Publication Date

Spring 2019

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Chris Pollett

Second Advisor

Jon Pearce

Third Advisor

Teng Moh

Keywords

parking lot images, Yolo, CNN, Deep Learning

Abstract

Detection of cars in a parking lot with deep learning involves locating all objects of interest in a parking lot image and classifying the contents of all bounding boxes as cars. Because of the variety of shape, color, contrast, pose, and occlusion, a deep neural net was chosen to encompass all the significant features required by the detector to differentiate cars from not cars. In this project, car detection was accomplished with a convolutional neural net (CNN) based on the You Only Look Once (YOLO) model architectures. An application was built to train and validate a car detection CNN as well as track the quantity of cars in a parking lot across a period of time. A separate service called Vision maps and standardizes the input data formats for the CNN as well as sanity checks the bounding box labeling with ground truth image annotations. Finally, another serviced called Skynet analyzes and summarizes the car count statistics over time on a series of parking lot images.

Download

Share

COinS