CAJ | 학술논문

在线多示例目标跟踪算法无法判别目标丢失以及无法适应目标尺度的变化。提出了一种基于视觉字典的在线多示例目标跟踪算法。算法将视觉字典和多示例跟踪分别作为检测器和跟踪器，利用互反馈技术提高跟踪性能。跟踪器完成目标的跟踪并为视觉字典的构建和更新提供训练样本；检测器则对跟踪器的结果（候选样本）进行判定，目标丢失时，暂停跟踪并重新检测目标，目标未丢失时，利用 Ransac 算法获得目标的尺度变换系数并在新尺度下更新跟踪器。为了提高目标丢失判别的准确性，提出了一种局部随机抽样的直方图相似性度量技术，采用局部划分思想和 Noisy-NR 模型计算候选样本与训练样本特征直方图的相似性，减少了传统直方图匹配由于受目标局部遮挡影响造成的误判。实验结果表明，该算法能够适应目标的尺度变化，检测目标的丢失，提高了跟踪稳定性。
재선다시례목표근종산법무법판별목표주실이급무법괄응목표척도적변화。제출료일충기우시각자전적재선다시례목표근종산법。산법장시각자전화다시례근종분별작위검측기화근종기，이용호반궤기술제고근종성능。근종기완성목표적근종병위시각자전적구건화경신제공훈련양본；검측기칙대근종기적결과（후선양본）진행판정，목표주실시，잠정근종병중신검측목표，목표미주실시，이용 Ransac 산법획득목표적척도변환계수병재신척도하경신근종기。위료제고목표주실판별적준학성，제출료일충국부수궤추양적직방도상사성도량기술，채용국부화분사상화 Noisy-NR 모형계산후선양본여훈련양본특정직방도적상사성，감소료전통직방도필배유우수목표국부차당영향조성적오판。실험결과표명，해산법능구괄응목표적척도변화，검측목표적주실，제고료근종은정성。
A novel object tracking algorithm fused with the visual dictionary and online multiple instance learning tracking (MILTrack)is proposed to solve the problem of tracking failure detection and scale changes in MILTrack algorithm.It regards the visual dictionary and MILTrack as detector and tracker respectively.Mutu-al feedback technology is employed for improving the tracking performance.The dictionary is constructed and updated by the training sample obtained from the tracker,while the detector make decision whether the object is lost or tracked.If we lost the object,a detection is implemented in a larger area.Otherwise,Ransac algorithm is utilized to obtain the scaling factors of the target,under which the tracker is updated.In order to improve the accuracy of the loss decision of the target,we propose a local random sampling of histogram similarity measure technique.The idea of local division and Noisy-NR model is employed for the measurement of similarity between the histograms of candidate sample and training target samples.The results shows that our algorithm makes the MILTrack algorithm adaptively adjust the scale of the target,and the detection of tracking failure is possible. The stability of tracking is improved.