基于改进YOLOV5的火焰检测算法

摘要/Abstract

摘要： 针对现有的火焰检测算法检测平均精度低、小目标火焰漏检率高的问题，提出一种改进YOLOV5的火焰检测算法。该算法使用Transformer Encode模块代替YOLOV5主干网络末端的CSP bottleneck模块，以增强网络捕获不同局部信息的能力，提高火焰检测的平均精度，并且在YOLOV5网络中增加CBAM注意力模块，增强网络提取图像特征的能力，对于小目标火焰能够较好地提取特征，降低小目标火焰的漏检率。将该算法在公开数据集BoWFire、Bilkent上进行实验，结果表明，改进YOLOV5网络的火焰检测平均精度更高，可达83.9%，小目标火焰漏检率更低，仅为1.6%，检测速率为34帧/s，相比于原YOLOV5网络，平均精度提升了2.4个百分点，小目标火焰漏检率降低了4.1个百分点，改进后的YOLOV5网络能够满足火焰检测的实时性和精度要求。

关键词: YOLOV5算法, Transformer, CBAM注意力

Abstract: Aiming at the existing flame detection algorithms having problems of low average detection accuracy and high missed detection rate of small target flames， an improved YOLOV5 flame detection algorithm is proposed. The algorithm uses the Transformer Encode module to replace the CSP bottleneck module at the end of the YOLOV5 backbone network， which enhances the network's ability to capture different local information and improves the average accuracy of flame detection. In addition， the CBAM attention module is added to the YOLOV5 networker， which enhances the network's ability to extract image features， and can better extract features for small target flames， reducing the missed detection rate of small target flames. Experiment with the algorithm on the public datasets BoWFire and Bilkent， the experimental results show that the average flame detection accuracy of the improved YOLOV5 network is higher， reaching 83.9%， the small target flame missed detection rate is lower， only 1.6%， and the detection rate is 34 frames/s. Compared with the original YOLOV5 network， the average accuracy is improved 2.4 percentage points， the small target flame missed detection rate is reduced by 4.1 percentage points， the improved YOLOV5 network can meet the real-time and precision requirements of flame detection.

Key words: YOLOV5 algorithm, Transformer, CBAM attention

王洪义, 孔梅梅, 徐荣青. 基于改进YOLOV5的火焰检测算法[J]. 计算机与现代化, 2023, 0(01): 103-107.

WANG Hong-yi, KONG Mei-mei, XU Rong-qing. Flame Detection Algorithm Based on Improved YOLOV5[J]. Computer and Modernization, 2023, 0(01): 103-107.

参考文献

［1］ FOGGIA P， SAGGESE A， VENTO M. Real-time fire detection for video-surveillance applications using a combination of experts based on color， shape， and motion［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2015，25（9）:1545-1556.
［2］ ZHANG Q， LIU X J， HUANF L. Video image fire recognition based on color space and moving object detection［C］// 2020 International Conference on Artificial Intelligence and Computer Engineering （ICAICE）. 2020:367-371.
［3］杨晓帆，陈廷槐.人工神经网络固有的优点和缺点［J］.计算机科学， 1994（2）:23-26.
［4］ CHUNG Y L， CHUNG H Y， CHOU C W. Efficient flame recognition method based on a deep convolutional neural network and image processing［C］// 2019 IEEE 8th Global Conference on Consumer Electronics（GCCE）. 2019:573-574.
［5］ CHAOXIA C Y， SHANG W W， ZHANG F. Information-guided flame detection based on faster R-CNN［J］. IEEE Access， 2020，8:58923-58932.
［6］王婉婷，姜国龙，褚云飞，等. 从RCNN到YOLO系列的物体检测系统综述［J］. 齐鲁工业大学学报， 2021，35（5）:9-16.
［7］谈世磊，别雄波，卢功林，等. 基于YOLOv5网络模型的人员口罩佩戴实时检测［J］. 激光杂志， 2021，42（2）:147-150.
［8］ DAI Z T. Image flame detection method based on improved YOLOv3［J］. IOP Conference Series Earth and Environmental Science， 2021，693（1）:012012.
［9］赵媛媛，朱军，谢亚坤，等. 改进Yolo-v3的视频图像火焰实时检测算法［J］. 武汉大学学报（信息科学版）， 2021，46（3）:326-334.
［10］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017:6000-6010.
［11］ WOO S， PARK J， LEE J， et al. CBAM: Convolutional block attention module［C］// Proceedings of the 15th European Conference on Computer Vision. 2018:3-19.
［12］ REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN: Towards real-time object detection with region proposal networks［J］. Advances in Neural Information Processing Systems， 2015，28:91-99.
［13］ REDMON J， FARHADI A. Yolov3: An incremental improvement［J］. arXiv preprint arXiv:1804.02767， 2018.
［14］ BOCHKOVSKIY A， WANG C Y， LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection［J］. arXiv preprint arXiv:2004.10934， 2020．
［15］ LIU S， QI L， QIN H F， 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.
［16］ 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.
［17］ DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16×16 words: Transformers for image recognition at scale［J］. arXiv preprint arXiv:2010.11929， 2020.
［18］王国睿. 基于Transformer改进YOLO v4的火灾检测方法［J］. 智能计算机与应用， 2021，11（7）:86-90.
［19］ ZHU X K， LYU S C， WANG X， et al. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. 2021:2778-2788.
［20］ HE K M， ZHANG X Y， REN S Q， et al. Identity mappings in deep residual networks［C］// 2016 European Conference on Computer Vision. 2016:630-645.
［21］ DONG Y H， CORDONNIER J B， LOUKAS A. Attention is not all you need: Pure attention loses rank doubly exponentially with Depth［J］. arXiv preprint arXiv: 2103.03404， 2021.
［22］谭富祥，钱育蓉，孔钰婷，等. 基于Transformer的多分支单图像去雨方法［J］. 计算机应用研究， 2022，39（8）:2500-2505.
［23］赵冬梅，李志坚. 基于Transformer的网络安全态势预测［J］. 华中科技大学学报（自然科学版）， 2022，50（5）:46-52.
［24］ WOO S， PARK J， LEE J Y， et al. CBAM: Convolutional block attention module［C］// Proceedings of the 15th European Conference on Computer Vision （ECCV）. 2018: 3-19.
［25］ FU H X， SONG G Q， WANG Y C. Improved YOLOv4 marine target detection combined with CBAM［J］. Symmetry， 2021，13（4）:623.
［26］王生霄，侯兴松，黑夏萌. 嵌入CBAM结构的改进YOLOV3超宽带雷达生命信号检测算法［J］. 国外电子测量技术， 2020，39（3）:1-6.
［27］付国栋，黄进，杨涛，等. 改进CBAM的轻量级注意力模型［J］. 计算机工程与应用， 2021，57（20）:150-156.
［28］ LI W Z， YU Z Y. A lightweight convolutional neural network flame detection algorithm［C］// 2021 IEEE 11th International Conference on Electronics Information and Emergency Communication （ICEIEC）. 2021:83-86.

