File size: 5,449 Bytes
e5b568e e7d94f5 e5b568e e7d94f5 260eb6d e5b568e 260eb6d e7d94f5 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e f4c5d90 e5b568e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
import argparse
import numpy as np
import cv2 as cv
from mp_palmdet import MPPalmDet
def str2bool(v):
if v.lower() in ['on', 'yes', 'true', 'y', 't']:
return True
elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
return False
else:
raise NotImplementedError
backends = [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_BACKEND_CUDA]
targets = [cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_CUDA, cv.dnn.DNN_TARGET_CUDA_FP16]
help_msg_backends = "Choose one of the computation backends: {:d}: OpenCV implementation (default); {:d}: CUDA"
help_msg_targets = "Chose one of the target computation devices: {:d}: CPU (default); {:d}: CUDA; {:d}: CUDA fp16"
try:
backends += [cv.dnn.DNN_BACKEND_TIMVX]
targets += [cv.dnn.DNN_TARGET_NPU]
help_msg_backends += "; {:d}: TIMVX"
help_msg_targets += "; {:d}: NPU"
except:
print('This version of OpenCV does not support TIM-VX and NPU. Visit https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU for more information.')
parser = argparse.ArgumentParser(description='Hand Detector from MediaPipe')
parser.add_argument('--input', '-i', type=str, help='Usage: Set path to the input image. Omit for using default camera.')
parser.add_argument('--model', '-m', type=str, default='./palm_detection_mediapipe_2023feb.onnx', help='Usage: Set model path, defaults to palm_detection_mediapipe_2023feb.onnx.')
parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
parser.add_argument('--score_threshold', type=float, default=0.8, help='Usage: Set the minimum needed confidence for the model to identify a palm, defaults to 0.8. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold. An empirical score threshold for the quantized model is 0.49.')
parser.add_argument('--nms_threshold', type=float, default=0.3, help='Usage: Suppress bounding boxes of iou >= nms_threshold. Default = 0.3.')
parser.add_argument('--save', '-s', type=str, default=False, help='Usage: Set “True” to save file with results (i.e. bounding box, confidence level). Invalid in case of camera input. Default will be set to “False”.')
parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Usage: Default will be set to “True” and will open a new window to show results. Set to “False” to stop visualizations from being shown. Invalid in case of camera input.')
args = parser.parse_args()
def visualize(image, results, print_results=False, fps=None):
output = image.copy()
if fps is not None:
cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
for idx, palm in enumerate(results):
score = palm[-1]
palm_box = palm[0:4]
palm_landmarks = palm[4:-1].reshape(7, 2)
# put score
palm_box = palm_box.astype(np.int32)
cv.putText(output, '{:.4f}'.format(score), (palm_box[0], palm_box[1]+12), cv.FONT_HERSHEY_DUPLEX, 0.5, (0, 255, 0))
# draw box
cv.rectangle(output, (palm_box[0], palm_box[1]), (palm_box[2], palm_box[3]), (0, 255, 0), 2)
# draw points
palm_landmarks = palm_landmarks.astype(np.int32)
for p in palm_landmarks:
cv.circle(output, p, 2, (0, 0, 255), 2)
# Print results
if print_results:
print('-----------palm {}-----------'.format(idx + 1))
print('score: {:.2f}'.format(score))
print('palm box: {}'.format(palm_box))
print('palm landmarks: ')
for plm in palm_landmarks:
print('\t{}'.format(plm))
return output
if __name__ == '__main__':
# Instantiate MPPalmDet
model = MPPalmDet(modelPath=args.model,
nmsThreshold=args.nms_threshold,
scoreThreshold=args.score_threshold,
backendId=args.backend,
targetId=args.target)
# If input is an image
if args.input is not None:
image = cv.imread(args.input)
# Inference
results = model.infer(image)
if len(results) == 0:
print('Hand not detected')
# Draw results on the input image
image = visualize(image, results, print_results=True)
# Save results if save is true
if args.save:
print('Resutls saved to result.jpg\n')
cv.imwrite('result.jpg', image)
# Visualize results in a new window
if args.vis:
cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
cv.imshow(args.input, image)
cv.waitKey(0)
else: # Omit input to call default camera
deviceId = 0
cap = cv.VideoCapture(deviceId)
tm = cv.TickMeter()
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
if not hasFrame:
print('No frames grabbed!')
break
# Inference
tm.start()
results = model.infer(frame)
tm.stop()
# Draw results on the input image
frame = visualize(frame, results, fps=tm.getFPS())
# Visualize results in a new Window
cv.imshow('MPPalmDet Demo', frame)
tm.reset()
|