CAJ | 학술논문

针对CamShift跟踪算法仅采用颜色作特征,易发生跟踪错误等问题,提出了一种基于特征融合的算法.采用改进的背景差分法自动检测目标,目标模型联合了颜色和梯度方向特征,并对特征的可信度进行加权处理,有效解决了CamShift算法在有颜色相近的干扰目标存在情况下跟踪可能失效的问题.实验表明,该算法提高了跟踪的准确性和稳健性.
침대CamShift근종산법부채용안색작특정,역발생근종착오등문제,제출료일충기우특정융합적산법.채용개진적배경차분법자동검측목표,목표모형연합료안색화제도방향특정,병대특정적가신도진행가권처리,유효해결료CamShift산법재유안색상근적간우목표존재정황하근종가능실효적문제.실험표명,해산법제고료근종적준학성화은건성.
Since the Continuously Adaptive MeanShift (CamShift) tracking algorithm only adopts color as feature, which would result in tracking error, an improved algorithm based on feature fusion was proposed. The presented algorithm detected the moving target automatically using an improved background subtraction method. Object model combined color and gradients orientation features, and weighted the reliability of features. It also overcame the possible CamShift invalidity in the situation of some similar color objects. The experimental results show that the algorithm enhances the reliability and robustness of tracking.