Kalman Filter

本质是一种最优估计法.  核心是"预测"+"测量反馈".

一个视频:

http://blog.sina.com.cn/s/blog_461db08c0102uwws.html

加深理解,:

http://blog.csdn.net/heyijia0327/article/details/17487467

http://blog.csdn.net/heyijia0327/article/details/17667341

http://blog.csdn.net/junshen1314/article/details/49185815

http://www.voidcn.com/blog/autocyz/article/p-5731864.html

http://www.cnblogs.com/jcchen1987/p/4371439.html

http://blog.csdn.net/xiahouzuoxin/article/details/39582483

http://blog.csdn.net/lanbing510/article/details/40936343

https://segmentfault.com/a/1190000000514987

这篇文章里面有C实现:

http://blog.csdn.net/xiahouzuoxin/article/details/39582483

这篇文章的讲解也很深刻, 有几个图非常有意思:

http://blog.jasonding.top/2014/10/23/Machine%20Learning/%E3%80%90%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89%E3%80%91%E5%9F%BA%E4%BA%8EKalman%E6%BB%A4%E6%B3%A2%E5%99%A8%E7%9A%84%E8%BF%9B%E8%A1%8C%E7%89%A9%E4%BD%93%E7%9A%84%E8%B7%9F%E8%B8%AA/

用控制论的角度去看,

http://www.geek-workshop.com/thread-15257-1-1.html

这一篇是讲"状态空间模型"的. 其理念是KF的基础, 推而广之也是很有意义的.

http://bbs.loveuav.com/thread-276-1-1.html