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 branch 4.x

Browse Source
This commit is contained in:
Alexander Smorkalov
2024-07-16 10:11:21 +03:00
parent 420663498f 53a5b85d9f
commit fc9208cff5
102 changed files with 3618 additions and 2171 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/dnn/yolo_detector.cpp
+22 -10
View File
@@ -27,7 +27,8 @@ void yoloPostProcessing(
std::vector<Rect2d>& keep_boxes,
float conf_threshold,
float iou_threshold,
const std::string& test_name
const std::string& model_name,
const int nc
);
std::vector<std::string> classes;
@@ -40,6 +41,7 @@ std::string keys =
"{ yolo | yolox | yolo model version. }"
"{ 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 to label detected objects. }"
"{ nc | 80 | Number of classes. Default is 80 (coming from COCO dataset). }"
"{ thr | .5 | Confidence threshold. }"
"{ nms | .4 | Non-maximum suppression threshold. }"
"{ mean | 0.0 | Normalization constant. }"
@@ -107,19 +109,21 @@ void yoloPostProcessing(
std::vector<Rect2d>& keep_boxes,
float conf_threshold,
float iou_threshold,
const std::string& test_name)
const std::string& model_name,
const int nc=80)
{
// Retrieve
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect2d> boxes;
if (test_name == "yolov8")
if (model_name == "yolov8" || model_name == "yolov10" ||
model_name == "yolov9")
{
cv::transposeND(outs[0], {0, 2, 1}, outs[0]);
}
if (test_name == "yolonas")
if (model_name == "yolonas")
{
// outs contains 2 elemets of shape [1, 8400, 80] and [1, 8400, 4]. Concat them to get [1, 8400, 84]
Mat concat_out;
@@ -131,25 +135,30 @@ void yoloPostProcessing(
// remove the second element
outs.pop_back();
// unsqueeze the first dimension
outs[0] = outs[0].reshape(0, std::vector<int>{1, 8400, 84});
outs[0] = outs[0].reshape(0, std::vector<int>{1, 8400, nc + 4});
}
// assert if last dim is 85 or 84
CV_CheckEQ(outs[0].dims, 3, "Invalid output shape. The shape should be [1, #anchors, 85 or 84]");
CV_CheckEQ((outs[0].size[2] == nc + 5 || outs[0].size[2] == 80 + 4), true, "Invalid output shape: ");
for (auto preds : outs)
{
preds = preds.reshape(1, preds.size[1]); // [1, 8400, 85] -> [8400, 85]
for (int i = 0; i < preds.rows; ++i)
{
// filter out non object
float obj_conf = (test_name == "yolov8" || test_name == "yolonas") ? 1.0f : preds.at<float>(i, 4) ;
float obj_conf = (model_name == "yolov8" || model_name == "yolonas" ||
model_name == "yolov9" || model_name == "yolov10") ? 1.0f : preds.at<float>(i, 4) ;
if (obj_conf < conf_threshold)
continue;
Mat scores = preds.row(i).colRange((test_name == "yolov8" || test_name == "yolonas") ? 4 : 5, preds.cols);
Mat scores = preds.row(i).colRange((model_name == "yolov8" || model_name == "yolonas" || model_name == "yolov9" || model_name == "yolov10") ? 4 : 5, preds.cols);
double conf;
Point maxLoc;
minMaxLoc(scores, 0, &conf, 0, &maxLoc);
conf = (test_name == "yolov8" || test_name == "yolonas") ? conf : conf * obj_conf;
conf = (model_name == "yolov8" || model_name == "yolonas" || model_name == "yolov9" || model_name == "yolov10") ? conf : conf * obj_conf;
