Abstract
Abstract Since the outbreak of COVID-19, the domestic situation has gradually improved, but small-scale outbreaks are still frequent, the current situation of COVID-19 cannot be eased up. Using target detection algorithms to identify mask wearing to remind people to pay attention to the epidemic, can reduce the probability of cross infection in public places. YOLOv4 is a real-time target detection algorithm with fast detection speed and small size, but it has problems such as insufficient positioning of the bounding box and easy to miss the occluded targets. Based on this, we improve the algorithm and integrates the CBAM attention module into the backbone network. At the same time, the depthwise over-parameterized convolution (DO-Conv) is used to replace the ordinary convolution, which improves the network fitting ability without adding additional parameters. The experimental results show that the improved algorithm has improved the positioning accuracy of the bounding box and detection accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.