search

tnikolla / robot-grasp-detection

Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.
Apache License 2.0
232 stars 84 forks source link

what is the rectangle metric detection accuracy #25

Open ceng1027 opened 5 years ago

ceng1027 commented 5 years ago

Hi,

I have a question in the paper(Real-Time Grasp Detection Using Convolutional Neural Networks). In the table I , what's the rectangle metric detection accuracy? and how to compute the value? I search many paper, they don't have explanation.

thanks.

edwardnguyen1705 commented 4 years ago

@ceng1027 Please read Sec. V. Experiments and evaluation/A. Grasp detection. You can use the rectangle metric: ". .. consider a predicted grasp to be correct if both: 1) within 30 degrees 2) IoU >= .25 ..."

ceng1027 commented 4 years ago

Thank you for your reply. The content is very detailed, and my problem has been solved.

Thank you very much!

Best regards,

Yun-Feng