Inverse Attention Guided Deep Crowd Counting Network

In this paper, we address the challenging problem of crowd counting in congested scenes. Specifically, we present Inverse Attention Guided Deep Crowd Counting Network (IA-DCCN) that efficiently infuses segmentation information through an inverse attention mechanism into the counting network, resulting in significant improvements. The proposed method, which is based on VGG-16, is a single-step training framework and is simple to implement. The use of segmentation information does not require additional annotation efforts. We demonstrate the significance of segmentation guided inverse attention through a detailed analysis and ablation study. Furthermore, the proposed method is evaluated on three challenging crowd counting datasets and is shown to achieve significant improvements over several recent methods.

1. Introduction

Crowd counting [5], [11], [15], [16], [23], [24], [28], [30], [31], [34], [36], [38], [45]–[48] has attracted a lot of interest in the recent years. With growing population and occurrence of numerous crowded events such as political rallies, protests, marathons, etc., computer vision-based crowd analysis is becoming an increasingly important task.