Learning to Detect Pedestrians by Watching Videos

Author

Andrew Y. Chen, The University of Texas Rio Grande Valley

Date of Award

12-2019

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Dr. Hongkai Yu

Second Advisor

Dr. Jingru Zhang

Third Advisor

Dr. Bin Fu

Abstract

The field of deep learning has experienced a resurgence in the recent years, particularly resulting with the advent of AlexNet. Supervised learning is currently the most common and practical machine learning method. The struggle with employing supervised learning to approach problems is that it requires training data. Sufficient training data is correlated with performance for deep learning models. The issue is that preparing the training data can be a tedious and labor intensive task, especially on a large scale. The purpose of this paper is to determine how efficient a machine can learn when trained on automatically annotated data. The goal is to determine whether or not automatically generated training data is viable for teaching machines. This proposed framework is designed to generate data and train a classifier for pedestrian detection. The framework will be evaluated on a tailored pedestrian dataset and PASCAL VOC 2007.

Comments

Copyright 2019 Andrew Y. Chen. All Rights Reserved.

https://go.openathens.net/redirector/utrgv.edu?url=https://www.proquest.com/dissertations-theses/learning-detect-pedestrians-watching-videos/docview/2382602288/se-2?accountid=7119

Recommended Citation

Chen, Andrew Y., "Learning to Detect Pedestrians by Watching Videos" (2019). Theses and Dissertations. 436.
https://scholarworks.utrgv.edu/etd/436