Overview / Usage

A scaled down version of the self-driving system using an RC car, Raspberry Pi, Arduino, and open source software. The system uses a Raspberry Pi with a camera and an ultrasonic sensor as inputs, a processing computer that handles steering, object recognition (stop sign and traffic light) and distance measurement, and an Arduino board for RC car control. Bot detects the path and predicts if it needs move forward, turn left or turn right. along with that it also detects stop signs, traffic lights and any obstacles present in front of it.
We'll be using

Methodology / Approach

1. We took the remote control of the car and reverse engineered it to be controlled with arduino serial communication.
2. Video feed and the data from the ultrasonic sensor is sent to laptop through WiFi Socket.
3. Video feed is then decoded and processed to extract the Region of Interest (ROI).
4. Frames are saved from the video feed with labels "Right_image", "Left_image" and "Forward_image".
5. We will then train our classifier algorithm with the data using Tensorflow or Caffe using the Open Vino toolkit and create a model out of it.
6. Optimize our model to create an *.xml and *.bin file
7. Then we will create a setup using the Inference API so that it is easily gets optimized results on the CPU using the camera and finally it will be able to predict the direction and act on that.
8. For the Stop signs, traffic lights and objects we are using pretrained models. (We will also use webcrawler to collect images of custom objects and train o our custom classifier model later)

Technologies Used

Hardwares used:

1. Intel Powered PC
2. Raspberry Pi 3B+
3. Pi Camera
4. Ultrasonic sensor
5. Arduino

Technologies used:

1. Intel Optimised Python
2. Intel Optimised Tensorflow
3. OpenCV Library
4. Scikit Learn Library
5. Intel's OpenVino ToolKit for Computer Vision

Collaborators