提出了一种基于ViBe与目标检测的VSmokeNet烟雾检测算法。首先,该算法通过改进ViBe算法,减少噪声点的引入,提取到完整的运动前景区域,完成对烟雾的粗筛选;接着,利用大样本数据集训练的改进YOLOv5s网络对粗筛得到的烟雾运动前景区域进行二次筛选,最终实现视频烟雾的精确框定。实验结果表明,该算法在各种场景下有良好的检测效果。
Abstract
In the paper,a VSmokeNet smoke detection algorithm based on ViBe and target detection is proposed.Firstly the algorithm improves the ViBe algorithm to reduce the introduction of noise points,extracts the complete moving foreground region,and completes the rough screening of smoke.Then,the improved YOLOv5s network trained by large sample data sets is used to screen the smoke motion foreground area obtained by coarse screening for the second time,and finally the accurate framing of video smoke is achieved.The experimental results show that the algorithm has good detection effect in various scenes.
关键词
目标检测 /
烟雾检测 /
ViBe /
YOLOv5s
Key words
target detection /
smoke detection /
ViBe /
YOLOv5s
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈长友,杨健晟.面向视频图像的烟雾检测算法综述[J].激光与光电子学进展,2021,58(4):29-43.
[2] ZHOU Z Q,SHI Y S,GAO Z F,et al.Wild fire smoke detection based on local extremal region segmentation and surveil lance[J].Fire Safety Journal,2016,85(1):50-58.
[3] Zhao Y,Li Q,Gu Z.Early smoke detection of forest fire video using CS Adaboost algorithm[J].Journal for Light and Electron Optics,2015,126(19):2121-2124.
[4] 陈俊周,汪子杰,陈洪瀚,等.基于级联卷积神经网络的视频动态烟雾检测[J].电子科技大学学报,2016,45(6):992-996.
[5] Yin Z,Wan B,Yuan F,et al.A Deep Normalization and Convolutional Neural Network for Image Smoke Detection[J].IEEE Access,2017(5):18429-18438.
[6] Zhang Q X,Lin G H,Zhang Y M,et al.Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke Images[J].Procedia Engineering,2018(211):441-446.
[7] Wang C,Wang H,Yu F,et al.A High-Precision Fast Smoky Vehicle Detection Method Based on Improved Yolov5 Network[C]//2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID).IEEE,2021.
[8] 杨青,张著洪.改进型ViBe算法及其在运动目标提取中的应用[J].贵州大学学报(自然科学版),2019,36(2):74-78.
[9] LI X,WANG W H,HU X L,et al.Selective kernelnetworks[C]//2019 IEEE/CVF conference on computer vision and pattern recognition(CVPR).Long Beach,CA,USA.IEEE,2019:510-519.
[10] 宋华伟,屈晓娟,杨欣,等.基于改进YOLOv5的火焰雾检测[J].计算机工程,2022(11):1-7.
[11] 杜立召,徐岩,张为.一种双网融合的分阶段烟雾检测算法[J].西安电子科技大学学报,2020,47(4):141-148.
PDF(1990 KB)
