镜头边界检测是许多多媒体应用的一个重要步骤，而现有的镜头边界检测方法大都是首先提取视频帧低层视觉特征，然后构造相异性测度函数，但由于这些方法对低层特征变化、对象运动、摄像机运动和视频质量较敏感，为克服此问题，提出了一种基于图像分割和对象跟踪的镜头边界检测方法。该方法首先采用分区直方图对镜头进行预检，然后利用基于小波分析的无监督图像分割和对象跟踪技术，通过构造相异性测度函数来对镜头边界进行确认。由于分区直方图方法作为第１过滤器，可有效地减少图像分割和对象跟踪的视频帧数目，从而提高了整个算法的效率，而基于小波变换的无监督图像分割和对象跟踪，则对以上问题具有较好的鲁棒性。在3个多小时的CCTV和CNN新闻视频实验中，获得了972%查准率和964%的查全率。

As a critical step in many multimedia applications, shot boundary detection attracts many research interests in recent yearsMost present methods measure the similarity among video frames based on its low-level feathers However, they are sensitive to the change in brightness, color, motion of object,camera motions and the quality of video This paper proposes an innovative shot boundary detection method for news video based on image segmentation and object tracking It combines three main techniques, namely, the partitioned histogram comparison method, the image segmentation based on wavelet analysis and the object tracking The partitioned histogram comparison is used as the first filter to effectively reduce the number of video frames which need segmentation and object tracking The unsupervised image segmentation based on wavelet analysis and object tracking is robust to those problems mentioned above The efficacy of the proposed method is extensively tested with more than 3 hours of CCTV and CNN news programs, and that 964% recall with 972% precision has been achieved