andikarachman / Pedestrian-Detection

Pedestrian detection with Python and OpenCV
MIT License
1 stars 1 forks source link
computer-vision hog-features-extraction machine-learning opencv pedestrian-detection python svm-classifier

Pedestrian Detection

Introduction

We build a pedestrian detection system by by combining Histogram of Oriented Gradients (HoG) feature and support vector machine (SVM). HoG feature provides a reasonable and feature invariant object representation, while SVM framework gives us a robust classifier that can control both the training set error and the classifier's complexity. Complete descriptions of the technique are given the this paper.

While it is possible to detect pedestrians from images, videos, and webcam streaming, we only focus on detection from video.

Dependencies

Command format

The input of this system will be video, so we need to specify the path to the input and output video.

$ python pedestrian-detection.py [-h] -i INPUT -o OUTPUT