文献类型：会议论文

英文题名：Fast flame recognition algorithm base on segmentation network

作者：Niu, Chunyu[1];Guo, Hui[1];Wang, Yong[2]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai 200237, Peoples R China;[2]Qingdao Univ Technol, Sch Mech & Automot Engn, Qingdao 266033, Peoples R China

会议论文集：30th IEEE Conference Virtual Reality and 3D User Interfaces (IEEE VR)

会议日期：MAR 25-29, 2023

会议地点：Shanghai, PEOPLES R CHINA

语种：英文

外文关键词：Flame recognition; Instance segmentation; Flame positioning; Deep Learning

摘要：To solve the low recognition rate of the network to flame and keep the accuracy, we propose an Instance segmentation model for recognizing and locating flames more accurate This network is improved based on the deep learning model Mask R-CNN, it introduces four key components:(1) After analyzing the effects of space and channel attention, we used an efficient convolution channel attention. (2) By comparing the convolution kernel size, an optimized dilated convolution is added to the network, (3) To eliminate redundancy, reducing the depth of the backbone while guaranteeing the accuracy of the network. (4) Finally, Adding a flame extraction algorithm behind the head. Compared with Mask R-CNN, the model size is reduced by 16.3MB, and the recognition accuracy of flame is improved by 1.7%, The comparison shows that the network can also greatly improve the recognition effect of small flames.