sdm
sdm copied to clipboard
chengzhengxin
Supervised Descent Method Apply to Face Alignment, and Head Pose Estimation with Linear Regression. It is cross-platfrom, easily compile in windows, ubuntu, even in Android & iOS.
针对视频做关键点跟踪时，人在静止不动的情况下，68个关键点仍在抖动。请问大约是什么原因导致的？有校正方案或者思路推荐吗？ 另外在align_mean函数中， cv::Mat align_mean(cv::Mat mean, cv::Rect facebox, float scaling_x=1.0f, float scaling_y=1.0f, float translation_x=0.0f, float translation_y=0.0f) { using cv::Mat; // Initial estimate x_0: Center the mean face at the [-0.5, 0.5]...
Anyone that has been successful converting to iOS and/or Android, would you mind providing instructions on conversion? I have tried to follow for iOS and have had no luck. Thanks!
hello, thanks much for your project ! There is one problem when train model, in this project where could call function void ldmarkmodel::convert(std::vector &full_eyes_Indexs)?
hi robo 想问下文件labels_ibug_300W_train.xml在哪里，是你自己生成的还是在哪里下载的？ Thanks Hanson
“//左右眼睛的四个眼角，鼻尖点，左右两个嘴角，一共七个点，估计头部姿态，2*7+1维度的数据，最小二乘拟合出9个维度的数据，即一个3*3的旋转矩阵 //矩阵大小为15*9 float estimateHeadPoseMat[] = “ 请问一下 9个维度是指？
你好，请问estimateHeadPose2dArray这个矩阵是怎么得到的呢？为什么是15*9？这个9列是指的什么呢？谢谢！
想请问下mean_norm_shape对模型训练的影响，使用自己的数据训练，效果不好，是不是需要根据自己的数据重新计算mean_norm_shape？谢谢
我用cmake-gui生成之后，用vs2017打开，但在后续生成的时候遇到很多 error LNK2019或error LNK2001这样的错误，怎么解决？
Metadata
Owner
Metadata
Supervised Descent Method Apply to Face Alignment, and Head Pose Estimation with Linear Regression. It is cross-platfrom, easily compile in windows, ubuntu, even in Android & iOS.