A Study On The Use of Deep Learning for Automatic Audience Counting

Abstract

Counting objects or living beings is a common necessity in many areas of industry, commerce and services. Automating this activity can promote an optimization of the process involved and, consequently, the reduction of time and costs. With this in mind, computer vision is an approach that provides new possibilities for the digital processing of images, giving the computer a capacity of interpretation increasingly similar to humans. This work aims to compare the efficiency of volumetric counting techniques, both using traditional computational vision and deep learning, in counting audiences in face-to-face events. As a case study, this preliminary investigation focused on audience counting of film and / or theater sessions from audience photos. Gauge billing automatically, accurately and transparently is a recurring need of the entertainment industry. From our experiments it was possible to observe the great potential of the application of deep learning in this context. When compared to several automatic volumetric counting techniques available, deep learning was the strategy that presented the best results, reaching sensitivity and precision above 96%.