Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition
Emerging deep learning (DL) approaches with edge computing have enabled the automation of rich information extraction, such as complex events from camera feeds. Due to the low speed and accuracy of object detection, some objects are missed and not detected. As objects constitute simple events, missi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/2/81 |
| _version_ | 1797396101145296896 |
|---|---|
| author | Sepehr Honarparvar Sara Saeedi Steve Liang Jeremy Squires |
| author_facet | Sepehr Honarparvar Sara Saeedi Steve Liang Jeremy Squires |
| author_sort | Sepehr Honarparvar |
| collection | DOAJ |
| description | Emerging deep learning (DL) approaches with edge computing have enabled the automation of rich information extraction, such as complex events from camera feeds. Due to the low speed and accuracy of object detection, some objects are missed and not detected. As objects constitute simple events, missing objects result in missing simple events, thus the number of detected complex events. As the main objective of this paper, an integrated cloud and edge computing architecture was designed and developed to reduce missing simple events. To achieve this goal, we deployed multiple smart cameras (i.e., cameras which connect to the Internet and are integrated with computerised systems such as the DL unit) in order to detect complex events from multiple views. Having more simple events from multiple cameras can reduce missing simple events and increase the number of detected complex events. To evaluate the accuracy of complex event detection, the F-score of risk behaviour regarding COVID-19 spread events in video streams was used. The experimental results demonstrate that this architecture delivered 1.73 times higher accuracy in event detection than that delivered by an edge-based architecture that uses one camera. The average event detection latency for the integrated cloud and edge architecture was 1.85 times higher than that of only one camera. However, this finding was insignificant with regard to the current case study. Moreover, the accuracy of the architecture for complex event matching with more spatial and temporal relationships showed significant improvement in comparison to the edge computing scenario. Finally, complex event detection accuracy considerably depended on object detection accuracy. Regression-based models, such as you only look once (YOLO), were able to provide better accuracy than region-based models. |
| first_indexed | 2024-03-09T00:45:25Z |
| format | Article |
| id | doaj.art-282c22462a574494abe626f106a794a7 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T00:45:25Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-282c22462a574494abe626f106a794a72023-12-11T17:30:51ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-02-011028110.3390/ijgi10020081Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour RecognitionSepehr Honarparvar0Sara Saeedi1Steve Liang2Jeremy Squires3Department of Geomatics Engineering, University of Calgary, Calgary, AB T2N 4V8, CanadaDepartment of Geomatics Engineering, University of Calgary, Calgary, AB T2N 4V8, CanadaDepartment of Geomatics Engineering, University of Calgary, Calgary, AB T2N 4V8, CanadaSensorUp Inc., Calgary, AB T2L2K7, CanadaEmerging deep learning (DL) approaches with edge computing have enabled the automation of rich information extraction, such as complex events from camera feeds. Due to the low speed and accuracy of object detection, some objects are missed and not detected. As objects constitute simple events, missing objects result in missing simple events, thus the number of detected complex events. As the main objective of this paper, an integrated cloud and edge computing architecture was designed and developed to reduce missing simple events. To achieve this goal, we deployed multiple smart cameras (i.e., cameras which connect to the Internet and are integrated with computerised systems such as the DL unit) in order to detect complex events from multiple views. Having more simple events from multiple cameras can reduce missing simple events and increase the number of detected complex events. To evaluate the accuracy of complex event detection, the F-score of risk behaviour regarding COVID-19 spread events in video streams was used. The experimental results demonstrate that this architecture delivered 1.73 times higher accuracy in event detection than that delivered by an edge-based architecture that uses one camera. The average event detection latency for the integrated cloud and edge architecture was 1.85 times higher than that of only one camera. However, this finding was insignificant with regard to the current case study. Moreover, the accuracy of the architecture for complex event matching with more spatial and temporal relationships showed significant improvement in comparison to the edge computing scenario. Finally, complex event detection accuracy considerably depended on object detection accuracy. Regression-based models, such as you only look once (YOLO), were able to provide better accuracy than region-based models.https://www.mdpi.com/2220-9964/10/2/81internet of thingsCOVID-19video streamingcomplex event detectionsmart cameraedge processing |
| spellingShingle | Sepehr Honarparvar Sara Saeedi Steve Liang Jeremy Squires Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition ISPRS International Journal of Geo-Information internet of things COVID-19 video streaming complex event detection smart camera edge processing |
| title | Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition |
| title_full | Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition |
| title_fullStr | Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition |
| title_full_unstemmed | Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition |
| title_short | Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition |
| title_sort | design and development of an internet of smart cameras solution for complex event detection in covid 19 risk behaviour recognition |
| topic | internet of things COVID-19 video streaming complex event detection smart camera edge processing |
| url | https://www.mdpi.com/2220-9964/10/2/81 |
| work_keys_str_mv | AT sepehrhonarparvar designanddevelopmentofaninternetofsmartcamerassolutionforcomplexeventdetectionincovid19riskbehaviourrecognition AT sarasaeedi designanddevelopmentofaninternetofsmartcamerassolutionforcomplexeventdetectionincovid19riskbehaviourrecognition AT steveliang designanddevelopmentofaninternetofsmartcamerassolutionforcomplexeventdetectionincovid19riskbehaviourrecognition AT jeremysquires designanddevelopmentofaninternetofsmartcamerassolutionforcomplexeventdetectionincovid19riskbehaviourrecognition |