We then use the RGBA channels of the subsequent pixels to store (x, y, width, height) of the detected face(s), in the order that they have been detected. In the output frame, the 1st Pixel's R contains how many faces have been detected. Results are packed into the output frame (RGBA32Float) in the following manner: Once face(s) has been detected, the detection results are then passed out via Info Dat AND Pixel Packing.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |