Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

search loop #7

Open
fanhuigui opened this issue Mar 22, 2023 · 2 comments
Open

search loop #7

fanhuigui opened this issue Mar 22, 2023 · 2 comments

Comments

@fanhuigui
Copy link

Hello, thank you very much for your open source code. I studied it yesterday and found that it accumulates point searches every 500 frames, and every time it matches a point cloud, it matches ten frames. Isn't it supposed to match with the current frame point cloud? Why is the last ten frame point clouds used here? I don't understand. Thank you

@ChongjianYUAN
Copy link
Member

Hello, thank you very much for your open source code. I studied it yesterday and found that it accumulates point searches every 500 frames, and every time it matches a point cloud, it matches ten frames. Isn't it supposed to match with the current frame point cloud? Why is the last ten frame point clouds used here? I don't understand. Thank you

In the current version, we accumulate 10 frames of point clouds as a key frame, which serves as the basis for all loop detection. By accumulating point clouds, we can obtain denser data, resulting in better detection performance. However, we are developing an improved version that supports the detection of both current normal frames and accumulated key frames, whereas the current version only supports key frames.

@fanhuigui
Copy link
Author

Hello, thank you very much for your open source code. I studied it yesterday and found that it accumulates point searches every 500 frames, and every time it matches a point cloud, it matches ten frames. Isn't it supposed to match with the current frame point cloud? Why is the last ten frame point clouds used here? I don't understand. Thank you

In the current version, we accumulate 10 frames of point clouds as a key frame, which serves as the basis for all loop detection. By accumulating point clouds, we can obtain denser data, resulting in better detection performance. However, we are developing an improved version that supports the detection of both current normal frames and accumulated key frames, whereas the current version only supports key frames.

I learned that loop detection only started at frame 50. They all converted to the world coordinate system based on their posture, and then started matching. I have understood your meaning, and thank you very much. I am honored to learn your method.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants