Scale and density invariant head detection deep model for crowd counting in pedestrian crowds

Crowd counting in high density crowds has significant importance in crowd safety and crowd management. Existing state-of-the-art methods employ regression models to count the number of people in an image. However, regression models are blind and cannot localize the individuals in the scene. On the o...

Full description

Saved in:
Bibliographic Details
Published in:The Visual computer 2021-08, Vol.37 (8), p.2127-2137
Main Authors: Khan, Sultan Daud, Basalamah, Saleh
Format: Article
Language:English
Subjects:
Artificial Intelligence
Artificial neural networks
Cameras
Computer Graphics
Computer networks
Computer Science
High density
Image Processing and Computer Vision
Invariants
Methods
Neural networks
Original Article
Pedestrians
Regression models
Safety management
Sensors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Crowd counting in high density crowds has significant importance in crowd safety and crowd management. Existing state-of-the-art methods employ regression models to count the number of people in an image. However, regression models are blind and cannot localize the individuals in the scene. On the other hand, detection-based crowd counting in high density crowds is a challenging problem due to significant variations in scales, poses and appearances. The variations in poses and appearances can be handled through large capacity convolutional neural networks. However, the problem of scale lies in the heart of every detector and needs to be addressed for effective crowd counting. In this paper, we propose a end-to-end scale invariant head detection framework that can handle broad range of scales. We demonstrate that scale variations can be handled by modeling a set of specialized scale-specific convolutional neural networks with different receptive fields. These scale-specific detectors are combined into a single backbone network, where parameters of the network is optimized in end-to-end fashion. We evaluated our framework on challenging benchmark datasets, i.e., UCF-QNRF, UCSD. From experiment results, we demonstrate that proposed framework beats existing methods by a great margin.
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-020-01974-7