Real-time segmentation method of billet infrared image based on multi-scale feature fusion

Abstract

Obtaining the surface temperature of billets in heating furnaces has been a hot research in metallurgical industry applications. In order to accurately identify the billet location in infrared images and thus obtain the surface temperature of billets, this paper proposes a real-time segmentation network model based on multi-scale feature fusion to solve the problems of low resolution, low accuracy and slow detection speed of infrared images of traditional target image detection methods. In our method, a dataset with billet infrared images as the experimental object is firstly established, and the proposed network structure adopts multi-scale feature fusion to enhance the information interaction between feature maps at all levels and reduce the information loss during up-sampling by a dense up-sampling strategy. Meanwhile, a lightweight backbone network and deep separable convolution are used to reduce the number of network parameters and speed up the network inference, finally realizing real-time and accurate segmentation of the infrared images of blanks. The highest accuracy of the model in this paper reaches 94.89%. Meanwhile, an inference speed of 80fps is achieved on GTX2080Ti. Compared with the existing mainstream methods, the method in this paper can better meet the real-time and accuracy requirements of industrial production.