Skip to content

O
opencv
Commit 639b8007 authored by Vadim Pisarevsky's avatar Vadim Pisarevsky
Browse files
Options

Merge pull request #9941 from catree:improve_dnn_samples

parents 712689e8 48e07437
Hide whitespace changes
Inline Side-by-side
Showing with 285 additions and 120 deletions
samples/dnn/ssd_mobilenet_object_detection.cpp
View file @ 639b8007
...@@ -23,23 +23,25 @@ const char* classNames[] = {"background", ...@@ -23,23 +23,25 @@ const char* classNames[] = {"background",
"motorbike", "person", "pottedplant", "motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor"}; "sheep", "sofa", "train", "tvmonitor"};
const char* about = "This sample uses Single-Shot Detector " const char* about = "This sample uses MobileNet Single-Shot Detector "
"(https://arxiv.org/abs/1512.02325)" "(https://arxiv.org/abs/1704.04861) "
"to detect objects on image.\n" "to detect objects on camera/video/image.\n"
".caffemodel model's file is avaliable here: " ".caffemodel model's file is available here: "
"https://github.com/chuanqi305/MobileNet-SSD\n"; "https://github.com/chuanqi305/MobileNet-SSD\n"
"Default network is 300x300 and 20-classes VOC.\n";
const char* params const char* params
= "{ help | false | print usage }" = "{ help | false | print usage }"
"{ proto | MobileNetSSD_deploy.prototxt | model configuration }" "{ proto | MobileNetSSD_deploy.prototxt | model configuration }"
"{ model | MobileNetSSD_deploy.caffemodel | model weights }" "{ model | MobileNetSSD_deploy.caffemodel | model weights }"
"{ video | | video for detection }" "{ camera_device | 0 | camera device number }"
"{ video | | video or image for detection}"
"{ out | | path to output video file}" "{ out | | path to output video file}"
"{ min_confidence | 0.2 | min confidence }"; "{ min_confidence | 0.2 | min confidence }";
int main(int argc, char** argv) int main(int argc, char** argv)
{ {
cv::CommandLineParser parser(argc, argv, params); CommandLineParser parser(argc, argv, params);
if (parser.get<bool>("help")) if (parser.get<bool>("help"))
{ {
...@@ -55,19 +57,40 @@ int main(int argc, char** argv) ...@@ -55,19 +57,40 @@ int main(int argc, char** argv)
dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary); dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
//! [Initialize network] //! [Initialize network]
VideoCapture cap(parser.get<String>("video")); if (net.empty())
if(!cap.isOpened()) // check if we succeeded
{ {
cap = VideoCapture(0); cerr << "Can't load network by using the following files: " << endl;
cerr << "prototxt: " << modelConfiguration << endl;
cerr << "caffemodel: " << modelBinary << endl;
cerr << "Models can be downloaded here:" << endl;
cerr << "https://github.com/chuanqi305/MobileNet-SSD" << endl;
exit(-1);
}
VideoCapture cap;
if (parser.get<String>("video").empty())
{
int cameraDevice = parser.get<int>("camera_device");
cap = VideoCapture(cameraDevice);
if(!cap.isOpened())
{
cout << "Couldn't find camera: " << cameraDevice << endl;
return -1;
}
}
else
{
cap.open(parser.get<String>("video"));
if(!cap.isOpened()) if(!cap.isOpened())
{ {
cout << "Couldn't find camera" << endl; cout << "Couldn't open image or video: " << parser.get<String>("video") << endl;
return -1; return -1;
} }
} }
Size inVideoSize = Size((int) cap.get(CV_CAP_PROP_FRAME_WIDTH), //Acquire input size Size inVideoSize;
(int) cap.get(CV_CAP_PROP_FRAME_HEIGHT)); inVideoSize = Size((int) cap.get(CV_CAP_PROP_FRAME_WIDTH), //Acquire input size
(int) cap.get(CV_CAP_PROP_FRAME_HEIGHT));
Size cropSize; Size cropSize;
if (inVideoSize.width / (float)inVideoSize.height > WHRatio) if (inVideoSize.width / (float)inVideoSize.height > WHRatio)
...@@ -93,9 +116,18 @@ int main(int argc, char** argv) ...@@ -93,9 +116,18 @@ int main(int argc, char** argv)
for(;;) for(;;)
{ {
Mat frame; Mat frame;
cap >> frame; // get a new frame from camera cap >> frame; // get a new frame from camera/video or read image
//! [Prepare blob]
if (frame.empty())
{
waitKey();
break;
}
if (frame.channels() == 4)
cvtColor(frame, frame, COLOR_BGRA2BGR);
//! [Prepare blob]
Mat inputBlob = blobFromImage(frame, inScaleFactor, Mat inputBlob = blobFromImage(frame, inScaleFactor,
Size(inWidth, inHeight), meanVal, false); //Convert Mat to batch of images Size(inWidth, inHeight), meanVal, false); //Convert Mat to batch of images
