Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration
We present a novel system for anomaly detection in surveillance videos, specifically focusing on identifying instances where individuals deviate from public health guidelines during the pandemic. These anomalies encompassed behaviours like the absence of face masks, incorrect mask usage, coughing, n...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10740272/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846172974821933056 |
|---|---|
| author | Sareer Ul Amin Muhammad Sibtain Abbas Bumsoo Kim Yonghoon Jung Sanghyun Seo |
| author_facet | Sareer Ul Amin Muhammad Sibtain Abbas Bumsoo Kim Yonghoon Jung Sanghyun Seo |
| author_sort | Sareer Ul Amin |
| collection | DOAJ |
| description | We present a novel system for anomaly detection in surveillance videos, specifically focusing on identifying instances where individuals deviate from public health guidelines during the pandemic. These anomalies encompassed behaviours like the absence of face masks, incorrect mask usage, coughing, nose-picking, sneezing, spitting, and yawning. Monitoring such anomalies manually was challenging and prone to errors, necessitating automated solutions. To address this, a multi-attention-based deep learning system was employed, utilizing the EfficientNet-B0 architecture. EfficientNet-B0, featuring the Mobile Inverted Bottleneck Convolution (MBConv) block with Squeeze-and-Excitation (SE) modules, emphasizes informative channel characteristics while disregarding irrelevant ones. However, this approach neglected crucial spatial information necessary for visual recognition tasks. To improve this, the Convolutional Block Attention Module (CBAM) was integrated into EfficientNet-B0 to improve feature extraction. The baseline EfficientNet-B0 model’s SE module was replaced with the CBAM module within each MBConv module to retain spatial information related to anomaly activities. Additionally, the CBAM module, when embedded after the second convolutional layer, was observed to significantly enhance the classification ability of the model across different anomaly classes, resulting in a significant accuracy boost from 87 to 96%. In conclusion, we demonstrated the efficacy of the CBAM module in refining feature extraction and improving the classification performance of the proposed method, showcasing its potential for robust anomaly detection in surveillance videos. |
| format | Article |
| id | doaj-art-a0e96b30949c4e0e95514ea0842f26f2 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a0e96b30949c4e0e95514ea0842f26f22024-11-09T00:01:30ZengIEEEIEEE Access2169-35362024-01-011216269716271210.1109/ACCESS.2024.348879710740272Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM IntegrationSareer Ul Amin0https://orcid.org/0000-0001-9479-3846Muhammad Sibtain Abbas1https://orcid.org/0009-0008-0536-3894Bumsoo Kim2https://orcid.org/0000-0002-2188-3581Yonghoon Jung3https://orcid.org/0009-0006-8054-6012Sanghyun Seo4https://orcid.org/0000-0002-4824-3517Department of Computer Science and Engineering, Chung-Ang University, Seoul, South KoreaDepartment of Architectural Engineering, Chung-Ang University, Seoul, South KoreaDepartment of Applied Art and Technology, Chung-Ang University, Anseong-si, South KoreaDepartment of Applied Art and Technology, Chung-Ang University, Anseong-si, South KoreaCollege of Art and Technology, Chung-Ang University, Anseong-si, South KoreaWe present a novel system for anomaly detection in surveillance videos, specifically focusing on identifying instances where individuals deviate from public health guidelines during the pandemic. These anomalies encompassed behaviours like the absence of face masks, incorrect mask usage, coughing, nose-picking, sneezing, spitting, and yawning. Monitoring such anomalies manually was challenging and prone to errors, necessitating automated solutions. To address this, a multi-attention-based deep learning system was employed, utilizing the EfficientNet-B0 architecture. EfficientNet-B0, featuring the Mobile Inverted Bottleneck Convolution (MBConv) block with Squeeze-and-Excitation (SE) modules, emphasizes informative channel characteristics while disregarding irrelevant ones. However, this approach neglected crucial spatial information necessary for visual recognition tasks. To improve this, the Convolutional Block Attention Module (CBAM) was integrated into EfficientNet-B0 to improve feature extraction. The baseline EfficientNet-B0 model’s SE module was replaced with the CBAM module within each MBConv module to retain spatial information related to anomaly activities. Additionally, the CBAM module, when embedded after the second convolutional layer, was observed to significantly enhance the classification ability of the model across different anomaly classes, resulting in a significant accuracy boost from 87 to 96%. In conclusion, we demonstrated the efficacy of the CBAM module in refining feature extraction and improving the classification performance of the proposed method, showcasing its potential for robust anomaly detection in surveillance videos.https://ieeexplore.ieee.org/document/10740272/Anomaly detectionvideo surveillancecomputer visionattention methodintelligent surveillance system |
| spellingShingle | Sareer Ul Amin Muhammad Sibtain Abbas Bumsoo Kim Yonghoon Jung Sanghyun Seo Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration IEEE Access Anomaly detection video surveillance computer vision attention method intelligent surveillance system |
| title | Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration |
| title_full | Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration |
| title_fullStr | Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration |
| title_full_unstemmed | Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration |
| title_short | Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration |
| title_sort | enhanced anomaly detection in pandemic surveillance videos an attention approach with efficientnet b0 and cbam integration |
| topic | Anomaly detection video surveillance computer vision attention method intelligent surveillance system |
| url | https://ieeexplore.ieee.org/document/10740272/ |
| work_keys_str_mv | AT sareerulamin enhancedanomalydetectioninpandemicsurveillancevideosanattentionapproachwithefficientnetb0andcbamintegration AT muhammadsibtainabbas enhancedanomalydetectioninpandemicsurveillancevideosanattentionapproachwithefficientnetb0andcbamintegration AT bumsookim enhancedanomalydetectioninpandemicsurveillancevideosanattentionapproachwithefficientnetb0andcbamintegration AT yonghoonjung enhancedanomalydetectioninpandemicsurveillancevideosanattentionapproachwithefficientnetb0andcbamintegration AT sanghyunseo enhancedanomalydetectioninpandemicsurveillancevideosanattentionapproachwithefficientnetb0andcbamintegration |