OpenCV  5.0.0-pre
Open Source Computer Vision
Loading...
Searching...
No Matches
samples/dnn/segmentation.cpp
#include <fstream>
#include <sstream>
#include <iostream>
#include <opencv2/dnn.hpp>
#include "common.hpp"
using namespace cv;
using namespace std;
using namespace dnn;
const string about =
"Use this script to run semantic segmentation deep learning networks using OpenCV.\n\n"
"Firstly, download required models using `download_models.py` (if not already done). Set environment variable OPENCV_DOWNLOAD_CACHE_DIR to specify where models should be downloaded. Also, point OPENCV_SAMPLES_DATA_PATH to opencv/samples/data.\n"
"To run:\n"
"\t ./example_dnn_classification modelName(e.g. u2netp) --input=$OPENCV_SAMPLES_DATA_PATH/butterfly.jpg (or ignore this argument to use device camera)\n"
"Model path can also be specified using --model argument.";
const string param_keys =
"{ help h | | Print help message. }"
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"
"{ zoo | ../dnn/models.yml | An optional path to file with preprocessing parameters }"
"{ device | 0 | camera device number. }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera. }"
"{ colors | | Optional path to a text file with colors for an every class. "
"Every color is represented with three values from 0 to 255 in BGR channels order. }";
const string backend_keys = format(
"{ backend | default | Choose one of computation backends: "
"default: automatically (by default), "
"openvino: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"opencv: OpenCV implementation, "
"vkcom: VKCOM, "
"cuda: CUDA, "
"webnn: WebNN }");
const string target_keys = format(
"{ target | cpu | Choose one of target computation devices: "
"cpu: CPU target (by default), "
"opencl: OpenCL, "
"opencl_fp16: OpenCL fp16 (half-float precision), "
"vpu: VPU, "
"vulkan: Vulkan, "
"cuda: CUDA, "
"cuda_fp16: CUDA fp16 (half-float preprocess) }");
string keys = param_keys + backend_keys + target_keys;
vector<string> labels;
vector<Vec3b> colors;
static void colorizeSegmentation(const Mat &score, Mat &segm)
{
const int rows = score.size[2];
const int cols = score.size[3];
const int chns = score.size[1];
if (colors.empty())
{
// Generate colors.
colors.push_back(Vec3b());
for (int i = 1; i < chns; ++i)
{
Vec3b color;
for (int j = 0; j < 3; ++j)
color[j] = (colors[i - 1][j] + rand() % 256) / 2;
colors.push_back(color);
}
}
else if (chns != (int)colors.size())
{
CV_Error(Error::StsError, format("Number of output labels does not match "
"number of colors (%d != %zu)",
chns, colors.size()));
}
Mat maxCl = Mat::zeros(rows, cols, CV_8UC1);
Mat maxVal(rows, cols, CV_32FC1, score.data);
for (int ch = 1; ch < chns; ch++)
{
for (int row = 0; row < rows; row++)
{
const float *ptrScore = score.ptr<float>(0, ch, row);
uint8_t *ptrMaxCl = maxCl.ptr<uint8_t>(row);
float *ptrMaxVal = maxVal.ptr<float>(row);
for (int col = 0; col < cols; col++)
{
if (ptrScore[col] > ptrMaxVal[col])
{
ptrMaxVal[col] = ptrScore[col];
ptrMaxCl[col] = (uchar)ch;
}
}
}
}
segm.create(rows, cols, CV_8UC3);
for (int row = 0; row < rows; row++)
{
const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
Vec3b *ptrSegm = segm.ptr<Vec3b>(row);
for (int col = 0; col < cols; col++)
{
ptrSegm[col] = colors[ptrMaxCl[col]];
}
}
}
static void showLegend(FontFace fontFace)
{
static const int kBlockHeight = 30;
static Mat legend;
if (legend.empty())
{
const int numClasses = (int)labels.size();
if ((int)colors.size() != numClasses)
{
CV_Error(Error::StsError, format("Number of output labels does not match "
"number of labels (%zu != %zu)",
colors.size(), labels.size()));
}
legend.create(kBlockHeight * numClasses, 200, CV_8UC3);
for (int i = 0; i < numClasses; i++)
{
Mat block = legend.rowRange(i * kBlockHeight, (i + 1) * kBlockHeight);
block.setTo(colors[i]);
Rect r = getTextSize(Size(), labels[i], Point(), fontFace, 15, 400);
r.height += 15; // padding
r.width += 10; // padding
rectangle(block, r, Scalar::all(255), FILLED);
putText(block, labels[i], Point(10, kBlockHeight/2), Scalar(0,0,0), fontFace, 15, 400);
}
namedWindow("Legend", WINDOW_AUTOSIZE);
imshow("Legend", legend);
}
}
int main(int argc, char **argv)
{
CommandLineParser parser(argc, argv, keys);
const string modelName = parser.get<String>("@alias");
const string zooFile = findFile(parser.get<String>("zoo"));
keys += genPreprocArguments(modelName, zooFile);
parser = CommandLineParser(argc, argv, keys);
parser.about(about);
if (!parser.has("@alias") || parser.has("help"))
{
parser.printMessage();
return 0;
}
string sha1 = parser.get<String>("sha1");
float scale = parser.get<float>("scale");
Scalar mean = parser.get<Scalar>("mean");
bool swapRB = parser.get<bool>("rgb");
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
String model = findModel(parser.get<String>("model"), sha1);
const string backend = parser.get<String>("backend");
const string target = parser.get<String>("target");
int stdSize = 20;
int stdWeight = 400;
int stdImgSize = 512;
int imgWidth = -1; // Initialization
int fontSize = 50;
int fontWeight = 500;
FontFace fontFace("sans");
// Open file with labels names.
