首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201021--1)

基于定位置信度和区域全卷积网络的火焰检测方法

Fire Detection Method Based on Localization Confidence and Region-Based Fully Convolutional Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对火焰检测定位精度与检测精度不高的问题,提出了基于定位置信度和区域全卷积网络的火焰检测方法。首先使用扩大的可分离卷积提高感受野,减少模型参数量,提高检测速度;其次对预测候选框进行平移和伸缩操作,以提高候选区域的完整性;然后对非极大值抑制方法采用分类置信度作为排序标准,而导致的错误抑制问题,引入定位置信度,以提高候选框的定位精度及检测精度;最后加入新的标签,分别代表特征不明显的弱火焰与特征明显的强火焰,对弱火焰样本加强学习,使得弱火焰能与亮色背景更好区分,从而降低样本漏检率。实验结果表明,本文方法在Bilkent大学公开火焰数据集以及互联网搜集的测试数据上,检测的火焰区域更完整,火焰位置更精确,火焰检测率更高。

Abstract

Aiming at the problem of low location accuracy and detection accuracy of fire detection, a fire detection method based on localization confidence and region-based fully convolutional network is proposed. First, expanded separable convolutions are used to improve the receptive field, reduce the amount of model parameters, and improve the detection speed. Second, the prediction candidate frame is translated and stretched to improve the integrity of the candidate region. Then, for non-maximum suppression method, the classification confidence degree is used as a sorting standard, which leads to the error suppression problem, so as to improve the location accuracy and detection accuracy of the candidate frame. Finally, new tags are added, they represent the weak fire with no obvious characteristics and the strong fire with obvious characteristics, respectively. The weak fire samples are strengthened to distinguish the weak fire from the bright background, so as to reduce the sample missing rate. Experimental results show that the proposed method, based on the public fire data set of Bilkent University and the test data collected from the internet, can make the fire area detected to be more complete. The fire position is more accurate, and the fire detection rate is higher.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.9

DOI:10.3788/LOP57.201021

所属栏目:图像处理

基金项目:国家自然科学基金、江苏省“六大人才高峰”项目、江苏省高校自然科学基金重大项目、江苏省“青蓝工程”、淮安市“533英才工程”、淮安市自然科学课题;

收稿日期:2020-02-12

修改稿日期:2020-03-12

网络出版日期:2020-10-01

作者单位    点击查看

张鸿:江南大学物联网工程学院, 江苏 无锡 214122淮阴工学院计算机与软件工程学院, 江苏 淮安 223003
严云洋:江南大学物联网工程学院, 江苏 无锡 214122淮阴工学院计算机与软件工程学院, 江苏 淮安 223003
刘以安:江南大学物联网工程学院, 江苏 无锡 214122
高尚兵:淮阴工学院计算机与软件工程学院, 江苏 淮安 223003

联系人作者:严云洋(yunyang@hyit.edu.cn)

备注:国家自然科学基金、江苏省“六大人才高峰”项目、江苏省高校自然科学基金重大项目、江苏省“青蓝工程”、淮安市“533英才工程”、淮安市自然科学课题;

【1】Esfahlani S S. Mixed reality and remote sensing application of unmanned aerial vehicle in fire and smoke detection [J]. Journal of Industrial Information Integration. 2019, 15: 42-49.Esfahlani S S. Mixed reality and remote sensing application of unmanned aerial vehicle in fire and smoke detection [J]. Journal of Industrial Information Integration. 2019, 15: 42-49.

【2】Qureshi W S, Ekpanyapong M, Dailey M N, et al. QuickBlaze: early fire detection using a combined video processing approach [J]. Fire Technology. 2016, 52(5): 1293-1317.Qureshi W S, Ekpanyapong M, Dailey M N, et al. QuickBlaze: early fire detection using a combined video processing approach [J]. Fire Technology. 2016, 52(5): 1293-1317.

