def video(args):
config = load_config(args)
model = create_model(args, config)
cap = cv2.VideoCapture(0)
# cap = cv2.VideoCapture("/home/fabian/Documents/dataset/videos/test4.mp4")
if cap.isOpened() is False:
print('Error opening video stream or file')
exit(1)
logger.info('camera will capture {} FPS'.format(cap.get(cv2.CAP_PROP_FPS)))
if os.path.exists('mask.png'):
mask = Image.open('mask.png')
mask = mask.resize((200, 200))
else:
mask = None
fps_time = 0
degree = 0
detection_thresh = config.getfloat('predict', 'detection_thresh')
min_num_keypoints = config.getint('predict', 'min_num_keypoints')
while cap.isOpened():
degree += 5
degree = degree % 360
ret_val, image = cap.read()
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, model.insize)
with chainer.using_config('autotune', True):
humans = estimate(model,
image.transpose(2, 0, 1).astype(np.float32),
detection_thresh, min_num_keypoints)
pilImg = Image.fromarray(image)
pilImg = draw_humans(
model.keypoint_names,
model.edges,
pilImg,
humans,
mask=mask.rotate(degree) if mask else None,
visbbox=config.getboolean('predict', 'visbbox'),
)
img_with_humans = cv2.cvtColor(np.asarray(pilImg), cv2.COLOR_RGB2BGR)
msg = 'GPU ON' if chainer.backends.cuda.available else 'GPU OFF'
msg += ' ' + config.get('model_param', 'model_name')
cv2.putText(img_with_humans,
'FPS: % f' % (1.0 / (time.time() - fps_time)), (10, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
# img_with_humans = cv2.resize(img_with_humans, (3 * model.insize[0], 3 * model.insize[1]))
img_with_humans = cv2.resize(
img_with_humans, (1 * model.insize[0], 1 * model.insize[1]))
cv2.imshow('Pose Proposal Network' + msg, img_with_humans)
fps_time = time.time()
# press Esc to exit
if cv2.waitKey(1) == 27:
break
def compute_accuracy(t0, t1, x, y):
predicted = []
for i in range(len(x)):
predicted.append(estimate(t0, t1, x[i]))
delta = y - predicted
mse = mean(delta**2)
mae = mean(abs(delta))
r2 = 1 - (sum(delta**2) / sum((y - mean(y))**2))
print(f"""Here are the various metrics for accuracy:
\tMAE (Mean Absolute Error) = {round(mae, 2)}
\tMSE (Mean Square Error) = {round(mse, 2)}
\tRMSE (Root Mean Squared Error) = {round(sqrt(mse), 2)}
\tR-squared (Coefficient of determination) = {round(r2, 2)}""")
def main():
config = configparser.ConfigParser()
config.read('config.ini', 'UTF-8')
# load model
model = create_model(config)
cap = cv2.VideoCapture(0)
if cap.isOpened() is False:
print('Error opening video stream or file')
exit(1)
logger.info('camera will capture {} FPS'.format(cap.get(cv2.CAP_PROP_FPS)))
if os.path.exists('mask.png'):
mask = Image.open('mask.png')
mask = mask.resize((200, 200))
else:
mask = None
fps_time = 0
degree = 0
while cap.isOpened():
degree += 5
degree = degree % 360
ret_val, image = cap.read()
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, model.insize)
with chainer.using_config('autotune', True):
humans = estimate(model,
image.transpose(2, 0, 1).astype(np.float32))
pilImg = Image.fromarray(image)
pilImg = draw_humans(
model.keypoint_names,
model.edges,
pilImg,
humans,
mask=mask.rotate(degree) if mask else None
)
img_with_humans = cv2.cvtColor(np.asarray(pilImg), cv2.COLOR_RGB2BGR)
msg = 'GPU ON' if chainer.backends.cuda.available else 'GPU OFF'
msg += ' ' + config.get('model_param', 'model_name')
cv2.putText(img_with_humans, 'FPS: % f' % (1.0 / (time.time() - fps_time)),
