LCDnet: a lightweight crowd density estimation model for real-time video surveillance

<p dir="ltr">Automatic crowd counting using density estimation has gained significant attention in computer vision research. As a result, a large number of crowd counting and density estimation models using convolution neural networks (CNN) have been published in the last few years....

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Muhammad Asif Khan (7367468) (author)
مؤلفون آخرون: Hamid Menouar (16904844) (author), Ridha Hamila (7006457) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513530567327744
author Muhammad Asif Khan (7367468)
author2 Hamid Menouar (16904844)
Ridha Hamila (7006457)
author2_role author
author
author_facet Muhammad Asif Khan (7367468)
Hamid Menouar (16904844)
Ridha Hamila (7006457)
author_role author
dc.creator.none.fl_str_mv Muhammad Asif Khan (7367468)
Hamid Menouar (16904844)
Ridha Hamila (7006457)
dc.date.none.fl_str_mv 2023-03-06T03:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s11554-023-01286-8
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/LCDnet_a_lightweight_crowd_density_estimation_model_for_real-time_video_surveillance/24998270
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Computer vision and multimedia computation
Machine learning
Crowd counting
CNN
Density estimation
Lightweight
Real-time
dc.title.none.fl_str_mv LCDnet: a lightweight crowd density estimation model for real-time video surveillance
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Automatic crowd counting using density estimation has gained significant attention in computer vision research. As a result, a large number of crowd counting and density estimation models using convolution neural networks (CNN) have been published in the last few years. These models have achieved good accuracy over benchmark datasets. However, attempts to improve the accuracy often lead to higher complexity in these models. In real-time video surveillance applications using drones with limited computing resources, deep models incur intolerable higher inference delay. In this paper, we propose (i) a Lightweight Crowd Density estimation model (LCDnet) for real-time video surveillance, and (ii) an improved training method using curriculum learning (CL). LCDnet is trained using CL and evaluated over two benchmark datasets i.e., DroneRGBT and CARPK. Results are compared with existing crowd models. Our evaluation shows that the LCDnet achieves a reasonably good accuracy while significantly reducing the inference time and memory requirement and thus can be deployed over edge devices with very limited computing resources.</p><h2>Other Information</h2><p dir="ltr">Published in: Journal of Real-Time Image Processing<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11554-023-01286-8" target="_blank">https://dx.doi.org/10.1007/s11554-023-01286-8</a></p>
eu_rights_str_mv openAccess
id Manara2_4dae97b164691427429eeedc9cba0aad
identifier_str_mv 10.1007/s11554-023-01286-8
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24998270
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling LCDnet: a lightweight crowd density estimation model for real-time video surveillanceMuhammad Asif Khan (7367468)Hamid Menouar (16904844)Ridha Hamila (7006457)Information and computing sciencesComputer vision and multimedia computationMachine learningCrowd countingCNNDensity estimationLightweightReal-time<p dir="ltr">Automatic crowd counting using density estimation has gained significant attention in computer vision research. As a result, a large number of crowd counting and density estimation models using convolution neural networks (CNN) have been published in the last few years. These models have achieved good accuracy over benchmark datasets. However, attempts to improve the accuracy often lead to higher complexity in these models. In real-time video surveillance applications using drones with limited computing resources, deep models incur intolerable higher inference delay. In this paper, we propose (i) a Lightweight Crowd Density estimation model (LCDnet) for real-time video surveillance, and (ii) an improved training method using curriculum learning (CL). LCDnet is trained using CL and evaluated over two benchmark datasets i.e., DroneRGBT and CARPK. Results are compared with existing crowd models. Our evaluation shows that the LCDnet achieves a reasonably good accuracy while significantly reducing the inference time and memory requirement and thus can be deployed over edge devices with very limited computing resources.</p><h2>Other Information</h2><p dir="ltr">Published in: Journal of Real-Time Image Processing<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11554-023-01286-8" target="_blank">https://dx.doi.org/10.1007/s11554-023-01286-8</a></p>2023-03-06T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s11554-023-01286-8https://figshare.com/articles/journal_contribution/LCDnet_a_lightweight_crowd_density_estimation_model_for_real-time_video_surveillance/24998270CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/249982702023-03-06T03:00:00Z
spellingShingle LCDnet: a lightweight crowd density estimation model for real-time video surveillance
Muhammad Asif Khan (7367468)
Information and computing sciences
Computer vision and multimedia computation
Machine learning
Crowd counting
CNN
Density estimation
Lightweight
Real-time
status_str publishedVersion
title LCDnet: a lightweight crowd density estimation model for real-time video surveillance
title_full LCDnet: a lightweight crowd density estimation model for real-time video surveillance
title_fullStr LCDnet: a lightweight crowd density estimation model for real-time video surveillance
title_full_unstemmed LCDnet: a lightweight crowd density estimation model for real-time video surveillance
title_short LCDnet: a lightweight crowd density estimation model for real-time video surveillance
title_sort LCDnet: a lightweight crowd density estimation model for real-time video surveillance
topic Information and computing sciences
Computer vision and multimedia computation
Machine learning
Crowd counting
CNN
Density estimation
Lightweight
Real-time