【3】Frizzi S, Kaabi R, Bouchouicha M, et al. Convolutional neural network for video fire and smoke detection[C]∥IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society. 23-26 Oct. 2016, Florence, Italy. New York: , 2016, 877-882.

【4】Hao G, Yang Y K, Yi Q. General target detection method based on improved SSD[C]∥2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). 24-26 May 2019, Chongqing, China. New York: , 2019, 1787-1791.

【5】Lan W B, Dang J W, Wang Y P, et al. Pedestrian detection based on YOLO network model[C]∥2018 IEEE International Conference on Mechatronics and Automation (ICMA). 5-8 Aug. 2018, Changchun, China. New York: , 2018, 1547-1551.

【6】Du C X, Yan Y Y, Liu Y A, et al. Video fire detection method based on YOLOv2 [J]. Computer Science. 2019, 46(6): 301-304.
杜晨锡, 严云洋, 刘以安, 等. 基于YOLOv2的视频火焰检测方法 [J]. 计算机科学. 2019, 46(6): 301-304.

【7】Wu S, Zhang L. Using popular object detection methods for real time forest fire detection . [C]∥2018 11th International Symposium on Computational Intelligence and Design (ISCID). IEEE. 2019.

【8】Hui T. Halidan·Abudureyimu, Du H. Multi-type flame detection combined with Faster R-CNN Journal of Image and Graphics[J]. 0, 2019(1): 73-83.
回天. 哈力旦·阿布都热依木, 杜晗. 结合Faster R-CNN的多类型火焰检测 中国图象图形学报[J]. 0, 2019(1): 73-83.

【9】Hong W, Li C F. Flame detection method based on regional fully convolutional networks with residual network [J]. Laser & Optoelectronics Progress. 2018, 55(4): 041011.
洪伟, 李朝锋. 基于区域全卷积网络结合残差网络的火焰检测方法 [J]. 激光与光电子学进展. 2018, 55(4): 041011.

【10】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017, 39(6): 1137-1149.

【11】Jiang B R, Luo R X, Mao J Y, et al. Acquisition of localization confidence for accurate object detection[M]. ∥Computer Vision - ECCV 2018. Cham: , 2018, 816-832.

【12】Zhou R G, Cheng Y, Liu D Q. Quantum image scaling based on bilinear interpolation with arbitrary scaling ratio [J]. Quantum Information Processing. 2019, 18(9): 1-19.

【13】Ji X S, Wang H. Head detection method based on optimized deformable regional fully convolutional neutral netw orks [J]. Laser & Optoelectronics Progress. 2019, 56(14): 141009.
吉训生, 王昊. 基于优化可形变区域全卷积神经网络的人头检测方法 [J]. 激光与光电子学进展. 2019, 56(14): 141009.

【14】Elizabeth M M. Self-regulatory organizations; NYSE Arca, Inc.; Order granting an extension to limited exemption from rule 612(c) of regulation NMS in connection with the exchange''''s retail liquidity program until september 30, 2019 [J]. Federal Register FIND. 2019, 84: 192.

【15】Chen Z, Ye X Y, Qian D W, et al. Small-scale pedestrian detection based on improved Faster R-CNN [J]. Computer Engineering. 2020, 46(9): 226-232, 241.
陈泽, 叶学义, 钱丁炜, 等. 基于改进的Faster R-CNN小尺度行人检测 [J]. 计算机工程. 2020, 46(9): 226-232, 241.

【16】Krittayanawach N, Vateekul P. Robust compression technique for YOLOv3 on real-time vehicle detection[C]∥2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE). 10-11 Oct. 2019, Pattaya, Thailand. New York: , 2019, 1-6.

引用该论文

Zhang Hong,Yan Yunyang,Liu Yian,Gao Shangbing. Fire Detection Method Based on Localization Confidence and Region-Based Fully Convolutional Network[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201021

张鸿,严云洋,刘以安,高尚兵. 基于定位置信度和区域全卷积网络的火焰检测方法[J]. 激光与光电子学进展, 2020, 57(20): 201021

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF