How can I only use Mask R-CNN segmentation to detect dynamic objects?

[liubamboo]

I want to verify the output below

it only use Mask R-CNN segmentation to detect dynamic objects, but the parameter of main function can't support it. it only support only multi-view geometry method(G), both geometrical and deep learning approaches(N+G). But It can't support only deep learning method(G). Can you help me? thank you very much.

[hongu0603]

I want to verify the output below

it only use Mask R-CNN segmentation to detect dynamic objects, but the parameter of main function can't support it. it only support only multi-view geometry method(G), both geometrical and deep learning approaches(N+G). But It can't support only deep learning method(G). Can you help me? thank you very much.

i have the same question with you,did you solve it ?

[wenyan96]

you can modify the code in Tracking::GrabImageRGBD() with reference of ORBSLAM2. but remember maintain the imMask variable! And did you test the onlyGeometry code? when i tried this, i got a segment default error.