Hello，I was visualizing the effect on the kitti data set, but I found that the effect was not particularly good and there was a lot of noise. Is this normal?

[PHD-jlh]

The kitti bag I used was downloaded according to your link, and the parameters have not been adjusted. They were pulled from the original code. You can refer to the picture for the effect. You can see that there are a lot of ground points that are judged to be dynamic points. Please tell me how should I solve this problem

[gongjun136]

@PHD-jlh 距离远，稀疏了导致的，基于视点可见性的方法都存在这种问题，DynamicFilter中计算入射角处理了这种问题，感觉远处的丢掉算了。

[PHD-jlh]

@gongjun136 感谢回复，不过我在可视化的时候发现不只是远处会出现这种问题，在近处尤其是车周边的地面点云很容易被误检成动态点，这个问题可以通过参数调整来解决吗？或者有必要采用一些后处理策略去过滤吗？

[gongjun136]

@PHD-jlh 你是说载体车辆的近处地面点？我测试的效果好想并没有这种问题。

[772894624]

@PHD-jlh 你好，该如何根据提供的kitty数据集进行测试呢？能把运行的launch命令告诉我？

[gongjun136]

我用的作者提供的kitti数据集和fast lio2进行测试的，作者在数据中提供了真值，并且fast lio2代码也做了修改。

…

---Original--- From: ***@***.***> Date: Thu, Mar 28, 2024 12:10 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [hku-mars/M-detector] Hello，I was visualizing the effect on the kitti data set, but I found that the effect was not particularly good and there was a lot of noise. Is this normal? (Issue #18) @PHD-jlh 你好，该如何根据提供的kitty数据集进行测试呢？能把运行的launch命令告诉我？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: ***@***.***>

[772894624]

@gongjun136 好的 谢谢！

[PHD-jlh]

@gongjun136 你好，可以看一下我的可视化效果


这两张图就是地面非常多噪点，而且这个距离大概在10m以内，这种效果正常吗？
另外还想请问下，输出eval的npy文件的时候为什么永远比真值npy少一个文件呢，我是所有包都存在这个问题

[PHD-jlh]

我用的作者提供的kitti数据集和fast lio2进行测试的，作者在数据中提供了真值，并且fast lio2代码也做了修改。
…
---Original--- From: @.> Date: Thu, Mar 28, 2024 12:10 PM To: @.>; Cc: @.@.>; Subject: Re: [hku-mars/M-detector] Hello，I was visualizing the effect on the kitti data set, but I found that the effect was not particularly good and there was a lot of noise. Is this normal? (Issue #18) @PHD-jlh 你好，该如何根据提供的kitty数据集进行测试呢？能把运行的launch命令告诉我？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>

另外请问下这里fastlio2作者有说明在哪里做出了代码调整吗？readme里面并没有看到，只说了用fastlio的release版本，方便的话加个邮箱联系？

[iDonghq]

我用的作者提供的kitti数据集和fast lio2进行测试的，作者在数据中提供了真值，并且fast lio2代码也做了修改。
…
---Original--- From: @.> Date: Thu, Mar 28, 2024 12:10 PM To: _@**._>; Cc: _@.@._>; Subject: Re: [hku-mars/M-detector] Hello，I was visualizing the effect on the kitti data set, but I found that the effect was not particularly good and there was a lot of noise. Is this normal? (Issue #18) @PHD-jlh 你好，该如何根据提供的kitty数据集进行测试呢？能把运行的launch命令告诉我？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: _@_.*>

另外请问下这里fastlio2作者有说明在哪里做出了代码调整吗？readme里面并没有看到，只说了用fastlio的release版本，方便的话加个邮箱联系？

修改的地方太多了，所以作者没有说明