<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[mengxt169的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/mengxt169</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; mengxt169]]></copyright><item><title><![CDATA[FAST-LIVO2编译和运行]]></title><link>https://blog.youkuaiyun.com/mengxt169/article/details/145338226</link><guid>https://blog.youkuaiyun.com/mengxt169/article/details/145338226</guid><author>mengxt169</author><pubDate>Fri, 24 Jan 2025 11:19:00 +0800</pubDate><description><![CDATA[等了很久，终于开源了。]]></description><category></category></item><item><title><![CDATA[LinK3D学习]]></title><link>https://blog.youkuaiyun.com/mengxt169/article/details/141089857</link><guid>https://blog.youkuaiyun.com/mengxt169/article/details/141089857</guid><author>mengxt169</author><pubDate>Sat, 10 Aug 2024 14:01:27 +0800</pubDate><description><![CDATA[算法全称是：Linear Keypoints representation for 3D LiDAR point cloud，可以译作“三维激光点云的线性关键点表示”三维点云的不规则性、稀疏性和无序性使得2D的方法无法直接应用于3D模式。主要原因有：3D点云有很多不连续且相似的局部表面，容易导致误匹配3D点云通常更稀疏，且在空间中不均匀的分布，导致固定尺寸中空间中没有足够的点，无法形成有效的统计分布有动态物体和遮挡，导致当前帧和后续激光在相同局部表面无法形成一致的描述。]]></description><category></category></item><item><title><![CDATA[口罩人脸识别]]></title><link>https://blog.youkuaiyun.com/mengxt169/article/details/106744801</link><guid>https://blog.youkuaiyun.com/mengxt169/article/details/106744801</guid><author>mengxt169</author><pubDate>Sun, 14 Jun 2020 13:01:36 +0800</pubDate><description><![CDATA[https://www.notion.so/87bf2f0f4a2e4abdb46647c2c222a944

放个笔记链接吧，我太懒了。。。
]]></description><category></category></item></channel></rss>