15.6 fps
#project structure
pose.py
assets
mma.mp4
googleNet
graph_opt.pb
#pose.py
import os
import time
import cv2 as cv
import numpy as np
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--input', default="assets/mma.mp4", help='Path to image or video. Skip to capture frames from camera')
parser.add_argument('--thr', default=0.2, type=float, help='Threshold value for pose parts heat map')
parser.add_argument('--width', default=368, type=int, help='Resize input to specific width.')
parser.add_argument('--height', default=368, type=int, help='Resize input to specific height.')
args = parser.parse_args()
BODY_PARTS = {"Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,
"LEye": 15, "REar": 16, "LEar": 17, "Background": 18}
POSE_PAIRS = [["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],
["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],
["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],
["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"]]
inWidth = args.width
inHeight = args.height
net = cv.dnn.readNetFromTensorflow("googleNet/graph_opt.pb")
cap = cv.VideoCapture(args.input if args.input else 0)
# Define the codec and create VideoWriter object
fps = 25.175
frame_width = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
frame_height = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
size = (int(frame_width), int(frame_height))
fourcc = cv.VideoWriter_fourcc('m', 'p', '4', 'v')
path = 'C:/Users/zchen/PycharmProjects/opencv/googleNet/record'
writer = cv.VideoWriter()
success = writer.open(os.path.join(path, "pose estimation.mov"), fourcc, fps, size, True)
frame_count = 0
t1 = time.time()
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
net.setInput(cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))
out = net.forward()
out = out[:, :19, :, :] # MobileNet output [1, 57, -1, -1], we only need the first 19 elements
assert (len(BODY_PARTS) == out.shape[1])
points = []
for i in range(len(BODY_PARTS)):
# Slice heatmap of corresponging body's part.
heatMap = out[0, i, :, :]
# Originally, we try to find all the local maximums. To simplify a sample
# we just find a global one. However only a single pose at the same time
# could be detected this way.
_, conf, _, point = cv.minMaxLoc(heatMap)
x = (frameWidth * point[0]) / out.shape[3]
y = (frameHeight * point[1]) / out.shape[2]
# Add a point if it's confidence is higher than threshold.
points.append((int(x), int(y)) if conf > args.thr else None)
for pair in POSE_PAIRS:
partFrom = pair[0]
partTo = pair[1]
assert (partFrom in BODY_PARTS)
assert (partTo in BODY_PARTS)
idFrom = BODY_PARTS[partFrom]
idTo = BODY_PARTS[partTo]
if points[idFrom] and points[idTo]:
cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
t, _ = net.getPerfProfile()
freq = cv.getTickFrequency() / 1000
cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv.imshow("frame", frame)
writer.write(frame)
frame_count += 1
t2 = time.time()
# calculate FPS
fps = str(float(frame_count / float(t2 - t1))) + ' FPS'
print("Frames processed: {}".format(frame_count))
print("Elapsed time: {:.2f}".format(float(t2 - t1)))
print("FPS: {}".format(fps))
cap.release()
cv2.destroyAllWindows()
reference:
graph_opt.pb model