//! [Prepare blob] //! [Prepare blob]
...@@ -108,15 +140,23 @@ int main(int argc, char** argv) ...@@ -108,15 +140,23 @@ int main(int argc, char** argv)
Mat detection = net.forward("detection_out"); //compute output Mat detection = net.forward("detection_out"); //compute output
//! [Make forward pass] //! [Make forward pass]
std::vector<double> layersTimings; vector<double> layersTimings;
double freq = getTickFrequency() / 1000; double freq = getTickFrequency() / 1000;
double time = net.getPerfProfile(layersTimings) / freq; double time = net.getPerfProfile(layersTimings) / freq;
cout << "Inference time, ms: " << time << endl;
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>()); Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
frame = frame(crop); frame = frame(crop);
ostringstream ss;
if (!outputVideo.isOpened())
{
ss << "FPS: " << 1000/time << " ; time: " << time << " ms";
putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255));
}
else
cout << "Inference time, ms: " << time << endl;
float confidenceThreshold = parser.get<float>("min_confidence"); float confidenceThreshold = parser.get<float>("min_confidence");
for(int i = 0; i < detectionMat.rows; i++) for(int i = 0; i < detectionMat.rows; i++)
{ {
...@@ -131,7 +171,7 @@ int main(int argc, char** argv) ...@@ -131,7 +171,7 @@ int main(int argc, char** argv)
int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols); int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows); int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);
ostringstream ss; ss.str("");
ss << confidence; ss << confidence;
String conf(ss.str()); String conf(ss.str());
......
samples/dnn/ssd_object_detection.cpp
View file @ 639b8007
...@@ -40,15 +40,26 @@ static Mat preprocess(const Mat& frame) ...@@ -40,15 +40,26 @@ static Mat preprocess(const Mat& frame)
return preprocessed; 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 " const char* about = "This sample uses Single-Shot Detector "
"(https://arxiv.org/abs/1512.02325)" "(https://arxiv.org/abs/1512.02325) "
"to detect objects on image\n"; // TODO: link "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 const char* params
= "{ help | false | print usage }" = "{ help | false | print usage }"
"{ proto | | model configuration }" "{ proto | | model configuration }"
"{ model | | model weights }" "{ 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 }"; "{ min_confidence | 0.5 | min confidence }";
int main(int argc, char** argv) int main(int argc, char** argv)
...@@ -57,7 +68,7 @@ int main(int argc, char** argv) ...@@ -57,7 +68,7 @@ int main(int argc, char** argv)
if (parser.get<bool>("help")) if (parser.get<bool>("help"))
{ {
std::cout << about << std::endl; cout << about << endl;
parser.printMessage(); parser.printMessage();
return 0; return 0;
} }
...@@ -79,58 +90,101 @@ int main(int argc, char** argv) ...@@ -79,58 +90,101 @@ int main(int argc, char** argv)
exit(-1); exit(-1);
} }
cv::Mat frame = cv::imread(parser.get<string>("image"), -1); VideoCapture cap;
if (parser.get<String>("video").empty())
if (frame.channels() == 4) {
cvtColor(frame, frame, COLOR_BGRA2BGR); int cameraDevice = parser.get<int>("camera_device");
//! [Prepare blob] cap = VideoCapture(cameraDevice);
Mat preprocessedFrame = preprocess(frame); if(!cap.isOpened())
{
Mat inputBlob = blobFromImage(preprocessedFrame, 1.0f, Size(), Scalar(), false); //Convert Mat to batch of images cout << "Couldn't find camera: " << cameraDevice << endl;
//! [Prepare blob] 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;
}
}
//! [Set input blob] for (;;)
net.setInput(inputBlob, "data"); //set the network input {
//! [Set input blob] cv::Mat frame;
cap >> frame; // get a new frame from camera/video or read image
//! [Make forward pass] if (frame.empty())
Mat detection = net.forward("detection_out"); //compute output {
//! [Make forward pass] waitKey();
break;
}
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>()); if (frame.channels() == 4)
cvtColor(frame, frame, COLOR_BGRA2BGR);
float confidenceThreshold = parser.get<float>("min_confidence"); //! [Prepare blob]
for(int i = 0; i < detectionMat.rows; i++) Mat preprocessedFrame = preprocess(frame);
