Skip to content

tomekceszke/vehicles-counter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Vehicles Counter

This Octave/Matlab script first learns how to recognize cars using neural networks then detects and counts them on live stream.

  • Classification method: neural network with 1 hidden layer
  • Optimization : Backpropagation

Proof of concept

Note

  • Written only for educational purposes
  • Intentionally written in pure Matlab language, using only elementary arithmetic operations:

Input (snapshot)

street

'Cars' samples

car_sample

'Not cars' training samples

not_cars_sample

Run

Learn (optional)

  • collect some training samples using bin/collectSamples.bat
  • then put them to the respective directories under datasource/train/
  • run learn.m script in Matlab/Octave

Training efficiency

red_sample

Test (optional)

Detect

Requirements