Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes
Counting and localization of people in videos consisting of low density to high density crowds encounter many key challenges including complex backgrounds, scale variations, nonuniform distributions, and occlusions. For this purpose, we propose a scale driven convolutional neural network (SD-CNN) mo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8721049/ |
| _version_ | 1819295741374365696 |
|---|---|
| author | Saleh Basalamah Sultan Daud Khan Habib Ullah |
| author_facet | Saleh Basalamah Sultan Daud Khan Habib Ullah |
| author_sort | Saleh Basalamah |
| collection | DOAJ |
| description | Counting and localization of people in videos consisting of low density to high density crowds encounter many key challenges including complex backgrounds, scale variations, nonuniform distributions, and occlusions. For this purpose, we propose a scale driven convolutional neural network (SD-CNN) model, which is based on the assumption that heads are the dominant and visible features regardless of the density of crowds. To deal with the problem of different scales of heads in different regions of the videos, we annotate a set of heads in random locations of the videos to develop a scale map representing the mapping of head sizes. We then extract scale aware proposals based on the scale map which are fed to the SD-CNN model acting as a head detector. Our model provides a response matrix rendering accurate head positions via nonmaximal suppression. For experimental evaluations, we consider three standard datasets presenting low density to high density crowd scenes. Our proposed SD-CNN model outperforms the state-of-the-art methods in terms of both frame-level and pixel-level analyses. |
| first_indexed | 2024-12-24T04:47:02Z |
| format | Article |
| id | doaj.art-8ef4054db9de4ca393fbf63b118c884c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-24T04:47:02Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8ef4054db9de4ca393fbf63b118c884c2022-12-21T17:14:40ZengIEEEIEEE Access2169-35362019-01-017715767158410.1109/ACCESS.2019.29186508721049Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd ScenesSaleh Basalamah0Sultan Daud Khan1https://orcid.org/0000-0002-7406-8441Habib Ullah2https://orcid.org/0000-0002-2434-0849College of Computers and Information Systems, Umm Al-Qura University, Makkah, Saudi ArabiaCollege of Computer Science and Software Engineering, University of Hail, Hail, Saudi ArabiaCollege of Computer Science and Software Engineering, University of Hail, Hail, Saudi ArabiaCounting and localization of people in videos consisting of low density to high density crowds encounter many key challenges including complex backgrounds, scale variations, nonuniform distributions, and occlusions. For this purpose, we propose a scale driven convolutional neural network (SD-CNN) model, which is based on the assumption that heads are the dominant and visible features regardless of the density of crowds. To deal with the problem of different scales of heads in different regions of the videos, we annotate a set of heads in random locations of the videos to develop a scale map representing the mapping of head sizes. We then extract scale aware proposals based on the scale map which are fed to the SD-CNN model acting as a head detector. Our model provides a response matrix rendering accurate head positions via nonmaximal suppression. For experimental evaluations, we consider three standard datasets presenting low density to high density crowd scenes. Our proposed SD-CNN model outperforms the state-of-the-art methods in terms of both frame-level and pixel-level analyses.https://ieeexplore.ieee.org/document/8721049/Convolutional neural networksnon-maximal suppressionhead detectioncrowd countingmotion analysis |
| spellingShingle | Saleh Basalamah Sultan Daud Khan Habib Ullah Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes IEEE Access Convolutional neural networks non-maximal suppression head detection crowd counting motion analysis |
| title | Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes |
| title_full | Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes |
| title_fullStr | Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes |
| title_full_unstemmed | Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes |
| title_short | Scale Driven Convolutional Neural Network Model for People Counting and Localization in Crowd Scenes |
| title_sort | scale driven convolutional neural network model for people counting and localization in crowd scenes |
| topic | Convolutional neural networks non-maximal suppression head detection crowd counting motion analysis |
| url | https://ieeexplore.ieee.org/document/8721049/ |
| work_keys_str_mv | AT salehbasalamah scaledrivenconvolutionalneuralnetworkmodelforpeoplecountingandlocalizationincrowdscenes AT sultandaudkhan scaledrivenconvolutionalneuralnetworkmodelforpeoplecountingandlocalizationincrowdscenes AT habibullah scaledrivenconvolutionalneuralnetworkmodelforpeoplecountingandlocalizationincrowdscenes |