计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 240100051-7.doi: 10.11896/jsjkx.240100051
于泳波, 孙振, 朱灵茜, 李庆党
YU Yongbo, SUN Zhen, ZHU Lingxi, LI Qingdang
摘要： 针对城市建筑环境下的烟火检测存在检测精度低、耗时较长等问题,提出一种基于YOLOv5s改进的烟火检测算法。首先通过K-means重新聚类针对烟火数据集的先验框;在YOLOv5s的主干特征提取网络中嵌入CA(Coordinate attention)注意力机制,抑制噪声的干扰;借鉴DAMO-YOLO中的Efficient RepGFPN和BiFPN(Bidirectional Feature Pyramid Network)思想设计了一个全新的颈部BiGFPN,重构YOLOv5s的颈部促进多尺度融合;为了有效利用特征图的语义信息,引入轻量级通用上采样算子CARAFE(Content-Aware ReAssembly of Features);为了降低模型改进带来的参数量和计算量,采用GhostNet重构YOLOv5s的颈部;将边界框回归损失函数CIoU替换为SIoU,加速模型的收敛并且提高精度。实验结果表明,改进后的YOLOv5s拥有更少的参数量和计算量,而且mAP50提升了4.6%,基本能够满足烟火检测的要求。
中图分类号:
| [1]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Compu-ter Vision and Pattern Recognition.2014:580-587. [2]GIRSHICKR.Fast R-CNN[C]//Proceedings of the 2015 IEEE/CVF International Conference on Computer Vision.2015:1440-1448. [3]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towardsreal-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149. [4]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788. [5]REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.2017:651. [6]REDMON J,FARHADI A.YOLOv3:an incremental improvement[J].arXiv:1804.02767,2018. [7]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020. [8]FRIZZIS,KAABI R,BOUCHOUICHA M,et al.Convolutional neural netword for video fire and smoke deteciton [C]//IECON 2016-42nd Annual Conference of IEEE Industrial Electronics Society.Florence:IECON,2016.877-882. [9]HOU Y C,WANG H Q,WANG K.Improved multi-scale flamedetection method [J].Chinese Journal of Liquid Crystals and Displays,2021,36(5):751-759. [10]WU S X,ZHANG L B.Using popular object detection methods for real time forest fire detection[C]//11th International Symposium on Computational Intelligence and Design(ISCID).Hang-zhou,China,Piscataway,NJ:IEEE,2018:280-284. [11]HUI T,HALIDAN A,DU H.Multi-type flame detection combined with Faster R-CNN[J].Journal of Image and Graphics,2019,24(1):73-83. [12]WANG Y X,XIAO X L,WANG P F,et al.Improved YOLOv5s small target smoke and fire detection algorithm[J].Computer Engineering and Applications,2023,59(1):72-81. [13]HOU Q,ZHOU D,FENG J.Coordinate attention for efficientmobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13713-13722. [14]XU X,JIANG Y,CHEN W,et al..DAMO-YOLO:A Report on Real-Time Object Detection Design[J].arXiv:2211.15444,2022. [15]TAN M,PANG R,LE Q V.Efficientdet:Scalable and efficientobject detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:10781-10790. [16]WANG J Q,CHEN K,XU R,et al.CARAFE:contentaware reassembly of features[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision.2019:3007-3016. [17]HAN K,WANG Y,TIAN Q,et al.Ghostnet:more featuresfrom cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:1580-1589. [18]GEVORGYAN Z.SIoU loss:more powerful learning for bounding box regression[J].arXiv:2205.12740,2022. [19]ZHENG Z,WANG P,LIU W,et al.Distance- IoU loss:fasterand better learning for bounding box regression[C]// Procee-dings of the AAAI Conference on Artificial Intelligence.2020:12993-13000. [20]LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2018:8759-8768. |
|
||
首页