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
- Written only for educational purposes
- Intentionally written in pure Matlab language, using only elementary arithmetic operations:
- 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
- collect some test samples using bin/collectSamples.bat
- then put them to the respective directories under datasource/test/
- run check.m script
- open live stream using bin/startStream.bat
- run detect.m script