potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-31 00:03:03 +04:00
Code Packages Releases Wiki Activity

Merge pull request #25559 from gursimarsingh:improved_segmentation_sample

Browse Source 
Improved segmentation sample #25559

#25006

This pull request replaces caffe models with onnx for the dnn segmentation sample in cpp and python
fcnresnet-50 and fcnresnet-101 has been replaced
u2netp (foreground-background) segmentation onnx model has been added [U2NET](https://github.com/xuebinqin/U-2-Net) 

### Pull Request Readiness Checklist

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Gursimar Singh
2024-05-15 12:09:34 +05:30
committed by GitHub
parent 17e6b3f931
commit 48c31bddc4
3 changed files with 134 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/dnn/segmentation.cpp
+83 -66
View File
@@ -1,5 +1,6 @@
#include <fstream>
#include <sstream>
#include <iostream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
@@ -7,50 +8,54 @@
#include "common.hpp"
std::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. }"
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
"{ classes | | Optional path to a text file with names of classes. }"
"{ colors | | Optional path to a text file with colors for an every class. "
"An every color is represented with three values from 0 to 255 in BGR channels order. }";
std::string backend_keys = cv::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 }", cv::dnn::DNN_BACKEND_DEFAULT, cv::dnn::DNN_BACKEND_INFERENCE_ENGINE, cv::dnn::DNN_BACKEND_OPENCV, cv::dnn::DNN_BACKEND_VKCOM, cv::dnn::DNN_BACKEND_CUDA);
std::string target_keys = cv::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) }", cv::dnn::DNN_TARGET_CPU, cv::dnn::DNN_TARGET_OPENCL, cv::dnn::DNN_TARGET_OPENCL_FP16, cv::dnn::DNN_TARGET_MYRIAD, cv::dnn::DNN_TARGET_VULKAN, cv::dnn::DNN_TARGET_CUDA, cv::dnn::DNN_TARGET_CUDA_FP16);
std::string keys = param_keys + backend_keys + target_keys;
using namespace cv;
using namespace std;
using namespace dnn;
std::vector<std::string> classes;
std::vector<Vec3b> colors;
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)
int main(int argc, char **argv)
{
CommandLineParser parser(argc, argv, keys);
const std::string modelName = parser.get<String>("@alias");
const std::string zooFile = parser.get<String>("zoo");
const string modelName = parser.get<String>("@alias");
const string zooFile = parser.get<String>("zoo");
keys += genPreprocArguments(modelName, zooFile);
@@ -68,36 +73,33 @@ int main(int argc, char** argv)
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
String model = findFile(parser.get<String>("model"));
String config = findFile(parser.get<String>("config"));
String framework = parser.get<String>("framework");
int backendId = parser.get<int>("backend");
int targetId = parser.get<int>("target");
// Open file with classes names.
if (parser.has("classes"))
{
std::string file = parser.get<String>("classes");
std::ifstream ifs(file.c_str());
string file = parser.get<String>("classes");
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
while (std::getline(ifs, line))
string line;
while (getline(ifs, line))
{
classes.push_back(line);
}
}
// Open file with colors.
if (parser.has("colors"))
{
std::string file = parser.get<String>("colors");
std::ifstream ifs(file.c_str());
string file = parser.get<String>("colors");
ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
while (std::getline(ifs, line))
string line;
while (getline(ifs, line))
{
std::istringstream colorStr(line.c_str());
istringstream colorStr(line.c_str());
Vec3b color;
for (int i = 0; i < 3 && !colorStr.eof(); ++i)
@@ -114,23 +116,21 @@ int main(int argc, char** argv)
CV_Assert(!model.empty());
//! [Read and initialize network]
Net net = readNet(model, config, framework);
Net net = readNetFromONNX(model);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
//! [Read and initialize network]
// Create a window
static const std::string kWinName = "Deep learning semantic segmentation in OpenCV";
static const string kWinName = "Deep learning semantic segmentation in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL);
//! [Open a video file or an image file or a camera stream]
VideoCapture cap;
if (parser.has("input"))
cap.open(parser.get<String>("input"));
cap.open(findFile(parser.get<String>("input")));
else
cap.open(parser.get<int>("device"));
//! [Open a video file or an image file or a camera stream]
// Process frames.
Mat frame, blob;
while (waitKey(1) < 0)
@@ -141,29 +141,45 @@ int main(int argc, char** argv)
waitKey();
break;
}
imshow("Original Image", frame);
//! [Create a 4D blob from a frame]
blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, false);
//! [Create a 4D blob from a frame]
//! [Set input blob]
net.setInput(blob);
//! [Set input blob]
//! [Make forward pass]
Mat score = net.forward();
//! [Make forward pass]
Mat segm;
colorizeSegmentation(score, segm);
resize(segm, segm, frame.size(), 0, 0, INTER_NEAREST);
addWeighted(frame, 0.1, segm, 0.9, 0.0, frame);
if (modelName == "u2netp")
{
Mat mask, thresholded_mask, foreground_overlay, background_overlay, foreground_segmented;
mask = cv::Mat(score.size[2], score.size[3], CV_32F, score.ptr<float>(0, 0));
mask.convertTo(mask, CV_8U, 255);
threshold(mask, thresholded_mask, 0, 255, THRESH_BINARY + THRESH_OTSU);
resize(thresholded_mask, thresholded_mask, Size(frame.cols, frame.rows), 0, 0, INTER_AREA);
// Create overlays for foreground and background
foreground_overlay = Mat::zeros(frame.size(), frame.type());
background_overlay = Mat::zeros(frame.size(), frame.type());
// Set foreground (object) to red and background to blue
foreground_overlay.setTo(Scalar(0, 0, 255), thresholded_mask);
Mat inverted_mask;
bitwise_not(thresholded_mask, inverted_mask);
background_overlay.setTo(Scalar(255, 0, 0), inverted_mask);
// Blend the overlays with the original frame
addWeighted(frame, 1, foreground_overlay, 0.5, 0, foreground_segmented);
addWeighted(foreground_segmented, 1, background_overlay, 0.5, 0, frame);
}
else
{
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.
std::vector<double> layersTimes;
vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("Inference time: %.2f ms", t);
string label = format("Inference time: %.2f ms", t);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
imshow(kWinName, frame);
@@ -194,7 +210,8 @@ void colorizeSegmentation(const Mat &score, Mat &segm)
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()));
"number of colors (%d != %zu)",
chns, colors.size()));
}
Mat maxCl = Mat::zeros(rows, cols, CV_8UC1);
@@ -216,7 +233,6 @@ void colorizeSegmentation(const Mat &score, Mat &segm)
}
}
}
segm.create(rows, cols, CV_8UC3);
for (int row = 0; row < rows; row++)
{
@@ -239,7 +255,8 @@ void showLegend()
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()));
"number of labels (%zu != %zu)",
colors.size(), classes.size()));
}
legend.create(kBlockHeight * numClasses, 200, CV_8UC3);
for (int i = 0; i < numClasses; i++)