基于动态模板匹配的自适应尺度目标跟踪算法  

Adaptive Scale Target Tracking Algorithm Based on Dynamic Template Matching

作　　者：陈方芳 宋代平[1] Chen Fangfang;Song Daiping(College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400030)

机构地区：[1]重庆大学机械与运载工程学院,重庆400030

出　　处：《激光与光电子学进展》2023年第4期229-236,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(U1530138)。

摘　　要：为保证大型光学模块装校装置在装校过程的稳定性和准确性,需要对导向模块进行监测跟踪。针对传统模板匹配跟踪算法在工业应用中存在无法应对目标尺度变化、缺少有效的模板更新策略等问题,提出一种基于动态模板匹配的自适应尺度目标跟踪算法。首先对第一帧图像检测运动目标区域,提取目标模板中心点,生成模板图像金字塔;在之后的每一帧中,先计算各尺度下模板图像和目标图像的相似性,取相似度最大的尺度因子作为尺度变化量,借助动态模板更新策略更新模板;最后融合卡尔曼滤波算法,预测出候选目标范围。在OTB数据集上进行实验,结果表明,所提算法在满足实时性要求的同时,相较于传统算法,重合率提高约21个百分点。To ensure the stability and accuracy of a largescale optical module in the installation process,it is necessary to monitor and track the guide module.An adaptive scale target tracking algorithm based on dynamic template matching is proposed to address the problems of traditional template matching tracking algorithms in industrial applications,such as their inability to cope with target scale change and lack of a template adaptive update mechanism.First,the moving target area is identified from the first frame image,the center point of the target template is extracted,and the template image pyramid is generated.The template is updated using a dynamic template update strategy,and then the Kalman filtering algorithm is used to predict the potential target range in each subsequent frame.The similarity between the template image and the target image at each scale is calculated,and the scale factor with the highest similarity is taken as the scale change.In comparison to conventional algorithms,experiments on the OTB dataset demonstrate that the proposed algorithm can meet realtime requirements while increasing the coincidence rate by about 21 percentage points.

关 键 词：目标跟踪 动态模板 自适应尺度 卡尔曼滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]