Skip to content

Latest commit

 

History

History
23 lines (13 loc) · 917 Bytes

README.md

File metadata and controls

23 lines (13 loc) · 917 Bytes
Raw

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

  • opencv
  • numpy
  • imutils

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

  • INPUT: path to input video
  • OUTPUT: path to output video