OpenREALM icon indicating copy to clipboard operation
OpenREALM copied to clipboard

OpenREALM is a pipeline for real-time aerial mapping utilizing visual SLAM and 3D reconstruction frameworks.

Results 20 OpenREALM issues
Sort by recently updated
recently updated
newest added

Currently, during georeferencing we transform our GNSS measurements from WGS84 into UTM coordinates . It would be nice if we could choose our cartesian coordinate system. So instead of transforming...

enhancement

During #21 it became clear, that the exiv2 grabber expects the image naming convention: image_0000.jpg. Otherwise really weird behaviour could be observed, e.g. adding the same frame to "valid_input" during...

bug

## Description Fixes to numerous small bugs and odd behaviors discovered when trying to use the tiling stage for the first time in a while. There are also some improvements...

If our tracking gets completely messed up and decides are frames are facing the horizon, the current system will still add them to the map. This drastically expands the map...

Hi @laxnpander I have been running on a particular custom dataset. I am observing a weird phenomenon. The vision tracking is very bad compared to the GPS trajectory. It also...

Hi @laxnpander . The Readme has the following statement: "_The pipeline is designed for multirotor systems with downlooking 2-axis gimbal stabilized camera and alignment of the magnetic heading of the...

Thanks a lot for your work. I have successfully run gnss,noreo and reco using both the provided test data set and my own (**1014x760 resolution, 126m flight altitude**). However, when...

Hello, thank you very much for your outstanding contribution. I would like to ask, after adding latitude, longitude, and altitude information exiv2 tags to the images in my own dataset,...

Thanks for maintaining the OpenRealm project. When I ran gnss.launch, it was normal, but when I ran nocore.launch and core.launch, the following error occurred: [realm_pose_estimation-3] process has died [pid 16691,...

I believe the timestamp conversion between openrealm frame and SLAM timestamp was incorrect. The openrealm timestamp is in nanoseconds and the SLAMs expect the time in seconds. So it should...