#include <fstream>
#include <sstream>
#include <iostream>
#include "common.hpp"
using namespace dnn;
const string param_keys =
"{ help h | | Print help message. }"
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"
"{ zoo | 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. }"
"{ classes | | Optional path to a text file with names of classes. }"
"{ 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 | 0 | Choose one of computation backends: "
"%d: automatically (by default), "
"%d: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"%d: OpenCV implementation, "
"%d: VKCOM, "
"%d: CUDA }",
DNN_BACKEND_DEFAULT, DNN_BACKEND_INFERENCE_ENGINE, DNN_BACKEND_OPENCV, DNN_BACKEND_VKCOM, DNN_BACKEND_CUDA);
const string target_keys = format(
"{ target | 0 | Choose one of target computation devices: "
"%d: CPU target (by default), "
"%d: OpenCL, "
"%d: OpenCL fp16 (half-float precision), "
"%d: VPU, "
"%d: Vulkan, "
"%d: CUDA, "
"%d: CUDA fp16 (half-float preprocess) }",
DNN_TARGET_CPU, DNN_TARGET_OPENCL, DNN_TARGET_OPENCL_FP16, DNN_TARGET_MYRIAD, DNN_TARGET_VULKAN, DNN_TARGET_CUDA, DNN_TARGET_CUDA_FP16);
string keys = param_keys + backend_keys + target_keys;
vector<string> classes;
vector<Vec3b> colors;
void showLegend();
void colorizeSegmentation(
const Mat &score,
Mat &segm);
int main(
int argc,
char **argv)
{
const string modelName = parser.get<
String>(
"@alias");
const string zooFile = parser.get<
String>(
"zoo");
keys += genPreprocArguments(modelName, zooFile);
parser.about("Use this script to run semantic segmentation deep learning networks using OpenCV.");
if (argc == 1 || parser.has("help"))
{
parser.printMessage();
return 0;
}
float scale = parser.get<float>("scale");
bool swapRB = parser.get<bool>("rgb");
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
int backendId = parser.get<int>("backend");
int targetId = parser.get<int>("target");
if (parser.has("classes"))
{
string file = findFile(parser.get<
String>(
"classes"));
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError,
"File " + file +
" not found");
string line;
while (getline(ifs, line))
{
classes.push_back(line);
}
}
if (parser.has("colors"))
{
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError,
"File " + file +
" not found");
while (getline(ifs, line))
{
istringstream colorStr(
line.c_str());
for (int i = 0; i < 3 && !colorStr.eof(); ++i)
colorStr >> color[i];
colors.push_back(color);
}
}
if (!parser.check())
{
parser.printErrors();
return 1;
}
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
static const string kWinName = "Deep learning semantic segmentation in OpenCV";
if (parser.has("input"))
else
cap.
open(parser.get<
int>(
"device"));
{
cap >> frame;
if (frame.empty())
{
break;
}
imshow(
"Original Image", frame);
net.setInput(blob);
if (modelName == "u2netp")
{
vector<Mat> output;
net.forward(output, net.getUnconnectedOutLayersNames());
Mat pred = output[0].
reshape(1, output[0].size[2]);
resize(pred, mask,
Size(frame.cols, frame.rows), 0, 0, INTER_AREA);
Mat all_zeros = Mat::zeros(frame.size(),
CV_8UC1);
vector<Mat> channels = {all_zeros, all_zeros,
mask};
merge(channels, foreground_overlay);
addWeighted(frame, 0.25, foreground_overlay, 0.75, 0, frame);
}
else
{
Mat score = net.forward();
colorizeSegmentation(score, segm);
resize(segm, segm, frame.size(), 0, 0, INTER_NEAREST);
}
vector<double> layersTimes;
double t = net.getPerfProfile(layersTimes) / freq;
string label =
format(
"Inference time: %.2f ms", t);
if (!classes.empty())
showLegend();
}
return 0;
}
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())
{
colors.push_back(
Vec3b());
for (int i = 1; i < chns; ++i)
{
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 classes does not match "
"number of colors (%d != %zu)",
chns, colors.size()));
}
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;
}
}
}
}
for (int row = 0; row < rows; row++)
{
for (int col = 0; col < cols; col++)
{
ptrSegm[col] = colors[ptrMaxCl[col]];
}
}
}
void showLegend()
{
static const int kBlockHeight = 30;
{
const int numClasses = (int)classes.
size();
if ((int)colors.size() != numClasses)
{
CV_Error(Error::StsError,
format(
"Number of output classes does not match "
"number of labels (%zu != %zu)",
colors.size(), classes.size()));
}
for (int i = 0; i < numClasses; i++)
{
Mat block = legend.
rowRange(i * kBlockHeight, (i + 1) * kBlockHeight);
putText(block, classes[i],
Point(0, kBlockHeight / 2), FONT_HERSHEY_SIMPLEX, 0.5,
Vec3b(255, 255, 255));
}
}
}
Designed for command line parsing.
Definition utility.hpp:890
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 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.
void merge(const Mat *mv, size_t count, OutputArray dst)
Creates one multi-channel array out of several single-channel ones.
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.
GMat mask(const GMat &src, const GMat &mask)
Applies a mask to a matrix.
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 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.
int main(int argc, char *argv[])
Definition highgui_qt.cpp:3