基于高斯建模的电力场景明火检测Flame detection in electric power scenarios based on Gaussian modeling
黄均才,刘鉴栋,闫云凤,齐冬莲
HUANG Juncai,LIU Jiandong,YAN Yunfeng,QI Donglian
摘要(Abstract)：
基于深度学习的电力场景明火识别研究尚存在两个问题：一是相比于通用物体的清晰边界，火焰的边界具有很强的模糊性；二是基于深度学习的方法需要大量有标签的数据进行训练，但是目前严重缺乏电力场景下大规模的明火检测数据。针对第一个问题，通过对传统YOLOv5检测器进行改进，基于高斯建模捕获边框的不确定性；针对第二个问题，提出一种基于迁移学习的两阶段训练方法，只需要少量电力场景明火图片即可实现高精度的电力场景明火检测器训练。为了验证所提方法的有效性，利用网络公开数据及自有数据进行对比实验，结果表明所提出的方法具有很强的适用性。
There are two problems in flame detection in electric power scenarios based on deep learning:1)In contrast to the clear boundaries of general objects,the flame boundary is much hazy;2)The deep learning-based methods require a large amount of labeled data for training;however,there is a severe shortage of large-scale flame detection data in electric power scenarios. In response to the first problem,this paper improves the traditional YOLOv5 detector to capture the uncertainty of the frame through Gaussian modeling. For the second question,this paper proposes a two-stage training method based on migration learning,which requires only a small number of flame data of the power scenarios for high-precision flame detector training. For verifying the effectiveness of the proposed method,accessible data on the internet and private data are used for contrast experiment. The results show that the proposed method is of great adaptability.
关键词(KeyWords)：
电力场景;明火识别;深度学习;目标检测
electric power scenario;flame recognition;deep learning;object detection
基金项目(Foundation):
作者(Author):
黄均才,刘鉴栋,闫云凤,齐冬莲
HUANG Juncai,LIU Jiandong,YAN Yunfeng,QI Donglian
DOI: 10.19585/j.zjdl.202210004
参考文献(References)：
- [1] HORNG W B,PENG J W,CHEN C Y.A new imagebased real-time flame detection method using color analysis[C]//Proceedings 2005 IEEE Networking,Sensing and Control.Tucson:IEEE,2005:100-105.
- [2] CELIK T,DEMIREL H. Fire detection in video sequences using a generic color model[J].Fire Safety Journal,2009,44(2):147-158.
- [3]刘佳丽，叶炯耀.基于Ohta颜色空间的多信息融合火焰检测[J].华东理工大学学报（自然科学版），2019,45(6):962-969.
- [4] PREMAL C E,VINSLEY S S. Image processing based forest fire detection using YCbCr colour model[C]//2014International Conference on Circuits,Power and Computing Technologies(ICCPCT—2014). Kumaracoil:IEEE,2014:1229-1237.
- [5]张宾.基于视频的火灾火焰检测[D].鞍山：辽宁科技大学，2012.
- [6] KIM M G,PAN S B.A study on the flame detection and object classification technique using the color information[C]//2015 10th International Conference for Internet Technology and Secured Transactions(ICITST). London:IEEE,2015:120-123.
- [7] DIMITROPOULOS K,BARMPOUTIS P,GRAMMALIDIS N.Spatio-temporal flame modeling and dynamic texture analysis for automatic video-based fire detection[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,25(2):339-351.
- [8] CHOU K P,PRASAD M,GUPTA D,et al.Block-based feature extraction model for early fire detection[C]//2017IEEE Symposium Series on Computational Intelligence(SSCI).Hawaii:IEEE,2017:1-8.
- [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]侯易呈，王慧琴，王可.改进的多尺度火焰检测方法[J].液晶与显示，2021,36(5):751-759.
- [11]张玉萍.基于PCNN的森林火灾图像识别方法研究[D].哈尔滨：哈尔滨理工大学，2021.
- [12] HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
- [13] LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//The IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:8759-8768.
- [14] REDMON J,FARHADI A.Yolov3:An incremental improvement[J].arXiv Preprint,2018:1804.02767.