摘要
为解决火焰实时检测参数量大、对硬件计算能力要求高等问题,提出了改进型YOLO v4-tiny的轻量级火焰实时检测模型。首先,对模型的参数进行了修剪;其次,通过在模型的浅层加入改进型的CSP-RFBs,扩大网络浅层的感受野;然后,对CSP-ResNet的框架进行改进,提出了速度更快、准确率更高的沙漏型CSP-ResNet;最后,在网络深层采用改进型CSP-SPPs,对多重感受野进行进一步融合。实验结果表明,改进型YOLO v4-tiny模型的准确率可达48.5%,较原模型提升了15.5%;模型的参数量和权重文件大小分别为2.45 BFLOPs和16.3 Mb,分别比原模型减少了63.9%和30.6%。在移动开发板NVIDIA Jeston Xavier上FPS可达49.6,比原模型提升了21.9%。
In order to solve the problems of large number of parameters for real-time flame detection and high requirements for hardware computing power,a lightweight real-time flame detection model based on improved YOLO v4-tiny is proposed.Firstly,the parameters of the model are pruned.Secondly,by adding improved Receptive Field Blocks(CSP-RFBs)in the shallow layer of the model,the perceptual field of the model shallow layer is improved.Thirdly,the framework of CSP-ResNet is improved,and the“hourglass CSP-ResNet”with faster and higher accuracy is proposed.Finally,a modified Spatial Pyramid Pooling(SPP)is adopted at the deep level of the model to further fuse the multiple sensory fields.The experimental results show that the accuracy of the improved YOLO v4-tiny model can reach 48.5%,which is 15.5%better than the original model.The number of parameters of the model and the weight size of the weight file are 2.45BFLOPs and 16.3Mb,which are 63.9%and 30.6%less than the original model,respectively.The FPS on the mobile development board NVIDIA Jeston Xavier can reach 49.6,which is 21.9%better than the original model.
作者
王冠博
赵一帆
李波
杨俊东
丁洪伟
WANG Guan-bo;ZHAO Yi-fan;LI Bo;YANG Jun-dong;DING Hong-wei(School of Information Science&Engineering,Yunnan University,Kunming 650504;School of Electrical and Information Engineering,Yunnan University for Nationalities,Kunming 650031,China)
出处
《计算机工程与科学》
CSCD
北大核心
2022年第12期2196-2205,共10页
Computer Engineering & Science
基金
国家自然科学基金(61461053,61461054)。
作者简介
王冠博(1994),男,河南驻马店人,硕士生,研究方向为深度学习和计算机视觉。E-mail:1271578900@qq.com;赵一帆(1986),男,云南昆明人,博士,讲师,研究方向为电信技术、计算机软件和计算机应用。E-mail:17633894428@163.com;李波(1976),男,云南昆明人,博士,教授,研究方向为移动云计算和物联网。E-mail:1341587473@qq.com;杨俊东(1975),男,云南昆明人,博士,讲师,研究方向为通信系统理论及其应用研究。E-mail:17633891018@163.com;通信作者:丁洪伟(1964),男,云南昆明人,博士,教授,博士生导师,研究方向为多址通信技术和深度学习。E-mail:rcod1024@163.com,通信地址:650504云南省昆明市呈贡区云南大学呈贡校区信息学院。
