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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
//
// this sample demonstrates the use of pretrained openpose networks with opencv's dnn module.
//
// it can be used for body pose detection, using either the COCO model(18 parts):
// http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/coco/pose_iter_440000.caffemodel
// https://raw.githubusercontent.com/opencv/opencv_extra/master/testdata/dnn/openpose_pose_coco.prototxt
//
// or the MPI model(16 parts):
// http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/mpi/pose_iter_160000.caffemodel
// https://raw.githubusercontent.com/opencv/opencv_extra/master/testdata/dnn/openpose_pose_mpi_faster_4_stages.prototxt
//
// (to simplify this sample, the body models are restricted to a single person.)
//
//
// you can also try the hand pose model:
// http://posefs1.perception.cs.cmu.edu/OpenPose/models/hand/pose_iter_102000.caffemodel
// https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/models/hand/pose_deploy.prototxt
//
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;
#include <iostream>
using namespace std;
// connection table, in the format [model_id][pair_id][from/to]
// please look at the nice explanation at the bottom of:
// https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md
//
const int POSE_PAIRS[3][20][2] = {
{ // COCO body
{1,2}, {1,5}, {2,3},
{3,4}, {5,6}, {6,7},
{1,8}, {8,9}, {9,10},
{1,11}, {11,12}, {12,13},
{1,0}, {0,14},
{14,16}, {0,15}, {15,17}
},
{ // MPI body
{0,1}, {1,2}, {2,3},
{3,4}, {1,5}, {5,6},
{6,7}, {1,14}, {14,8}, {8,9},
{9,10}, {14,11}, {11,12}, {12,13}
},
{ // hand
{0,1}, {1,2}, {2,3}, {3,4}, // thumb
{0,5}, {5,6}, {6,7}, {7,8}, // pinkie
{0,9}, {9,10}, {10,11}, {11,12}, // middle
{0,13}, {13,14}, {14,15}, {15,16}, // ring
{0,17}, {17,18}, {18,19}, {19,20} // small
}};
int main(int argc, char **argv)
{
CommandLineParser parser(argc, argv,
"{ h help | false | print this help message }"
"{ p proto | | (required) model configuration, e.g. hand/pose.prototxt }"
"{ m model | | (required) model weights, e.g. hand/pose_iter_102000.caffemodel }"
"{ i image | | (required) path to image file (containing a single person, or hand) }"
"{ width | 368 | Preprocess input image by resizing to a specific width. }"
"{ height | 368 | Preprocess input image by resizing to a specific height. }"
"{ t threshold | 0.1 | threshold or confidence value for the heatmap }"
);
String modelTxt = parser.get<string>("proto");
String modelBin = parser.get<string>("model");
String imageFile = parser.get<String>("image");
int W_in = parser.get<int>("width");
int H_in = parser.get<int>("height");
float thresh = parser.get<float>("threshold");
if (parser.get<bool>("help") || modelTxt.empty() || modelBin.empty() || imageFile.empty())
{
cout << "A sample app to demonstrate human or hand pose detection with a pretrained OpenPose dnn." << endl;
parser.printMessage();
return 0;
}
// read the network model
Net net = readNetFromCaffe(modelTxt, modelBin);
// and the image
Mat img = imread(imageFile);
if (img.empty())
{
std::cerr << "Can't read image from the file: " << imageFile << std::endl;
exit(-1);
}
// send it through the network
Mat inputBlob = blobFromImage(img, 1.0 / 255, Size(W_in, H_in), Scalar(0, 0, 0), false, false);
net.setInput(inputBlob);
Mat result = net.forward();
// the result is an array of "heatmaps", the probability of a body part being in location x,y
int midx, npairs;
int nparts = result.size[1];
int H = result.size[2];
int W = result.size[3];
// find out, which model we have
if (nparts == 19)
{ // COCO body
midx = 0;
npairs = 17;
nparts = 18; // skip background
}
else if (nparts == 16)
{ // MPI body
midx = 1;
npairs = 14;
}
else if (nparts == 22)
{ // hand
midx = 2;
npairs = 20;
}
else
{
cerr << "there should be 19 parts for the COCO model, 16 for MPI, or 22 for the hand one, but this model has " << nparts << " parts." << endl;
return (0);
}
// find the position of the body parts
vector<Point> points(22);
for (int n=0; n<nparts; n++)
{
// Slice heatmap of corresponding body's part.
Mat heatMap(H, W, CV_32F, result.ptr(0,n));
// 1 maximum per heatmap
Point p(-1,-1),pm;
double conf;
minMaxLoc(heatMap, 0, &conf, 0, &pm);
if (conf > thresh)
p = pm;
points[n] = p;
}
// connect body parts and draw it !
float SX = float(img.cols) / W;
float SY = float(img.rows) / H;
for (int n=0; n<npairs; n++)
{
// lookup 2 connected body/hand parts
Point2f a = points[POSE_PAIRS[midx][n][0]];
Point2f b = points[POSE_PAIRS[midx][n][1]];
// we did not find enough confidence before
if (a.x<=0 || a.y<=0 || b.x<=0 || b.y<=0)
continue;
// scale to image size
a.x*=SX; a.y*=SY;
b.x*=SX; b.y*=SY;
line(img, a, b, Scalar(0,200,0), 2);
circle(img, a, 3, Scalar(0,0,200), -1);
circle(img, b, 3, Scalar(0,0,200), -1);
}
imshow("OpenPose", img);
waitKey();
return 0;
}