{
float confidence = detectionMat.at<float>(i, 2);
if(confidence > confidenceThreshold) Mat inputBlob = blobFromImage(preprocessedFrame, 1.0f, Size(), Scalar(), false); //Convert Mat to batch of images
{ //! [Prepare blob]
size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
float xLeftBottom = detectionMat.at<float>(i, 3) * frame.cols; //! [Set input blob]
float yLeftBottom = detectionMat.at<float>(i, 4) * frame.rows; net.setInput(inputBlob, "data"); //set the network input
float xRightTop = detectionMat.at<float>(i, 5) * frame.cols; //! [Set input blob]
float yRightTop = detectionMat.at<float>(i, 6) * frame.rows;
std::cout << "Class: " << objectClass << std::endl; //! [Make forward pass]
std::cout << "Confidence: " << confidence << std::endl; Mat detection = net.forward("detection_out"); //compute output
//! [Make forward pass]
std::cout << " " << xLeftBottom vector<double> layersTimings;
<< " " << yLeftBottom double freq = getTickFrequency() / 1000;
<< " " << xRightTop double time = net.getPerfProfile(layersTimings) / freq;
<< " " << yRightTop << std::endl; ostringstream ss;
ss << "FPS: " << 1000/time << " ; time: " << time << " ms";
putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255));
Rect object((int)xLeftBottom, (int)yLeftBottom, Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
(int)(xRightTop - xLeftBottom),
(int)(yRightTop - yLeftBottom));
rectangle(frame, object, Scalar(0, 255, 0)); 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); imshow("detections", frame);
waitKey(); if (waitKey(1) >= 0) break;
}
return 0; return 0;
} // main } // main
samples/dnn/yolo_object_detection.cpp
View file @ 639b8007
...@@ -15,29 +15,36 @@ const size_t network_width = 416; ...@@ -15,29 +15,36 @@ const size_t network_width = 416;
const size_t network_height = 416; const size_t network_height = 416;
const char* about = "This sample uses You only look once (YOLO)-Detector " const char* about = "This sample uses You only look once (YOLO)-Detector "
"(https://arxiv.org/abs/1612.08242)" "(https://arxiv.org/abs/1612.08242) "
"to detect objects on image\n"; // TODO: link "to detect objects on camera/video/image.\n"
"Models can be downloaded here: "
"https://pjreddie.com/darknet/yolo/\n"
"Default network is 416x416.\n"
"Class names can be downloaded here: "
"https://github.com/pjreddie/darknet/tree/master/data\n";
const char* params const char* params
= "{ help | false | print usage }" = "{ help | false | print usage }"
"{ cfg | | model configuration }" "{ cfg | | model configuration }"
"{ model | | model weights }" "{ model | | model weights }"
"{ image | | image for detection }" "{ camera_device | 0 | camera device number}"
"{ min_confidence | 0.24 | min confidence }"; "{ video | | video or image for detection}"
"{ min_confidence | 0.24 | min confidence }"
"{ class_names | | class names }";
int main(int argc, char** argv) int main(int argc, char** argv)
{ {
cv::CommandLineParser parser(argc, argv, params); CommandLineParser parser(argc, argv, params);
if (parser.get<bool>("help")) if (parser.get<bool>("help"))
{ {
std::cout << about << std::endl; cout << about << endl;
parser.printMessage(); parser.printMessage();
return 0; return 0;
} }
String modelConfiguration = parser.get<string>("cfg"); String modelConfiguration = parser.get<String>("cfg");
String modelBinary = parser.get<string>("model"); String modelBinary = parser.get<String>("model");
//! [Initialize network] //! [Initialize network]
dnn::Net net = readNetFromDarknet(modelConfiguration, modelBinary); dnn::Net net = readNetFromDarknet(modelConfiguration, modelBinary);
...@@ -53,65 +60,130 @@ int main(int argc, char** argv) ...@@ -53,65 +60,130 @@ int main(int argc, char** argv)
exit(-1); exit(-1);
} }
cv::Mat frame = cv::imread(parser.get<string>("image")); VideoCapture cap;
if (parser.get<String>("video").empty())
{
int cameraDevice = parser.get<int>("camera_device");
cap = VideoCapture(cameraDevice);
if(!cap.isOpened())
{
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;
}
}
vector<string> classNamesVec;
ifstream classNamesFile(parser.get<String>("class_names").c_str());
if (classNamesFile.is_open())
{
string className = "";
while (classNamesFile >> className)
