In order to improve the accuracy and speed of object detection on infrared images, an object detection method based on YOLOv3 is proposed. First, the rectangle filling, Mosaic data augmentation and adaptive anchors are used for data preprocessing, which lays the foundation for subsequent network training. Secondly, the convolution calculation layer and the cross stage partial module are used for the lightweight design to achieve high-speed detection while maintaining high-accurate. Then, spatial pyramid pooling is used to improve the learning ability of the network by enhancing the receptive field. Finally, bottom-up path augmentation is used to improve multi-layer feature fusion, which improves the transmission speed and utilization rate of low-level feature information. The experimental results show that the proposed method can detect cars accurately. Compared YOLOv3 methods, the proposed method has higher accuracy and faster speed, which meets the requirements of accurate and rapid detection on infrared images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.