numpy.org/) – Array and numerical operations
69
+ - [**Gradio**](https://www.gradio.app/) – Web-based user interface
70
+
71
+ ---
72
+
73
+ ## 🧠 Notes
74
+
75
+ - The app is **CPU-only**, optimized for lightweight use.
76
+ - For GPU acceleration, consider using TensorFlow or PyTorch-based pose models.
77
+ - Works best with short videos and well-lit subjects.
78
+
79
+ ---
80
+
81
+ ## πŸ”— Visit the Repository
82
+
83
+ πŸ‘‰ [GitHub: 1-echo / Projects_Repository](https://github.com/1-echo/Projects_Repository)
84
+
85
+ ---
86
+
87
+ ## πŸͺͺ License
88
+
89
+ This project is released under the **MIT License**.
90
+ You are free to use, modify, and distribute it with attribution.
91
+
92
+ ---
93
+
94
+ ## πŸ™Œ Acknowledgements
95
+
96
+ - [MediaPipe by Google](https://mediapipe.dev/)
97
+ - [Gradio](https://www.gradio.app/)
98
+ - [OpenCV](https://opencv.org/)
99
+ - [NumPy](https://numpy.org/)