(10, 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
img_with_humans = cv2.resize(img_with_humans, (3 * model.insize[0], 3 * model.insize[1]))
cv2.imshow('Pose Proposal Network' + msg, img_with_humans)
fps_time = time.time()
# press Esc to exit
if cv2.waitKey(1) == 27:
break
def video_handle(video_file, video_output):
global FPS_list
# Video reader
cam = cv2.VideoCapture(video_file)
input_fps = cam.get(cv2.CAP_PROP_FPS)
ret_val, input_image = cam.read()
video_length = int(cam.get(cv2.CAP_PROP_FRAME_COUNT))
ending_frame = video_length
# Video writer
frame_rate_ratio = 1
output_fps = input_fps / frame_rate_ratio
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
# 后面两者是写入的图片大小
out = cv2.VideoWriter(video_output, fourcc, output_fps, (672, 672))
i = 0 # default is 0
while (cam.isOpened()) and ret_val == True and i < ending_frame:
if i % frame_rate_ratio == 0:
tic = time.time()
mask = None
input_image = cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB)
input_image = cv2.resize(input_image, model.insize)
humans = estimate(
model,
input_image.transpose(2, 0, 1).astype(np.float32))
pilImg = Image.fromarray(input_image)
pilImg = draw_humans(
model.keypoint_names,
model.edges,
pilImg,
humans,
mask=mask.rotate(degree) if mask else None)
img_with_humans = cv2.cvtColor(np.asarray(pilImg),
cv2.COLOR_RGB2BGR)
msg = 'GPU ON' if chainer.backends.cuda.available else 'GPU OFF'
msg += ' ' + config.get('model_param', 'model_name')
FPS = round(1.0 / (time.time() - tic), 2)
FPS_list.append(FPS)
cv2.putText(img_with_humans,
'FPS: % f' % (1.0 / (time.time() - tic)), (10, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
img_with_humans = cv2.resize(
img_with_humans,
(3 * model.insize[0], 3 * model.insize[1]))
# cv2.imshow('Pose Proposal Network' + msg, img_with_humans)
print('Processing frame: {}/{}'.format(
i, video_length / frame_rate_ratio))
toc = time.time()
print('processing time is %.5f' % (toc - tic))
out.write(img_with_humans)
# 每次在这里变化的
ret_val, input_image = cam.read()
i += 1
# compute average FPS
average_fps = sum(FPS_list) / len(FPS_list)
print('total {} frame, {} frame per second\n\n\n'.format(
len(FPS_list), round(average_fps, 1)))
def t1_sigma(t0, t1, x, y, size):
t1_sum = 0
for i in range(size):
t1_sum += (estimate(t0, t1, x[i]) - y[i]) * x[i]
return t1_sum
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
# 后面两者是写入的图片大小
out = cv2.VideoWriter(video_output, fourcc, output_fps, (672, 672))
i = 0 # default is 0
while (cam.isOpened()) and ret_val == True and i < ending_frame:
# 每隔几帧处理一次帧图片
if i % frame_rate_ratio == 0:
tic = time.time()
mask = None
input_image = cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB)
input_image = cv2.resize(input_image, model.insize)
humans = estimate(
model,
input_image.transpose(2, 0, 1).astype(np.float32))
pilImg = Image.fromarray(input_image)
pilImg = draw_humans(model.keypoint_names,
model.edges,
pilImg,
humans,
mask=mask.rotate(degree) if mask else None)
img_with_humans = cv2.cvtColor(np.asarray(pilImg),
cv2.COLOR_RGB2BGR)
msg = 'GPU ON' if chainer.backends.cuda.available else 'GPU OFF'
msg += ' ' + config.get('model_param', 'model_name')
cv2.putText(img_with_humans,
'FPS: % f' % (1.0 / (time.time() - tic)), (10, 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
img_with_humans = cv2.resize(