if (conf < conf_threshold)
continue;
@@ -161,7 +170,7 @@ void yoloPostProcessing(
double h = det[3];
// [x1, y1, x2, y2]
if (test_name == "yolonas"){
if (model_name == "yolonas" || model_name == "yolov10"){
boxes.push_back(Rect2d(cx, cy, w, h));
} else {
boxes.push_back(Rect2d(cx - 0.5 * w, cy - 0.5 * h,
@@ -203,6 +212,7 @@ int main(int argc, char** argv)
// if model is default, use findFile to get the full path otherwise use the given path
std::string weightPath = findFile(parser.get<String>("model"));
std::string yolo_model = parser.get<String>("yolo");
int nc = parser.get<int>("nc");
float confThreshold = parser.get<float>("thr");
float nmsThreshold = parser.get<float>("nms");
@@ -219,6 +229,7 @@ int main(int argc, char** argv)
// check if yolo model is valid
if (yolo_model != "yolov5" && yolo_model != "yolov6"
&& yolo_model != "yolov7" && yolo_model != "yolov8"
&& yolo_model != "yolov10" && yolo_model !="yolov9"
&& yolo_model != "yolox" && yolo_model != "yolonas")
CV_Error(Error::StsError, "Invalid yolo model: " + yolo_model);
@@ -331,7 +342,8 @@ int main(int argc, char** argv)
yoloPostProcessing(
outs, keep_classIds, keep_confidences, keep_boxes,
confThreshold, nmsThreshold,
yolo_model);
yolo_model,
nc);
//![postprocess]
// covert Rect2d to Rect
samples/opengl/CMakeLists.txt
+10
View File
@@ -6,6 +6,9 @@ if(UNIX)
find_package(X11 QUIET)
endif()
find_package(PkgConfig QUIET)
pkg_search_module(EPOXY QUIET epoxy)
SET(OPENCV_OPENGL_SAMPLES_REQUIRED_DEPS
opencv_core
opencv_imgproc
@@ -22,6 +25,9 @@ if(BUILD_EXAMPLES AND OCV_DEPENDENCIES_FOUND)
if(NOT X11_FOUND)
ocv_list_filterout(all_samples "opengl_interop")
endif()
if(NOT EPOXY_FOUND)
ocv_list_filterout(all_samples "opengl3_2")
endif()
foreach(sample_filename ${all_samples})
ocv_define_sample(tgt ${sample_filename} opengl)
ocv_target_link_libraries(${tgt} PRIVATE "${OPENGL_LIBRARIES}" "${OPENCV_OPENGL_SAMPLES_REQUIRED_DEPS}")
@@ -29,6 +35,10 @@ if(BUILD_EXAMPLES AND OCV_DEPENDENCIES_FOUND)
ocv_target_link_libraries(${tgt} PRIVATE ${X11_LIBRARIES})
ocv_target_include_directories(${tgt} ${X11_INCLUDE_DIR})
endif()
if(sample_filename STREQUAL "opengl3_2.cpp")
ocv_target_link_libraries(${tgt} PRIVATE ${EPOXY_LIBRARIES})
ocv_target_include_directories(${tgt} PRIVATE ${EPOXY_INCLUDE_DIRS})
endif()
endforeach()
endif()
samples/opengl/opengl3_2.cpp
+169
View File
@@ -0,0 +1,169 @@
#include <iostream>
#include <epoxy/gl.h>
#ifdef _WIN32
#define WIN32_LEAN_AND_MEAN 1
#define NOMINMAX 1
#include <windows.h>
#endif
#if defined(__APPLE__)
#include <OpenGL/gl.h>
#include <OpenGL/glu.h>
#else
#include <GL/gl.h>
#include <GL/glu.h>
#endif
#include "opencv2/core.hpp"
#include "opencv2/core/opengl.hpp"
#include "opencv2/core/cuda.hpp"
#include "opencv2/highgui.hpp"
using namespace std;
using namespace cv;
using namespace cv::cuda;
const int win_width = 800;
const int win_height = 640;
struct DrawData
{
GLuint vao, vbo, program, textureID;
};
static cv::Mat rot(float angle)
{
cv::Mat R_y = (cv::Mat_<float>(4,4) <<
cos(angle), 0, sin(angle), 0,
