文献类型：期刊文献

中文题名：基于自适应样本均衡与信息融合的林火检测数据增强方法

英文题名：Adaptive Sample Equalization and Information Fusion Augmentation Method for Forest Fire Data

作者：吴福明[1] 宋智豪[1] 王超[1] 符利勇[2,3] 业巧林[1]

第一作者：吴福明

机构：[1]南京林业大学信息科学技术学院,南京210037;[2]中国林业科学研究院资源信息研究所,北京100091;[3]国家林业和草原局森林经营与生长模拟重点实验室,北京100091

年份：2023

卷号：59

期号：6

起止页码：88-101

中文期刊名：林业科学

外文期刊名：Scientia Silvae Sinicae

收录：CSTPCD;;EI(收录号：20233814754137);Scopus;北大核心:【北大核心2020】；CSCD:【CSCD2023_2024】；

基金：张家口市崇礼区森林防火综合体系建设无人机巡护监测系统(DA2020001)。

语种：中文

中文关键词：森林防火;烟火检测;样本均衡;自适应;数据增强;信息融合

外文关键词：forest fire prevention;smoke and fire detection;the sample balance;adaptiveness;data augmentation;information fusion

分类号：S762

摘要：【目的】提出一种基于自适应样本均衡与信息融合的林火检测数据增强(SMA)方法,以解决因林火样本数据难以获取、各类别分布不均衡、场景表达能力不充分等导致林火检测效果不佳的问题。【方法】以河北省张家口市崇礼区采集的无人机林火图像为研究对象:1)对无人机视频进行预处理,构建原始数据集;2)采用类别统计、标注框中心化等方法分析数据存在的问题,如小目标居多、类别分布不均衡和标注框尺寸分散等;3)针对类别分布失衡问题,引入自适应参数,实现样本动态调整;4)为保证信息跨样本融合的有效性,提出新的参数指标IOA作为判定阈值,并给出合理参考值;5)设计12组消融试验,以无人机采集数据为样本,根据控制变量原则,对比原始数据、随机数据增强、马赛克数据增强和SMA方法在SSD、YOLOv3、YOLOv4主流算法中的林火检测结果;6)以MAP(平均查准率)为指标,评估不同数据增强方法在同一算法中的效果。【结果】消融试验结果显示,SMA方法在SSD、YOLOv3、YOLOv4算法中MAP分别为48.16%、82.02%、67.79%,相比原始数据分别提升12.14%、11.50%、36.83%,相比随机数据增强分别提升11.95%、4.86%、16.33%,相比马赛克数据增强分别提升1.06%、18.24%、1.79%。【结论】现有数据增强方法未能充分利用林火数据中蕴涵的信息,SMA方法引入自适应参数可解决样本分布不均衡问题,IOA指标引入能够实现数据跨样本融合。SMA方法在SSD、YOLOv3和YOLOv4算法中MAP相较传统方法均有提升,表现出对林火数据检测的有效性。
【Objective】Among the current forest fire detection methods,the research based on deep learning is the most active.However,when dealing with real scenes,the model detection effect is often poor due to insufficient samples of forest fire,imbalanced distribution of categories and weak expression ability of scenes,et al.To alleviate this problems,we presented a newly developed data augmentation method called self-adaptive mix augmentation(SMA).【Method】This study takes UAV(unmanned aerial vehicle)forest fire images collected from Chongli district,Zhangjiakou city,Hebei Province as the research object.The work is as follows:1)Preprocess the UAV video to construct the original data set.2)Use methods such as category statistics and annotation box centralization to analyze and find out the problems existing in the data,such as:nimiety of small targets,unbalanced target distribution and scattered annotation box size.3)For the problem of imbalanced categories,we introduced self-adaptive parameters to achieve the dynamic adjustment of samples.4)In order to ensure the effectiveness of cross-sample information fusion,IOA(intersection over aim)was proposed as a judgment threshold to give a reasonable reference value.5)According to the principle of control variables,we designed 12 ablation experiments with UAV data as samples,and compared the results of forest fire detection of original sample,ordinary data augmentation,Mosaic and SMA methods in SSD,YOLOv3 and YOLOv4 mainstream algorithms,respectively.6)MAP(mean average precision)was selected as the index to evaluate the results of different data augmentation methods in the same algorithm.【Result】The results of ablation test showed that in SSD,YOLOv3 and YOLOv4 algorithms,the MAP performance of SMA method was 48.16%,82.02%and 67.79%,compared with the original data,it increased by 12.14%,11.50%,36.83%,compared with traditional random augmentation,it increased by 11.95%,4.86%and 16.33%,compared with the Mosaic method,it increased by 1.06%,18.24%,and 1.79%.【Conclusion】Traditional data augmentation methods did not fully explore the information contained in samples in forest fire data set.The SMA method in this study introduces self-adaptive parameters to alleviate the problem of sample imbalance,and the introduction of IOA achieves cross-sample fusion.The experimental results showed that the SMA method improves the MAP performance of SSD,YOLOv3 and YOLOv4 algorithms compared with the traditional method,which proves the effectiveness of SMA method on forest fire data set.