中文摘要：

提出一种对机器视觉测量视场内任意位姿目标物体视差变形导致测量误差进行物体自动跟踪和变形补正的方法。在分析视差变形基础上，提出自动跟踪检测模型，得出补正参数。通过改进的序贯相似性检测算法（ssDA）模板匹配、图像的二值化处理和腐蚀、质心坐标求取和轮廓边缘搜索等计算，计算出反映目标物体位置、姿态偏移的特征参数，从而求得目标物体自动跟踪位置、姿态偏移补正量。以任意位姿M4螺母内螺纹检测为实验对象，实验结果表明，该自动跟踪补正方法可行，具有较好的跟踪一致性，取得了较好的视差变形补正效果。

英文摘要：

A method is introduced for automatic tracking and deformation correction of the measurement error, caused by the parallax deformation of the target object in any position of the visual field. Based on the analysis of parallax deformation, an automatic tracking detection model is proposed to obtain the correction parameters. Through the improvement of SSDA template matching, image binarization and corrosion, centroid coordinate acquisition and contour edge search, the characteristic parameters reflecting the position and pose deviation of the target object are calculated. Thus, the object automatic tracking position and pose deviation correction amount can be obtained. In this paper, the internal thread of arbitrary position pose M4 nut is used as the experimental object. The experimental results show that the automatic tracking correction method is feasible and has good tracking consistency, and achieves better correction effect of parallax distortion.