mirror of
https://github.com/opencv/opencv.git
synced 2024-11-25 19:50:38 +08:00
10e1de74d2
* Intel Inference Engine deep learning backend. * OpenFace network using Inference Engine backend
106 lines
4.9 KiB
Python
106 lines
4.9 KiB
Python
# To use Inference Engine backend, specify location of plugins:
|
|
# export LD_LIBRARY_PATH=/opt/intel/deeplearning_deploymenttoolkit/deployment_tools/external/mklml_lnx/lib:$LD_LIBRARY_PATH
|
|
import cv2 as cv
|
|
import numpy as np
|
|
import argparse
|
|
|
|
parser = argparse.ArgumentParser(
|
|
description='This script is used to demonstrate OpenPose human pose estimation network '
|
|
'from https://github.com/CMU-Perceptual-Computing-Lab/openpose project using OpenCV. '
|
|
'The sample and model are simplified and could be used for a single person on the frame.')
|
|
parser.add_argument('--input', help='Path to image or video. Skip to capture frames from camera')
|
|
parser.add_argument('--proto', help='Path to .prototxt')
|
|
parser.add_argument('--model', help='Path to .caffemodel')
|
|
parser.add_argument('--dataset', help='Specify what kind of model was trained. '
|
|
'It could be (COCO, MPI) depends on dataset.')
|
|
parser.add_argument('--thr', default=0.1, 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.')
|
|
parser.add_argument('--inf_engine', action='store_true',
|
|
help='Enable Intel Inference Engine computational backend. '
|
|
'Check that plugins folder is in LD_LIBRARY_PATH environment variable')
|
|
|
|
args = parser.parse_args()
|
|
|
|
if args.dataset == 'COCO':
|
|
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"] ]
|
|
else:
|
|
assert(args.dataset == 'MPI')
|
|
BODY_PARTS = { "Head": 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, "Chest": 14,
|
|
"Background": 15 }
|
|
|
|
POSE_PAIRS = [ ["Head", "Neck"], ["Neck", "RShoulder"], ["RShoulder", "RElbow"],
|
|
["RElbow", "RWrist"], ["Neck", "LShoulder"], ["LShoulder", "LElbow"],
|
|
["LElbow", "LWrist"], ["Neck", "Chest"], ["Chest", "RHip"], ["RHip", "RKnee"],
|
|
["RKnee", "RAnkle"], ["Chest", "LHip"], ["LHip", "LKnee"], ["LKnee", "LAnkle"] ]
|
|
|
|
inWidth = args.width
|
|
inHeight = args.height
|
|
|
|
net = cv.dnn.readNetFromCaffe(args.proto, args.model)
|
|
if args.inf_engine:
|
|
net.setPreferableBackend(cv.dnn.DNN_BACKEND_INFERENCE_ENGINE)
|
|
|
|
cap = cv.VideoCapture(args.input if args.input else 0)
|
|
|
|
while cv.waitKey(1) < 0:
|
|
hasFrame, frame = cap.read()
|
|
if not hasFrame:
|
|
cv.waitKey()
|
|
break
|
|
|
|
frameWidth = frame.shape[1]
|
|
frameHeight = frame.shape[0]
|
|
inp = cv.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),
|
|
(0, 0, 0), swapRB=False, crop=False)
|
|
net.setInput(inp)
|
|
out = net.forward()
|
|
|
|
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((x, 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('OpenPose using OpenCV', frame)
|