The pixel level corners were detected by classical Harris corner detector, and then some methods were used to get sub-pixel accuracy.
针对摄像机标定模板图像的角点检测问题，提出了两种简便而有效的亚像素级精度的提取算法。
The image need not pretreatment and the accuracy of registration can reach as high a level as sub-pixel if you registrate image by mutual information method.
互信息的使用使得待配准图像不需要进行预处理，并且配准的精度可以达到亚像素级。
Experimental results indicate that the optimum method has a faster image registration speed and a better image registration precision. The registration results reach the level of sub-pixel.
实验结果表明，此优化方法不仅提高了计算速度，而且提高了配准精度，配准结果达到了亚像素级水平。
Experiment results indicate this algorithm can extract Center of Structured Light Stripe accurately, it is of strong anti-noise capability and its accuracy is at sub-pixel level.
实验结果表明，该算法能够准确地提取出光条中心，具有很强的抗噪声能力，精度为亚像素级。
Experiment results indicate this algorithm can extract Center of Structured Light Stripe accurately, it is of strong anti-noise capability and its accuracy is at sub-pixel level.
实验结果表明，该算法能够准确地提取出光条中心，具有很强的抗噪声能力，精度为亚像素级。
应用推荐