基于目标增强和视觉跟踪的红外运动点目标半自动标注算法  

Infrared Moving-point Target Semi-Automatic Labeling Algorithm Based on Target Enhancement and Visual Tracking

作　　者：何敏[1] 回丙伟 易梦妮 胡卫东[1] HE Min;HUI Bingwei;YI Mengni;HU Weidong(ATR Key Laboratory,School of Electronic Science and Engineering,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学电子科学学院ATR重点实验室,湖南长沙410073

出　　处：《红外技术》2022年第10期1073-1081,共9页Infrared Technology

基　　金：ATR重点实验室基金“面向目标检测跟踪识别应用的多源数据集构建”项目。

摘　　要：本文针对红外视频数据标注效率低、标注质量差等问题,提出了一种基于目标增强和视觉跟踪的红外序列图像中运动点目标半自动标注方法。首先对一段连续时间内的红外序列图像进行配准和背景对消以增强目标特征;然后使用视觉跟踪算法对增强后的特征进行高效自动定位;最后通过相位谱重构得到单帧图像的目标显著图,进而确定目标的准确坐标;在自动标注过程中,利用相邻帧标注结果的差异性选择关键帧,可以让标注人员快速定位可能发生错误的图像帧并对其进行手动标注。实验结果表明该算法可以显著降低标注人员的参与度,有效解决数据标注作业中周期长、质量难以保证的问题。Infrared video data annotation has the problems of low efficiency and poor quality.In this paper,a semi-automatic labeling method for moving point targets in infrared sequence images is proposed based on target enhancement and visual tracking to solve it.First,infrared sequence images in a continuous period of time were registered and fused to enhance the target features.Second,a visual tracking algorithm was utilized to locate the fused features efficiently and automatically.Lastly,a saliency map was obtained through phase spectrum reconstruction,and the exact coordinates of a target were obtained.During automatic annotation,the difference between the annotation results of adjacent frames was used to select key frames,which enabled the annotators to locate the image frames that had errors and manually annotated them quickly.The results of the experiments showed that the algorithm significantly reduced the participation of annotators and effectively solved the problems of long period and poor quality assurance in data annotation.

关 键 词：半自动标注 红外点目标 视觉跟踪 序列图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]