【作者】 钱惠敏； 茅耀斌； 王执铨；

【Author】 QIAN Hui-min MAO Yao-bin WANG Zhi-quan (School of Automation,Nanjing University of Sci.& Tech.,Nanjing,210094)

【机构】 南京理工大学自动化学院；

【摘要】 实用的跟踪系统要求能实时地适应运动目标的外观变化,尺度固定不变的跟踪窗口不能有效地跟踪存在明显尺度变化的目标。本文将多尺度图像的信息量度量方法引入到运动目标跟踪中,提出了一种跟踪窗口自动更新算法,并用此算法改进了基于颜色直方图的 Mean-Shift 跟踪方案。实验结果表明,改进的 Mean-Shift 跟踪算法对尺寸逐渐减小和逐渐增大的目标都能自动选择合适的跟踪窗口大小。更多还原

【Abstract】 A practical tracking system is required to update the appearance changes of moving objects in real-time.The system with fixed size tracking window could not catch an object effectively when distinct scale of the object changes, therefore it is important to select the scale of tracking window automatically.The information measure of multi-scale image in scale space has been used to differentiate the scale and was introduced into moving object tracking in this paper. Automatic updating method of tracking window was proposed,and was integrated into the classical Mean-Shift tracking algorithm based on color histogram.Experimental results demonstrated that the improved algorithm could select the proper size of the tracking window in the scenarios that not only the object scale increases but the scale decreases as well.更多还原