dial-rpi / freehandusrecon Goto Github PK

I wonder where to find the dataset containing 640 RRUS video.

Hi! Thank you for sharing your great work!
I hava serveral questions:

1. Could you please provide a sample of 'data/US_mask.png', 'data/avg_img.png' and so on? I think it is a mask that segments the fan or rectangle area in the ultrasound images, but I am not sure.
2. data/Demo/Demo_USCalib.txt：Is this the calibration transformation between the ultrasound image coordinate and the probe/tracking marker coordinate? But I couldn't find it used in the paper, am I right?
3. In the paper, the ground truth is the tracking position, not the relative position under the US image coordinate. Why not using the latter as the network output? (Is it because the calibration process brings error to the data?)

Looking forward to your reply! Thank you!

Good morning,
First of all, thank you for your work!
I have a question about how you write My' in the demo_pos.txt file.
Mi' is a matrix of 4x4 as is the result of Mi'=M(i+1)*Mi^-1. . In the article you say that you decompose Mi' into 6 degrees of freedom but in the txt you write 9 values.
What representation do you use for the 9 values?
Thank you in advance.
Cordially
Vanessa.

Hello there @Tonight1121 @yanrpi,

Thank you guys for sharing the code! I was having an issue with the command you provided to run the demo case, I can't seem to find you are calling the actual image or data from. Also, how do I run the pre-trained models that you have provided on the GoogleDrive?

Thank you,
Sohaib

I hope to get your answer
I want to ask if some files are missing
The following are the problems I encountered while running

FileNotFoundError: [WinError 3] 系统找不到指定的路径。: '/zion/guoh9\US_recon/US_vid_frames\train'
Transform initialization mode: random_SRE2
Training mode: scratch