Skip to content

Latest commit

 

History

History
36 lines (31 loc) · 1.44 KB

README.md

File metadata and controls

36 lines (31 loc) · 1.44 KB
Raw

allgo

Capstone Project (Inha University, 2017 fall semester) Self Driving Car - System Self Driving car using color detection.

Key Points

  • Two approach
    • Color Detection
    • Neural Networks
Color Detection Approach

Two bottom frames checked for their colors and decision is made accordingly

Cat

python rasp/autocar.py
<iframe src="https://docs.google.com/presentation/d/e/2PACX-1vRCX5FwVTLh-jBEkWzX7Yslm6VVHjOoNLJOurFSI8OQ09s3ung_BhXZGYkRVYEF68yMnu_EkMQ0sMIn/embed?start=false&loop=false&delayms=3000" frameborder="0" width="960" height="569" allowfullscreen="true" mozallowfullscreen="true" webkitallowfullscreen="true"></iframe> ##### Neural Networks Approach Only Model creation stage is completed. Computer initialise server to collect camera data from raspberry takes input from keyboard where to go, and sends this data to raspberry to control motor. Simultaneously saves frame and command in data array for model training.
  • Start MotorServer(motor_controller.py) from rasp
  • Start CompServer(collect_training_data.py) from comp
  • Start Camera Stream(camera_client.py) from rasp

    Now train data in your computer to get model
  • run mlp_training.py in folder comp

.........in progresss........
........wait for updates......

Requirements

Comp

  • Opencv
  • Tensorflow(optional for data)
pip install wiringpi
pip install raspicam