Face recognition with Jetson Inference

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

My goal is to run python face recognition with Jetson inference.

68747470733a2f2f636c6f75642e67697468756275736572636f6e74656e742e636f6d2f6173736574732f3839363639322f32343433303339382f33366630653366302d313363622d313165372d383235382d3464306339636531653431392e676966

Here this code: face_recognition/facerec_from_webcam_faster.py at master · ageitgey/face_recognition · GitHub

I want to join it with a Jetson Inference object detector code: jetson-inference/detectnet.py at master · dusty-nv/jetson-inference · GitHub

My problem is that the Jetson Inference code uses input = videoSource(“/dev/video0”) to read the camera, and the face recognition code uses video_capture = cv2.VideoCapture(0)

That is, one uses cuda and the other numpy, if I’m not mistaken (I’m not an expert).

How do I link the face recognition code with Jetson inference so that it can read the image of the jetson inference sample code?

3

Hi,

You can wrap the input from jetson-inference to be a cvmat and feed it to the face recognition source.

Some examples can be found below:

Thanks.

1 Like
7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.