Public Dataset of Parking Lot Videos for Computational Vision Applied to Surveillance

In this work, we propose a new dataset, the UFPArk, which consists of a selection of video clips based on a surveillance camera’s footage throughout a day. The aforementioned dataset is relevant to areas such as computer vision-based object detection, human behavior detection and Internet of Things (IoT) applications, which gained momentum with recent Deep Learning (DL) breakthroughs. To validate our dataset, we conduct some experiments that illustrate the relevance of this effort and its applicability in academic and commercial environments.

I. Introduction

The increased availability of datasets is one of the key enablers for the latest improvements in Machine Learning (ML) techniques. Recent advances in ML boosted its adoption even in daily life applications: in crowded cities for example, a common problem for drivers is finding available parking spots – a time-consuming task that even contributes to traffic congestion.