[1]	王海洋, 弓同鑫, 杨锦涛, 陈再龙. 多尺度时间编码的工业园区短期负荷预测[J]. 计算机与现代化, 2024, 0(12): 59-65.
[2]	李岸然1, 方阳阳2, 程慧杰2, 张申申2, 阎金强3, 于腾3, 杨国为3. 基于双流Transformer的单幅图像去雾方法[J]. 计算机与现代化, 2024, 0(03): 78-84.
[3]	李亚平, 王军防, 余红梅, 窦一民, 肖媛, 田继林. Regformer：基于稀疏注意力的输油管道水力压降预测方法[J]. 计算机与现代化, 2024, 0(01): 59-66.
[4]	付鸿林, 张太红, 杨雅婷, 艾孜麦提·艾瓦尼尔, 马博. 基于生成对抗网络的维语场景文字修改网络[J]. 计算机与现代化, 2024, 0(01): 41-46.
[5]	许叶彤, 耿信哲, 赵伟强, 张月, 宁海龙, 雷涛. 基于CNN-Transformer混合结构的遥感影像变化检测模型[J]. 计算机与现代化, 2023, 0(07): 79-85.
[6]	刘静, 陈金广. 基于通道注意力和Transformer的图像标题生成方法[J]. 计算机与现代化, 2023, 0(05): 8-12.
[7]	林椹尠, 屈嘉欣, 罗亮. 基于改进的Transformer_decoder的增强图像描述[J]. 计算机与现代化, 2023, 0(01): 7-12.
[8]	李鑫, 任德均, 任秋霖, 曹林杰, 闫宗一. 基于Retinanet的轮毂焊缝检测定位方法[J]. 计算机与现代化, 2022, 0(09): 60-67.
[9]	陈彤, 周登文. 基于多级Transformer的超大倍率重建网络:参考图像超分辨率[J]. 计算机与现代化, 2022, 0(08): 121-126.
[10]	何晨曦, 王正勇, 卿粼波, 何小海, 吴小强. 基于全局自注意力的小麦图像识别[J]. 计算机与现代化, 2022, 0(04): 38-44.
[11]	冯茹嘉, 张海军, 潘伟民. 基于情感分析和Transformer模型的微博谣言检测[J]. 计算机与现代化, 2021, 0(10): 1-7.
[12]	李欣晔, 张承强, 周雄图, 郭太良, 张永爱. 多场景融合的细粒度图像描述生成算法[J]. 计算机与现代化, 2021, 0(09): 1-6.
[13]	杨佳雪, 彭国争, 韩立新. 基于用户动态兴趣的视频点击率预测模型[J]. 计算机与现代化, 2021, 0(03): 82-87.