【作者】 仲莉恩；

【导师】 程文刚；

【作者基本信息】 华北电力大学（北京） ， 计算机应用技术， 2010， 硕士

【摘要】 视频目标跟踪是计算机视觉、模式识别、人工智能、图像处理等领域的重要研究任务之一。视频目标跟踪,就是通过对摄像机拍摄到的图像序列进行分析,在图像中检测出运动的目标或是用户感兴趣的区域,并在后续帧中估算出目标位置。本文针对静止场景中的目标跟踪,提出了一种结合颜色特征和投影直方图的方法来消除阴影,该方法对被检测为运动目标分别从颜色特征、竖直和水平投影直方图上进行判断；另外,对区域协方差跟踪方法进行了改进,并对目标的进入、离开、合并、分离、遮挡做了相应的处理；设计并开发了视频目标跟踪的实验系统,采用模块化实现。实验结果表明,利用上述方法能够有效地消除运动目标的阴影,并对目标跟踪具有较高的准确性。更多还原

【Abstract】 Video object tracking is an important task in the fields of computer vision, pattern recognition, artificial intelligence and image processing. Video object tracking analyses the image sequences shoot by camera and detects moving objects or various areas of interest in it, then estimates object locations in subsequent frames. This paper aims at object tracking in static scene, a method using the color feature and project histogram to eliminate shadow is proposed. It processes each detected area separately from the color, vertical, horizontal projection histogram. In addition, the object tracking method based on covariance is improved. Meanwhile, it handles objects entering, leaving, merging, separating and occlusion. Finally, an experimental video object tracking system is designed and developed. It uses modular implementation and achieves good performance. The experimental results show that the above methods eliminate the shadow of moving objects effectively and have higher accuracy in object tracking.更多还原