potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 23:33:05 +04:00
Code Packages Releases Wiki Activity

Add camera/video/image input for C++ DNN object detection samples. Add nice display and computation time.

Browse Source
This commit is contained in:
catree
2017-10-25 22:02:35 +02:00
parent 21c8e6d02d
commit 48e07437f0
3 changed files with 298 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/dnn/ssd_object_detection.cpp
+105 -51
View File
@@ -40,15 +40,26 @@ static Mat preprocess(const Mat& frame)
return preprocessed;
}
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"; // TODO: link
"(https://arxiv.org/abs/1512.02325) "
"to detect objects on camera/video/image.\n"
".caffemodel model's file is available here: "
"https://github.com/weiliu89/caffe/tree/ssd#models\n"
"Default network is 300x300 and 20-classes VOC.\n";
const char* params
= "{ help | false | print usage }"
"{ proto | | model configuration }"
"{ model | | model weights }"
"{ image | | image for detection }"
"{ camera_device | 0 | camera device number}"
"{ video | | video or image for detection}"
"{ min_confidence | 0.5 | min confidence }";
int main(int argc, char** argv)
@@ -57,7 +68,7 @@ int main(int argc, char** argv)
if (parser.get<bool>("help"))
{
std::cout << about << std::endl;
cout << about << endl;
parser.printMessage();
return 0;
}
@@ -79,58 +90,101 @@ int main(int argc, char** argv)
exit(-1);
}
cv::Mat frame = cv::imread(parser.get<string>("image"), -1);
if (frame.channels() == 4)
cvtColor(frame, frame, COLOR_BGRA2BGR);
//! [Prepare blob]
Mat preprocessedFrame = preprocess(frame);
Mat inputBlob = blobFromImage(preprocessedFrame, 1.0f, Size(), Scalar(), false); //Convert Mat to batch of images
//! [Prepare blob]
//! [Set input blob]
net.setInput(inputBlob, "data"); //set the network input
//! [Set input blob]
//! [Make forward pass]
Mat detection = net.forward("detection_out"); //compute output
//! [Make forward pass]
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
float confidenceThreshold = parser.get<float>("min_confidence");
for(int i = 0; i < detectionMat.rows; i++)
VideoCapture cap;
if (parser.get<String>("video").empty())
{
float confidence = detectionMat.at<float>(i, 2);
if(confidence > confidenceThreshold)
int cameraDevice = parser.get<int>("camera_device");
cap = VideoCapture(cameraDevice);
if(!cap.isOpened())
{
size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
float xLeftBottom = detectionMat.at<float>(i, 3) * frame.cols;
float yLeftBottom = detectionMat.at<float>(i, 4) * frame.rows;
float xRightTop = detectionMat.at<float>(i, 5) * frame.cols;
float yRightTop = detectionMat.at<float>(i, 6) * frame.rows;
std::cout << "Class: " << objectClass << std::endl;
std::cout << "Confidence: " << confidence << std::endl;
std::cout << " " << xLeftBottom
<< " " << yLeftBottom
<< " " << xRightTop
<< " " << yRightTop << std::endl;
Rect object((int)xLeftBottom, (int)yLeftBottom,
(int)(xRightTop - xLeftBottom),
(int)(yRightTop - yLeftBottom));
rectangle(frame, object, Scalar(0, 255, 0));
cout << "Couldn't find camera: " << cameraDevice << endl;
return -1;
}
}
else
{
cap.open(parser.get<String>("video"));
if(!cap.isOpened())
{
cout << "Couldn't open image or video: " << parser.get<String>("video") << endl;
return -1;
}
}
imshow("detections", frame);
waitKey();
for (;;)
{
cv::Mat frame;
cap >> frame; // get a new frame from camera/video or read image
if (frame.empty())
{
waitKey();
break;
}
if (frame.channels() == 4)
cvtColor(frame, frame, COLOR_BGRA2BGR);
//! [Prepare blob]
Mat preprocessedFrame = preprocess(frame);
Mat inputBlob = blobFromImage(preprocessedFrame, 1.0f, Size(), Scalar(), false); //Convert Mat to batch of images
//! [Prepare blob]
//! [Set input blob]
net.setInput(inputBlob, "data"); //set the network input
//! [Set input blob]
//! [Make forward pass]
Mat detection = net.forward("detection_out"); //compute output
//! [Make forward pass]
vector<double> layersTimings;
double freq = getTickFrequency() / 1000;
double time = net.getPerfProfile(layersTimings) / freq;
ostringstream ss;
ss << "FPS: " << 1000/time << " ; time: " << time << " ms";
putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255));
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
float confidenceThreshold = parser.get<float>("min_confidence");
for(int i = 0; i < detectionMat.rows; i++)
{
float confidence = detectionMat.at<float>(i, 2);
if(confidence > confidenceThreshold)
{
size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);
ss.str("");
ss << confidence;
String conf(ss.str());
Rect object(xLeftBottom, yLeftBottom,
xRightTop - xLeftBottom,
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);
if (waitKey(1) >= 0) break;
}
return 0;
} // main