A Model Development of Smoker Detector Captured in CCTV Footage using MobileNetv2-SSD Algorithm | IEEE Conference Publication | IEEE Xplore

A Model Development of Smoker Detector Captured in CCTV Footage using MobileNetv2-SSD Algorithm


Abstract:

The development of a model for identifying smokers in closed-circuit video (CCTV) footage is presented in this research work employing the MobileNetv2 - SSD (Single Shot ...Show More

Abstract:

The development of a model for identifying smokers in closed-circuit video (CCTV) footage is presented in this research work employing the MobileNetv2 - SSD (Single Shot MultiBox Detector) algorithm. The vitality of the research hinges in its ability to automatically monitor and enforce no-smoking policies in the Philippines, improving public health and safety. With the usage of this model, smoking infractions can be reduced while also alleviating the workload of manual monitoring while providing prompt solutions. According to the research’s finding, the proposed model exhibits excellent results in terms of accuracy, precision, sensitivity/recall, specificity, and F1-score evaluation. The following test results for the MobileNetV2 SSD algorithm were obtained for the detection of smokers: Accuracy: 0.9722, Precision: 0.9728, Sensitivity/Recall: 0.9722, Specificity: 0.9722, and F1-score: 0.9722. These findings demonstrate the developed model’s efficacy and durability in accurately recognizing smoking incidents in CCTV footage. This study’s findings pave the way for further research, such as adding multimodal data and building real-world applications of the smoker detection system.
Date of Conference: 10-13 October 2023
Date Added to IEEE Xplore: 16 November 2023
ISBN Information:

ISSN Information:

Conference Location: Nara, Japan

References

References is not available for this document.