Closed VikashPR closed 1 year ago
Hi @VikashPR,
I am not familiar with the MMPD dataset. However, based on my understanding, you need to convert the frame color space from RGB to HSV inside the MMPDLoader's _readmat() function. You can refer to the UBFCrPPGLoader's _readvideo() function.
Hi @VikashPR,
I am not familiar with the MMPD dataset. However, based on my understanding, you need to convert the frame color space from RGB to HSV inside the MMPDLoader's _readmat() function. You can refer to the UBFCrPPGLoader's _readvideo() function.
This is the way to go, definitely give it a try and let us know how it goes. You should be able to use OpenCV to do the actual conversion. An example of doing so can be found here.
Looks like you've succeeded in using HSV instead of RGB in your version of this repo here, so I'm guessing this question of yours has been resolved @VikashPR. As a result, I'll go ahead and close this issue.
Hi @VikashPR,
I am not familiar with the MMPD dataset. However, based on my understanding, you need to convert the frame color space from RGB to HSV inside the MMPDLoader's _readmat() function. You can refer to the UBFCrPPGLoader's _readvideo() function.
@KenTee Thank you. I was able to figure out how to change RGB to HSV in all datasets except MMPD. And changing so I was expecting to get better results, but I figured out that results with RGB are much better than HSV.
Hi, Can someone please help me this. I wanted to use HSV in TS-CAN algorithm with MMPD datasets, Instead of using RGB. I am using
PURE_MMPD_TSCAN_BASIC.yaml