if (parser.has("labels"))
{
string file = findFile(parser.get<String>("labels"));
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
string line;
while (getline(ifs, line))
{
labels.push_back(line);
}
}
// Open file with colors.
if (parser.has("colors"))
{
string file = findFile(parser.get<String>("colors"));
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
string line;
while (getline(ifs, line))
{
istringstream colorStr(line.c_str());
Vec3b color;
for (int i = 0; i < 3 && !colorStr.eof(); ++i)
colorStr >> color[i];
colors.push_back(color);
}
}
if (!parser.check())
{
parser.printErrors();
return 1;
}
CV_Assert(!model.empty());
if (backend != "default" || target != "cpu"){
engine = ENGINE_CLASSIC;
}
Net net = readNetFromONNX(model, engine);
net.setPreferableBackend(getBackendID(backend));
net.setPreferableTarget(getTargetID(target));
// Create a window
static const string kWinName = "Deep learning semantic segmentation in OpenCV";
namedWindow(kWinName, WINDOW_AUTOSIZE);
if (parser.has("input"))
cap.open(findFile(parser.get<String>("input")));
else
cap.open(parser.get<int>("device"));
if (!cap.isOpened()) {
cerr << "Error: Video could not be opened." << endl;
return -1;
}
// Process frames.
Mat frame, blob;
while (waitKey(1) < 0)
{
cap >> frame;
if (frame.empty())
{
break;
}
if (imgWidth == -1){
imgWidth = max(frame.rows, frame.cols);
fontSize = min(fontSize, (stdSize*imgWidth)/stdImgSize);
fontWeight = min(fontWeight, (stdWeight*imgWidth)/stdImgSize);
}
imshow("Original Image", frame);
blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, false);
net.setInput(blob);
if (modelName == "u2netp")
{
vector<Mat> output;
net.forward(output, net.getUnconnectedOutLayersNames());
Mat pred = output[0].reshape(1, output[0].size[2]);
pred.convertTo(pred, CV_8U, 255.0);
Mat mask;
resize(pred, mask, Size(frame.cols, frame.rows), 0, 0, INTER_AREA);
// Create overlays for foreground and background
Mat foreground_overlay;
// Set foreground (object) to red
Mat all_zeros = Mat::zeros(frame.size(), CV_8UC1);
vector<Mat> channels = {all_zeros, all_zeros, mask};
merge(channels, foreground_overlay);
// Blend the overlays with the original frame
addWeighted(frame, 0.25, foreground_overlay, 0.75, 0, frame);
}
else
{
Mat score = net.forward();
Mat segm;
colorizeSegmentation(score, segm);
resize(segm, segm, frame.size(), 0, 0, INTER_NEAREST);
addWeighted(frame, 0.1, segm, 0.9, 0.0, frame);
}
// Put efficiency information.
vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
string label = format("Inference time: %.2f ms", t);
Rect r = getTextSize(Size(), label, Point(), fontFace, fontSize, fontWeight);
r.height += fontSize; // padding
r.width += 10; // padding
rectangle(frame, r, Scalar::all(255), FILLED);
putText(frame, label, Point(10, fontSize), Scalar(0,0,0), fontFace, fontSize, fontWeight);
imshow(kWinName, frame);
if (!labels.empty())
showLegend(fontFace);
}
return 0;
}
Designed for command line parsing.
Definition utility.hpp:890
Wrapper on top of a truetype/opentype/etc font, i.e. Freetype's FT_Face.
