Recreating trajectory from video

[sumeetgm89]

Hi,

I have been trying to find a way to plot the trajectory of the camera/user based on the IMU data recovered from a video shot from a Z1. There was a repository i came across,

GitHub - monschine/extract_camm: This repository is dedicated to parsing and...

But it did not work for me. I tried using exiftool to extract the data from the video, initially that did not work either. i posted a question regarding this on the exiftool forum and the author generously addressed the issue and published a new version of exiftool that extracted this data from the video. now that i have the imu data i have been trying various methods to plot the trajectory, experimented with the madgwick and kalman filters as well, but still not have been able to plot a trajectory that resembles the actual path i travelled during the video. Has anybody else succeeded at it? Any pointers?
Thank you.

The ricoh theta desktop app does a fantastic job at this, i am trying to do the same.
@craig i saw in one post here that you were experimenting with this, did you succeed?

Regards,
Sumeet Maru

[craig]

I can get the Z1 accelerometer and gyroscope data, but cannot plot a path.

IMU Data Libraries

This is fantastic. Thank you for your generosity. I showed this to the intern and she was excited. She would have either been stuck or would have taken a long time. I ran parse_camm on her existing data and then used the fusion library as a test. [image] I think she’s in a great position to start making assumptions about the sensor behavior and running tests to verify her assumptions. Your work makes it so much easier! plot below is from the Z1 data. nice. [image]

The author of extract_camm did use it with Gait-Tracking

GitHub - xioTechnologies/Gait-Tracking

However, the path does not look like the path I walked.

python imufusion_tracking.py -i '/path/2/R0013405_1.csv'

I believe the RICOH desktop app is using Visual SLAM, not the IMU data.