SSD神经网络+opencv的人体识别

SSD神经网络+opencv的人体识别

之前听说opencv3可以运行深度学习的模型，所以我就试试看，用的 是caffe训练好的模型文件，这里自己去网上找吧，不分享了。结合SSD的caffemodel和net就可以实现图片中人体的检测，其实SSD可以识别21种物体，具体的物体大家看代码里面有写 

直接上代码

#include
#include
#include
#include
#include
#include
#include


using namespace cv;
using namespace cv::dnn;
using namespace std;


const size_t inWidth = 300;
const size_t inHeight = 300;
const float WHRatio = inWidth / (float)inHeight;
const float inScaleFactor = 0.007843f;
const float meanVal = 127.5;
const char* classNames[] = { "background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor" };


const char* about = "This sample uses Single-Shot Detector "
"(https://arxiv.org/abs/1512.02325)"
"to detect objects on image.\n"
".caffemodel model's file is avaliable here: "
"https://github.com/chuanqi305/MobileNet-SSD/blob/master/MobileNetSSD_train.caffemodel\n";


const char* params
= "{ help           | false | print usage         }"
"{ proto          | MobileNetSSD_300x300.prototxt | model configuration }"
"{ model          |       | model weights       }"
"{ video          |       | video for detection }"
"{ out            |       | path to output video file}"
"{ min_confidence | 0.2   | min confidence      }";


int main(int argc, char** argv)
{
cv::CommandLineParser parser(argc, argv, params);


if (parser.get("help"))
{
//cout << about << endl;
parser.printMessage();


return 0;
}


String modelConfiguration = "MobileNetSSD_deploy.prototxt";
String modelBinary = "MobileNetSSD_deploy.caffemodel";


//! [Initialize network]
dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
//! [Initialize network]


Mat frame = imread("8.jpg");
//! [Prepare blob]


Mat inputBlob = blobFromImage(frame, inScaleFactor,
Size(inWidth, inHeight), meanVal); //Convert Mat to batch of images
//! [Prepare blob]


//! [Set input blob]
net.setInput(inputBlob, "data");                //set the network input
//! [Set input blob]


TickMeter tm;
tm.start();
//! [Make forward pass]
Mat detection = net.forward("detection_out");                                  //compute output
tm.stop();
//cout << "Inference time, ms: " << tm.getTimeMilli() << endl;
//! [Make forward pass]


Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr());






float confidenceThreshold = parser.get("min_confidence");
for (int i = 0; i < detectionMat.rows; i++)
{
float confidence = detectionMat.at(i, 2);


if (confidence > confidenceThreshold)
{
size_t objectClass = (size_t)(detectionMat.at(i, 1));


int xLeftBottom = static_cast(detectionMat.at(i, 3) * frame.cols);
int yLeftBottom = static_cast(detectionMat.at(i, 4) * frame.rows);
int xRightTop = static_cast(detectionMat.at(i, 5) * frame.cols);
int yRightTop = static_cast(detectionMat.at(i, 6) * frame.rows);


ostringstream ss;
ss << confidence;
String conf(ss.str());


Rect object((int)xLeftBottom, (int)yLeftBottom,
(int)(xRightTop - xLeftBottom),
(int)(yRightTop - yLeftBottom));


rectangle(frame, object, Scalar(0, 255, 0));
String label = String(classNames[objectClass]) + ": " + conf;
int baseLine = 0;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height),
Size(labelSize.width, labelSize.height + baseLine)),
Scalar(255, 255, 255), CV_FILLED);
putText(frame, label, Point(xLeftBottom, yLeftBottom),
FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0));
}
}






imshow("detections", frame);
waitKey(0);




return 0;

}