【作者】 胡硕；

【导师】 朱明；

【作者基本信息】 中国科学院研究生院（长春光学精密机械与物理研究所） ， 光学工程， 2006， 博士

【摘要】 本文通过对图像处理领域中自动目标识别技术以及快速目标跟踪算法的研究,找出一种切实可行的办法来解决目前靶场设备跟踪系统存在的一些问题。在目标检测的算法研究方面,本文从检测效果、运行时间和算法实现难度等方面考虑,选用curvelet变换进行图像增强和噪声滤除,同时结合小波变换进行边缘检测,以达到准确检测目标的目的。实验结果表明,在图像增强和去噪效果方面,curvelet变换的效果要大大优于其他同类方法,特别是在噪声严重的情况下curvelet变换优越性更为显著。本文研究了基于小波变换的形状匹配算法,并针对小波表达的起始点问题,引入了Zernike矩,提出一种起始点无关的小波系数形状匹配算法。算法首先对输入图像进行预处理后提取目标轮廓,生成具有平移、尺度不变的形状链状表达,并通过小波变换进行多尺度分析。然后计算各个尺度下的各阶Zernike矩,来解决小波变换的起始点问题,实现形状表达的旋转不变性。实验结果表明该算法适用于轮廓较明显的目标,同时具有速度快、精度高、鲁棒性强的优点。提出一种基于遗传算法的快速相关跟踪算法。针对图像数据的特点,采用新的编码方式,定义了新的交叉和变异算子。采用抽样法的初始化种群方式,并引入竞争进化策略,减少了迭代次数,有效降低了计算量。实验结果证明,在保证匹配精度的同时,该算法比原始算法在计算时间降低100多倍。针对传统相关跟踪算法中存在的一些问题,在分析多种模板更新算法的基础上,提出一种基于直方图信息的模板更新策略。同时,利用kalman滤波器完成目标大面积遮挡条件下对目标轨迹的预测,在一定程度上解决了相关跟踪中的遮更多还原

【Abstract】 In this dissertation, the methods of automatic target recognition and fast object tracking are studied for the problems in target tracking system currently.Aiming at detecting objects precisely, a method of image enhancement and noise removing based on the curvelet transform with edge detection based on wavelet transform is proposed. The simulation results of image enhancement and noise removing show the curvelet transform yields the better visual quality than others especially at low SNR.The algorithms of shape matching based on wavelet coefficients are introduced. For overcoming the problem that the wavelet representation depends on the starting point of the sampled contour, the Zernike moments are introduced , and a novel Starting-Point-Independent wavelet coefficients shape matching algorithm is presented. The proposed matching algorithm firstly gains the object contours, and give the translation and scale invariant object shape representation. The object shape representation is converted to the dyadic wavelet representation by the wavelet transform. And then calculate the Zernike moments of wavelet representation in different scales. With respect to property of rotation invariant of Zernike moments, consider the Zernike moments as the feature vector to calculate the dissimilarity between the object and template image, which overcoming the problem of dependency of starting point. The experimental results have proved the proposed algorithm to be efficient, precise, and robust.更多还原