Open In App

Project Idea | (Robust Pedestrian detection)

Improve
Improve
Like Article
Like
Save
Share
Report

The aim of this project is to develop an application which can detect pedestrians effectively. The problem of motion-based object detection can be divided into two parts:
a) Classifying pedestrians and non pedestrians features
a) Detecting pedestrians in each frame
b) Associating the detections corresponding to the same object over time

Tool :This project is based on Machine learning, We can provide image data set of pedestrians and non-pedestrians as an training data to the software tool which will extract important features using Adaboost classifier or SVM etc. and similar combination of strong/important features will be taken out for post-processing. We can use Python or Matlab as a building tool for this system.

Implementation : The Implementation of such a tool depends on two factors – Feature extraction and object detection methods.
So you can use various classifiers available online and also read about basic feature extraction algorithm.

Research : Detecting humans in images is a challenging task owing to their variable appearance. This is a booming research topic which is still going on for surveillance of large crowds in real time applications. Research areas include image processing, artificial Intelligence and machine learning.

References:
IEEE Transaction paper on https://lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdf
Survey Paper: http://www.thesai.org/Downloads/Volume5No10/Paper_7-A_Survey_of_Pedestrian_Detection_in_Video.pdf


Last Updated : 21 May, 2017
Like Article
Save Article
Previous
Next
Share your thoughts in the comments
Similar Reads