Definition imgproc.hpp:4996
n-dimensional dense array class
Definition mat.hpp:950
Mat & setTo(InputArray value, InputArray mask=noArray())
Sets all or some of the array elements to the specified value.
MatSize size
Definition mat.hpp:2447
uchar * data
pointer to the data
Definition mat.hpp:2427
Mat reshape(int cn, int rows=0) const
Changes the shape and/or the number of channels of a 2D matrix without copying the data.
void create(int rows, int cols, int type)
Allocates new array data if needed.
uchar * ptr(int i0=0)
Returns a pointer to the specified matrix row.
Mat rowRange(int startrow, int endrow) const
Creates a matrix header for the specified row span.
bool empty() const
Returns true if the array has no elements.
void convertTo(OutputArray m, int rtype, double alpha=1, double beta=0) const
Converts an array to another data type with optional scaling.
Template class for 2D rectangles.
Definition types.hpp:447
_Tp width
width of the rectangle
Definition types.hpp:492
_Tp height
height of the rectangle
Definition types.hpp:493
Template class for specifying the size of an image or rectangle.
Definition types.hpp:338
Template class for short numerical vectors, a partial case of Matx.
Definition matx.hpp:379
Class for video capturing from video files, image sequences or cameras.
Definition videoio.hpp:727
virtual bool open(const String &filename, int apiPreference=CAP_ANY)
Opens a video file or a capturing device or an IP video stream for video capturing.
virtual bool isOpened() const
Returns true if video capturing has been initialized already.
Scalar mean(InputArray src, InputArray mask=noArray())
Calculates an average (mean) of array elements.
void merge(const Mat *mv, size_t count, OutputArray dst)
Creates one multi-channel array out of several single-channel ones.
void min(InputArray src1, InputArray src2, OutputArray dst)
Calculates per-element minimum of two arrays or an array and a scalar.
void max(InputArray src1, InputArray src2, OutputArray dst)
Calculates per-element maximum of two arrays or an array and a scalar.
void addWeighted(InputArray src1, double alpha, InputArray src2, double beta, double gamma, OutputArray dst, int dtype=-1)
Calculates the weighted sum of two arrays.
std::string String
Definition cvstd.hpp:151
#define CV_8U
Definition interface.h:76
#define CV_32FC1
Definition interface.h:129
unsigned char uchar
Definition interface.h:51
#define CV_8UC1
Definition interface.h:99
#define CV_8UC3
Definition interface.h:101
cv::String findFile(const cv::String &relative_path, bool required=true, bool silentMode=false)
Try to find requested data file.
String format(const char *fmt,...)
Returns a text string formatted using the printf-like expression.
#define CV_Error(code, msg)
Call the error handler.
Definition exception.hpp:174
double getTickFrequency()
Returns the number of ticks per second.
#define CV_Assert(expr)
Checks a condition at runtime and throws exception if it fails.
Definition exception.hpp:198
Mat blobFromImage(InputArray image, double scalefactor=1.0, const Size &size=Size(), const Scalar &mean=Scalar(), bool swapRB=false, bool crop=false, int ddepth=CV_32F)
Creates 4-dimensional blob from image. Optionally resizes and crops image from center,...
Net readNetFromONNX(CV_WRAP_FILE_PATH const String &onnxFile, int engine=ENGINE_AUTO)
Reads a network model ONNX.
EngineType
Definition dnn.hpp:1020
@ ENGINE_CLASSIC
Force use the old dnn engine similar to 4.x branch.
Definition dnn.hpp:1021
@ ENGINE_AUTO
Try to use the new engine and then fall back to the classic version.
Definition dnn.hpp:1023
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
int waitKey(int delay=0)
Waits for a pressed key.
void namedWindow(const String &winname, int flags=WINDOW_AUTOSIZE)
Creates a window.
void rectangle(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a simple, thick, or filled up-right rectangle.
Size getTextSize(const String &text, int fontFace, double fontScale, int thickness, int *baseLine)
Calculates the width and height of a text string.
void putText(InputOutputArray img, const String &text, Point org, int fontFace, double fontScale, Scalar color, int thickness=1, int lineType=LINE_8, bool bottomLeftOrigin=false)
Draws a text string.
void line(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a line segment connecting two points.
void resize(InputArray src, OutputArray dst, Size dsize, double fx=0, double fy=0, int interpolation=INTER_LINEAR)
Resizes an image.
int main(int argc, char *argv[])
Definition highgui_qt.cpp:3
void scale(cv::Mat &mat, const cv::Mat &range, const T min, const T max)
Definition quality_utils.hpp:90
Definition core.hpp:107