基于opencv 手识识别基础

Posted 2022-08-23 qianbo_insist

手识识别

使用caffe训练的pose_iter_102000.caffemodel 可以直接识别手的各个关节和重要点，这里我们使用opencv 4.4.0，当然我们可以使用更高的版本，区别不大

另外一个就是要使用opencv的dnn模块
在这里插入图片描述

在这里插入图片描述

show me the code

#include <iostream>

using namespace std;
using namespace cv;
using namespace cv::dnn;
#ifdef _DEBUG
#pragma comment(lib,"opencv_world440d.lib")
#else
#pragma comment(lib,"opencv_world440.lib")
#endif

const int POSE_PAIRS[20][2] =

	0,1, 1,2, 2,3, 3,4,         // thumb
	0,5, 5,6, 6,7, 7,8,         // index
	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
;

string protoFile = "hand/pose_deploy.prototxt";
string weightsFile = "hand/pose_iter_102000.caffemodel";

int nPoints = 22;

int main(int argc, char **argv)


	cout << "USAGE : ./handPoseImage <imageFile> " << endl;

string imageFile = "qianbo2.jpg";
	// Take arguments from commmand line
	if (argc == 2)
	
		imageFile = argv[1];
	

	float thresh = 0.01;

	Mat frame = imread(imageFile);
	Mat frameCopy = frame.clone();
	int frameWidth = frame.cols;
	int frameHeight = frame.rows;

	float aspect_ratio = frameWidth / (float)frameHeight;
	int inHeight = 368;
	int inWidth = (int(aspect_ratio*inHeight) * 8) / 8;

	cout << "inWidth = " << inWidth << " ; inHeight = " << inHeight << endl;

	double t = (double)cv::getTickCount();
	Net net = readNetFromCaffe(protoFile, weightsFile);

	Mat inpBlob = blobFromImage(frame, 1.0 / 255, Size(inWidth, inHeight), Scalar(0, 0, 0), false, false);

	net.setInput(inpBlob);

	Mat output = net.forward();

	int H = output.size[2];
	int W = output.size[3];

	// find the position of the body parts
	vector<Point> points(nPoints);
	for (int n = 0; n < nPoints; n++)
	
		// Probability map of corresponding body's part.
		Mat probMap(H, W, CV_32F, output.ptr(0, n));
		resize(probMap, probMap, Size(frameWidth, frameHeight));

		Point maxLoc;
		double prob;
		minMaxLoc(probMap, 0, &prob, 0, &maxLoc);
		if (prob > thresh)
		
			circle(frameCopy, cv::Point((int)maxLoc.x, (int)maxLoc.y), 8, Scalar(0, 255, 255), -1);
			cv::putText(frameCopy, cv::format("%d", n), cv::Point((int)maxLoc.x, (int)maxLoc.y), cv::FONT_HERSHEY_COMPLEX, 1, cv::Scalar(0, 0, 255), 2);

		
		points[n] = maxLoc;
	

	int nPairs = sizeof(POSE_PAIRS) / sizeof(POSE_PAIRS[0]);

	for (int n = 0; n < nPairs; n++)
	
		// lookup 2 connected body/hand parts
		Point2f partA = points[POSE_PAIRS[n][0]];
		Point2f partB = points[POSE_PAIRS[n][1]];

		if (partA.x <= 0 || partA.y <= 0 || partB.x <= 0 || partB.y <= 0)
			continue;

		line(frame, partA, partB, Scalar(0, 255, 255), 8);
		circle(frame, partA, 8, Scalar(0, 0, 255), -1);
		circle(frame, partB, 8, Scalar(0, 0, 255), -1);
	

	t = ((double)cv::getTickCount() - t) / cv::getTickFrequency();
	cout << "Time Taken = " << t << endl;
	imshow("Output-Keypoints", frameCopy);
	imshow("Output-Skeleton", frame);
	imwrite("Output-Skeleton.jpg", frame);

	waitKey();

	return 0;