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

Add SeerSense Support #1294

Merged
merged 8 commits into from
Jun 9, 2024
Merged

Add SeerSense Support #1294

merged 8 commits into from
Jun 9, 2024

Conversation

borongyuan
Copy link
Contributor

@borongyuan borongyuan commented May 30, 2024

Hi @matlabbe,

XVisio invited me to try out their SeerSense depth camera last year. Their product is similar to OAK in many aspects. For example, its processor uses Myriad X, stereo cameras has 150° DFOV, and it supports OpenVINO. Besides, it has some highlights, such as having 2 deep engines (SGBM/ToF) and providing edge VIO (which OAK has not implemented yet). I have now basically integrated it into RTAB-Map (including RGBD and Odom), and the performance looks good.

Here is the documentation for their C++ API. I think their architecture design is simpler, but not as deeply configurable as DepthAI. This may limit some of its uses.

I sent you an invitation email so that they can send you a module for test and review.

@borongyuan borongyuan marked this pull request as ready for review June 3, 2024 04:27
@borongyuan
Copy link
Contributor Author

SeerSense.1.mp4

@matlabbe matlabbe merged commit a327c95 into introlab:master Jun 9, 2024
0 of 8 checks passed
@matlabbe
Copy link
Member

matlabbe commented Jun 9, 2024

That looks great! I do have a xvisio camera here (that they sent me in 2019), but I think it is more a prototype and I had some issues with the xslam sdk (old name of their sdk). I don't think I can use it with the new SDK.
20240609_111757

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

Successfully merging this pull request may close these issues.

2 participants