May I ask how I can use the Coral dev board and a USB camera(LogiC270)to utilize MoveNet for obtaining real-time single human pose estimation data?

Question

I'm using a Windows 10 computer to connect the Coral Dev Board via WSL（Ubuntu 22.04.2）. I've already achieved the basic example of obtaining keypoint information from images,code:python3 examples/movenet_pose_estimation_2.py \ --model test_data/movenet_single_pose_lightning_ptq_edgetpu.tflite \ --input test_data/shendun1.jpg. However, I can't perform real-time keypoint estimation using a USB camera. Additionally, the camera running code:`edgetpu_classify_server \

--source /dev/video1:YUY2:640x480:30/1
--model ${DEMO_FILES}/mobilenet_v2_1.0_224_quant_edgetpu.tflite
--labels ${DEMO_FILES}/imagenet_labels.txt ` allows me to view the video in a browser, but I want to use a USB camera for real-time keypoint estimation and save the keypoint information in a file. At the same time, I want to view the video information in a windowed application (rather than a browser). Can anyone help me with this?I am truly grateful for any help provided.

I placed the code:

import argparse
import csv
import cv2
from PIL import Image
from PIL import ImageDraw
from pycoral.adapters import common
from pycoral.utils.edgetpu import make_interpreter
import numpy as np

_NUM_KEYPOINTS = 17

def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument(
        '-m', '--model', required=True, help='File path of .tflite file.')
    parser.add_argument(
        '--csv',
        default='keypoints.csv',
        help='File path of the output CSV file for keypoints.')
    args = parser.parse_args()

    cap = cv2.VideoCapture('/dev/video1')

    # delegate_path = '/home/mendel/coral/pycoral/libedgetpu_bin/direct/aarch64/libedgetpu.so.1'
    # This line of code is incorrect whether added or not.

    interpreter = make_interpreter(args.model)
    interpreter.allocate_tensors()

    while True:
        
        ret, frame = cap.read()
        if not ret:
            break

        
        img = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
        resized_img = img.resize(common.input_size(interpreter), Image.ANTIALIAS)
        common.set_input(interpreter, resized_img)

        interpreter.invoke()

        pose = common.output_tensor(interpreter, 0).copy().reshape(_NUM_KEYPOINTS, 3)

        draw = ImageDraw.Draw(img)
        width, height = img.size
        for i in range(_NUM_KEYPOINTS):
            draw.ellipse(
                xy=[
                    pose[i][1] * width - 2, pose[i][0] * height - 2,
                    pose[i][1] * width + 2, pose[i][0] * height + 2
                ],
                fill=(255, 0, 0))

        output_frame = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)

        cv2.imshow('MoveNet keypoints', output_frame)

        with open(args.csv, 'w', newline='') as csvfile:
            csvwriter = csv.writer(csvfile)
            for i in range(_NUM_KEYPOINTS):
                csvwriter.writerow([pose[i][0], pose[i][1], pose[i][2]])

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

if __name__ == '__main__':
    main()

into the "pycoral/examples" directory, and then ran the code python3 examples/move2.py -m test_data/movenet_single_pose_lightning_ptq_edgetpu.tflite --csv keypoints.csv.

The error message is "CC". I'm unsure whether the issue is with my code or the configuration. I hope someone can provide me with some assistance.

The error message is "CC". I'm unsure whether the issue is with my code or the configuration. I hope someone can provide me with some assistance.

The error message is "CC". I'm unsure whether the issue is with my code or the configuration. I hope someone can provide me with some assistance.

The error message is

mendel@indigo-zebra:~$ cd pycoral
mendel@indigo-zebra:~/pycoral$ python3 examples/move2.py -m test_data/movenet_single_pose_lightning_ptq_edgetpu.tflite --csv keypoints.csv
Traceback (most recent call last):
  File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 160, in load_delegate
    delegate = Delegate(library, options)
  File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 119, in __init__
    raise ValueError(capture.message)
ValueError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "examples/move2.py", line 82, in <module>
    main()
  File "examples/move2.py", line 30, in main
    interpreter = make_interpreter(args.model)
  File "/usr/lib/python3/dist-packages/pycoral/utils/edgetpu.py", line 87, in make_interpreter
    delegates = [load_edgetpu_delegate({'device': device} if device else {})]
  File "/usr/lib/python3/dist-packages/pycoral/utils/edgetpu.py", line 52, in load_edgetpu_delegate
    return tflite.load_delegate(_EDGETPU_SHARED_LIB, options or {})
  File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 163, in load_delegate
    library, str(e)))
ValueError: Failed to load delegate from libedgetpu.so.1

I'm unsure whether the issue is with my code or the configuration. I hope someone can provide me with some assistance.