-
Notifications
You must be signed in to change notification settings - Fork 1
Run With Own Event Data
Chahat Deep Singh edited this page Jul 11, 2021
·
4 revisions
Collect the event data as a ROSBag using the provided event camera driver. We recommend using a newer generation event camera because of better noise performance. We used the Samsung Gen3 DVS but either the CelePixel or the Davis346 or the Prophesee camera.
- Once the ROSBag is obtained, we need to save these events into a CSV file which can be read by our Matlab script to generate event frames. The ROSBag to CSV conversion script assumes that the events are in this format. Run the
Scripts/BagToEvents.py
script as follows:
python BagToEvents.py --BagFileName='<Path_to_ROSBag_File>.bag' --TopicName='<ROSTopic_Name>' --WriteFileName='<Path_where_to_SAVE>.csv'
An example is given below:
python BagToEvents.py --BagFileName='Propellers.bag' --TopicName='/samsung/left/camera/events' --WriteFileName='./EVPropNet.csv'
- Finally, run the
Scripts/CSVToEventFrames.m
MATLAB script by changing theFileName
variable to the CSV file andBasePath
to the folder in which CSV is present in order to obtain the event frames inWriteBasePath
.
Now follow the instructions of Running Test Code On Sample data to run the test code on your own data.