As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Object detection algorithms have been widely used in important fields such as national defense, military industry and transportation. However, due to the limitation of computing power and power consumption of hardware devices, most of the object detection models deployed in mobile devices are lightweight models, and their detection accuracy can not fully meet the needs of complicated scenes. This paper proposes a new model adding path aggregation and attention mechanism to nanodet, an anchor-free detection model, and improves the detection accuracy with litte cost. On our dataset, tested with RTX 3080TI the AP50 reaches 62.09% and only cost little additional inference time. It has a good reference value for the deployment of lightweight model in engineering practice.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.