Citation: Xu, J.; Zhao, H.; Min, W. A
Two-Stage Approach to Important
Area Detection in Gathering Place
Using a Novel Multi-Input Attention
Network. Sensors 2022, 22, 285.
https://doi.org/10.3390/s22010285
Academic Editor: Nunzio Cennamo
Received: 26 November 2021
Accepted: 28 December 2021
Published: 31 December 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Two-Stage Approach to Important Area Detection in Gathering
Place Using a Novel Multi-Input Attention Network
Jianqiang Xu
1
, Haoyu Zhao
1
and Weidong Min
2,3,
*
1
School of Information Engineering, Nanchang University, Nanchang 330031, China; xjq@ncu.edu.cn (J.X.);
zhaohaoyu@email.ncu.edu.cn (H.Z.)
2
School of Software, Nanchang University, Nanchang 330047, China
3
Jiangxi Key Laboratory of Smart City, Nanchang 330047, China
* Correspondence: minweidong@ncu.edu.cn
Abstract:
An important area in a gathering place is a region attracting the constant attention of
people and has evident visual features, such as a flexible stage or an open-air show. Finding such
areas can help security supervisors locate the abnormal regions automatically. The existing related
methods lack an efficient means to find important area candidates from a scene and have failed to
judge whether or not a candidate attracts people’s attention. To realize the detection of an important
area, this study proposes a two-stage method with a novel multi-input attention network (MAN).
The first stage, called important area candidate generation, aims to generate candidate important
areas with an image-processing algorithm (i.e., K-means++, image dilation, median filtering, and the
RLSA algorithm). The candidate areas can be selected automatically for further analysis. The second
stage, called important area candidate classification, aims to detect an important area from candidates
with MAN. In particular, MAN is designed as a multi-input network structure, which fuses global
and local image features to judge whether or not an area attracts people’s attention. To enhance the
representation of candidate areas, two modules (i.e., channel attention and spatial attention modules)
are proposed on the basis of the attention mechanism. These modules are mainly based on multi-layer
perceptron and pooling operation to reconstruct the image feature and provide considerably efficient
representation. This study also contributes to a new dataset called gathering place important area
detection for testing the proposed two-stage method. Lastly, experimental results show that the
proposed method has good performance and can correctly detect an important area.
Keywords:
important area detection; image processing algorithm; multi-input attention network;
gathering place important area detection dataset
1. Introduction
An important area refers to a region that can attract people’s attention in a gathering
place. People are consistently willing to considerably focus on a particular area and gather
around it, such as a flexible stage, open-air dance, or some unusual event occurring in an
area. Two examples of an important area where people are gathered and staring at the area
are shown in Figure 1. The left side of the first row in Figure 1 shows numerous people
sitting on the ground in a circle, and the right side shows a stage in the middle of the image
attracting people to come and watch. The red rectangles in the second row in Figure 1
represent the important areas that this study wants to detect. The two areas attract people’s
attention, and they gather around it.
Compared with the surrounding regions, an important area has evident visual features.
Certain dangerous things can happen in these areas, thereby possibly affecting security.
Security supervisors can locate abnormal regions by monitoring an important area. With
the help of important area detection, this study can be completed automatically. However,
important visual features can be easily captured by humans but not as easily for computers.
Sensors 2022, 22, 285. https://doi.org/10.3390/s22010285 https://www.mdpi.com/journal/sensors