classNamesVec.push_back(className);
}
//! [Resizing without keeping aspect ratio] for(;;)
cv::Mat resized; {
cv::resize(frame, resized, cv::Size(network_width, network_height)); Mat frame;
//! [Resizing without keeping aspect ratio] cap >> frame; // get a new frame from camera/video or read image
//! [Prepare blob] if (frame.empty())
Mat inputBlob = blobFromImage(resized, 1 / 255.F); //Convert Mat to batch of images {
//! [Prepare blob] waitKey();
break;
}
//! [Set input blob] if (frame.channels() == 4)
net.setInput(inputBlob, "data"); //set the network input cvtColor(frame, frame, COLOR_BGRA2BGR);
//! [Set input blob]
//! [Make forward pass] //! [Resizing without keeping aspect ratio]
cv::Mat detectionMat = net.forward("detection_out"); //compute output Mat resized;
//! [Make forward pass] resize(frame, resized, Size(network_width, network_height));
//! [Resizing without keeping aspect ratio]
//! [Prepare blob]
Mat inputBlob = blobFromImage(resized, 1 / 255.F); //Convert Mat to batch of images
//! [Prepare blob]
float confidenceThreshold = parser.get<float>("min_confidence"); //! [Set input blob]
for (int i = 0; i < detectionMat.rows; i++) net.setInput(inputBlob, "data"); //set the network input
{ //! [Set input blob]
const int probability_index = 5;
const int probability_size = detectionMat.cols - probability_index; //! [Make forward pass]
float *prob_array_ptr = &detectionMat.at<float>(i, probability_index); Mat detectionMat = net.forward("detection_out"); //compute output
//! [Make forward pass]
size_t objectClass = std::max_element(prob_array_ptr, prob_array_ptr + probability_size) - prob_array_ptr; vector<double> layersTimings;
float confidence = detectionMat.at<float>(i, (int)objectClass + probability_index); 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));
if (confidence > confidenceThreshold) float confidenceThreshold = parser.get<float>("min_confidence");
for (int i = 0; i < detectionMat.rows; i++)
{ {
float x = detectionMat.at<float>(i, 0); const int probability_index = 5;
float y = detectionMat.at<float>(i, 1); const int probability_size = detectionMat.cols - probability_index;
float width = detectionMat.at<float>(i, 2); float *prob_array_ptr = &detectionMat.at<float>(i, probability_index);
float height = detectionMat.at<float>(i, 3);
float xLeftBottom = (x - width / 2) * frame.cols; size_t objectClass = max_element(prob_array_ptr, prob_array_ptr + probability_size) - prob_array_ptr;
float yLeftBottom = (y - height / 2) * frame.rows; float confidence = detectionMat.at<float>(i, (int)objectClass + probability_index);
float xRightTop = (x + width / 2) * frame.cols;
float yRightTop = (y + height / 2) * frame.rows; if (confidence > confidenceThreshold)
{
std::cout << "Class: " << objectClass << std::endl; float x = detectionMat.at<float>(i, 0);
std::cout << "Confidence: " << confidence << std::endl; float y = detectionMat.at<float>(i, 1);
float width = detectionMat.at<float>(i, 2);
std::cout << " " << xLeftBottom float height = detectionMat.at<float>(i, 3);
<< " " << yLeftBottom int xLeftBottom = static_cast<int>((x - width / 2) * frame.cols);
<< " " << xRightTop int yLeftBottom = static_cast<int>((y - height / 2) * frame.rows);
<< " " << yRightTop << std::endl; int xRightTop = static_cast<int>((x + width / 2) * frame.cols);
int yRightTop = static_cast<int>((y + height / 2) * frame.rows);
Rect object((int)xLeftBottom, (int)yLeftBottom,
(int)(xRightTop - xLeftBottom), Rect object(xLeftBottom, yLeftBottom,
(int)(yRightTop - yLeftBottom)); xRightTop - xLeftBottom,
yRightTop - yLeftBottom);
rectangle(frame, object, Scalar(0, 255, 0));
rectangle(frame, object, Scalar(0, 255, 0));
if (objectClass < classNamesVec.size())
{
ss.str("");
ss << confidence;
String conf(ss.str());
String label = String(classNamesVec[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));
}
else
{
cout << "Class: " << objectClass << endl;
cout << "Confidence: " << confidence << endl;
cout << " " << xLeftBottom
<< " " << yLeftBottom
<< " " << xRightTop
<< " " << yRightTop << endl;
}
}
} }
}
imshow("detections", frame); imshow("detections", frame);
waitKey(); if (waitKey(1) >= 0) break;
}
return 0; return 0;
} // main } // main
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment