https://github.com/dev-khant/subway-surfer-hand-motion

Hand Motion Object Detector
https://github.com/dev-khant/subway-surfer-hand-motion

object-detection ssd-mobilenet tensorflow

Last synced: about 2 months ago
JSON representation

Hand Motion Object Detector

• Host: GitHub
• URL: https://github.com/dev-khant/subway-surfer-hand-motion
• Owner: Dev-Khant
• Created: 2021-10-22T11:01:17.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-11-30T15:00:02.000Z (over 4 years ago)
• Last Synced: 2025-01-23T06:32:38.399Z (over 1 year ago)
• Topics: object-detection, ssd-mobilenet, tensorflow
• Language: Python
• Homepage:
• Size: 154 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Subway Surfers with Hand Motions

![img](https://user-images.githubusercontent.com/57898986/140607483-332a70eb-05ba-44d3-b1e7-b6d3a9036597.png)

## Object Detection Model

Built an Object Detector which detects the position of Hand and accordingly predicts the movement. The movements are Up, Down, Right, Left. These movements are then passed to the game.



Model used for detection is SSD_MobileNet_V2_FPNLite as it can detect object in around 25ms with the help of Tensorflow Object Detection API [here](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md) and for setting up the environment go through the official article [here](https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/).
 

Folder for Tensorflow Object Detection API is on MASTER branch .



Used custom dataset consisting of 250 train images and 50 test images for each class.



The link for the working video [YouTube](https://www.youtube.com/watch?v=LYiCKA1DeFg).