Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks

The purpose of crowd counting is to estimate the number of pedestrians in crowd images. Crowd counting or density estimation is an extremely challenging task in computer vision, due to large scale variations and dense scene. Current methods solve these issues by compounding multi-scale Convolutional...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhu Liping, Zhang Hong, Ali Sikandar, Yang Baoli, Li Chengyang
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2020
Materias:	crowd counting multi-scale crowd density estimation density map 68t45 Science Q Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/c13a28ff0ef4422b9d3c2c974cb5d7a9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c13a28ff0ef4422b9d3c2c974cb5d7a9
record_format	dspace
spelling	oai:doaj.org-article:c13a28ff0ef4422b9d3c2c974cb5d7a92021-12-05T14:10:51ZCrowd counting via Multi-Scale Adversarial Convolutional Neural Networks2191-026X10.1515/jisys-2019-0157https://doaj.org/article/c13a28ff0ef4422b9d3c2c974cb5d7a92020-07-01T00:00:00Zhttps://doi.org/10.1515/jisys-2019-0157https://doaj.org/toc/2191-026XThe purpose of crowd counting is to estimate the number of pedestrians in crowd images. Crowd counting or density estimation is an extremely challenging task in computer vision, due to large scale variations and dense scene. Current methods solve these issues by compounding multi-scale Convolutional Neural Network with different receptive fields. In this paper, a novel end-to-end architecture based on Multi-Scale Adversarial Convolutional Neural Network (MSA-CNN) is proposed to generate crowd density and estimate the amount of crowd. Firstly, a multi-scale network is used to extract the globally relevant features in the crowd image, and then fractionally-strided convolutional layers are designed for up-sampling the output to recover the loss of crucial details caused by the earlier max pooling layers. An adversarial loss is directly employed to shrink the estimated value into the realistic subspace to reduce the blurring effect of density estimation. Joint training is performed in an end-to-end fashion using a combination of Adversarial loss and Euclidean loss. The two losses are integrated via a joint training scheme to improve density estimation performance.We conduct some extensive experiments on available datasets to show the significant improvements and supremacy of the proposed approach over the available state-of-the-art approaches.Zhu LipingZhang HongAli SikandarYang BaoliLi ChengyangDe Gruyterarticlecrowd countingmulti-scalecrowd density estimationdensity map68t45ScienceQElectronic computers. Computer scienceQA75.5-76.95ENJournal of Intelligent Systems, Vol 30, Iss 1, Pp 180-191 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	crowd counting multi-scale crowd density estimation density map 68t45 Science Q Electronic computers. Computer science QA75.5-76.95
spellingShingle	crowd counting multi-scale crowd density estimation density map 68t45 Science Q Electronic computers. Computer science QA75.5-76.95 Zhu Liping Zhang Hong Ali Sikandar Yang Baoli Li Chengyang Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
description	The purpose of crowd counting is to estimate the number of pedestrians in crowd images. Crowd counting or density estimation is an extremely challenging task in computer vision, due to large scale variations and dense scene. Current methods solve these issues by compounding multi-scale Convolutional Neural Network with different receptive fields. In this paper, a novel end-to-end architecture based on Multi-Scale Adversarial Convolutional Neural Network (MSA-CNN) is proposed to generate crowd density and estimate the amount of crowd. Firstly, a multi-scale network is used to extract the globally relevant features in the crowd image, and then fractionally-strided convolutional layers are designed for up-sampling the output to recover the loss of crucial details caused by the earlier max pooling layers. An adversarial loss is directly employed to shrink the estimated value into the realistic subspace to reduce the blurring effect of density estimation. Joint training is performed in an end-to-end fashion using a combination of Adversarial loss and Euclidean loss. The two losses are integrated via a joint training scheme to improve density estimation performance.We conduct some extensive experiments on available datasets to show the significant improvements and supremacy of the proposed approach over the available state-of-the-art approaches.
format	article
author	Zhu Liping Zhang Hong Ali Sikandar Yang Baoli Li Chengyang
author_facet	Zhu Liping Zhang Hong Ali Sikandar Yang Baoli Li Chengyang
author_sort	Zhu Liping
title	Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
title_short	Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
title_full	Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
title_fullStr	Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
title_full_unstemmed	Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks
title_sort	crowd counting via multi-scale adversarial convolutional neural networks
publisher	De Gruyter
publishDate	2020
url	https://doaj.org/article/c13a28ff0ef4422b9d3c2c974cb5d7a9
work_keys_str_mv	AT zhuliping crowdcountingviamultiscaleadversarialconvolutionalneuralnetworks AT zhanghong crowdcountingviamultiscaleadversarialconvolutionalneuralnetworks AT alisikandar crowdcountingviamultiscaleadversarialconvolutionalneuralnetworks AT yangbaoli crowdcountingviamultiscaleadversarialconvolutionalneuralnetworks AT lichengyang crowdcountingviamultiscaleadversarialconvolutionalneuralnetworks
_version_	1718371687886487552

Crowd counting via Multi-Scale Adversarial Convolutional Neural Networks

Ejemplares similares