0, 1, 0, 0,
-sin(angle), 0, cos(angle), 0,
0, 0, 0, 1);
return R_y;
}
static GLuint create_shader(const char* source, GLenum type) {
GLuint shader = glCreateShader(type);
glShaderSource(shader, 1, &source, NULL);
glCompileShader(shader);
return shader;
}
static void draw(void* userdata) {
DrawData* data = static_cast<DrawData*>(userdata);
static float angle = 0.0f;
angle += 1.f;
cv::Mat trans = rot(CV_PI * angle / 360.f);
glClearColor(0.0, 0.0, 0.0, 1.0);
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
glUseProgram(data->program);
glUniformMatrix4fv(glGetUniformLocation(data->program, "transform"), 1, GL_FALSE, trans.ptr<float>());
glBindTexture(GL_TEXTURE_2D, data->textureID);
glBindVertexArray(data->vao);
glDrawArrays(GL_TRIANGLE_STRIP, 0, 4);
glBindVertexArray(0);
}
int main(int argc, char* argv[])
{
string filename;
if (argc < 2)
{
cout << "Usage: " << argv[0] << " image" << endl;
filename = "baboon.jpg";
}
else
filename = argv[1];
Mat img = imread(samples::findFile(filename));
if (img.empty())
{
cerr << "Can't open image " << filename << endl;
return -1;
}
flip(img, img, 0);
namedWindow("OpenGL", WINDOW_OPENGL);
resizeWindow("OpenGL", win_width, win_height);
DrawData data;
glEnable(GL_DEPTH_TEST);
const char *vertex_shader_source =
"#version 330 core\n"
"layout (location = 0) in vec3 position;\n"
"layout (location = 1) in vec2 texCoord;\n"
"out vec2 TexCoord;\n"
"uniform mat4 transform;\n"
"void main() {\n"
" gl_Position = transform * vec4(position, 1.0);\n"
" TexCoord = texCoord;\n"
"}\n";
const char *fragment_shader_source =
"#version 330 core\n"
"in vec2 TexCoord;\n"
"out vec4 color;\n"
"uniform sampler2D ourTexture;\n"
"void main() {\n"
" color = texture(ourTexture, TexCoord);\n"
"}\n";
data.program = glCreateProgram();
GLuint vertex_shader = create_shader(vertex_shader_source, GL_VERTEX_SHADER);
GLuint fragment_shader = create_shader(fragment_shader_source, GL_FRAGMENT_SHADER);
glAttachShader(data.program, vertex_shader);
glAttachShader(data.program, fragment_shader);
glLinkProgram(data.program);
glUseProgram(data.program);
GLfloat vertices[] = {
// Positions // Texture Coords
1.0f, 1.0f, 0.0f, 1.0f, 1.0f, // Top Right
1.0f, -1.0f, 0.0f, 1.0f, 0.0f, // Bottom Right
-1.0f, 1.0f, 0.0f, 0.0f, 1.0f, // Top Left
-1.0f, -1.0f, 0.0f, 0.0f, 0.0f // Bottom Left
};
glGenVertexArrays(1, &data.vao);
glGenBuffers(1, &data.vbo);
glBindVertexArray(data.vao);
glBindBuffer(GL_ARRAY_BUFFER, data.vbo);
glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW);
// Position attribute
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 5 * sizeof(GLfloat), (GLvoid*)0);
glEnableVertexAttribArray(0);
// Texture Coord attribute
glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, 5 * sizeof(GLfloat), (GLvoid*)(3 * sizeof(GLfloat)));
glEnableVertexAttribArray(1);
glBindVertexArray(0); // Unbind VAO
// Image to texture
glGenTextures(1, &data.textureID);
glBindTexture(GL_TEXTURE_2D, data.textureID);
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGB, img.cols, img.rows, 0, GL_BGR, GL_UNSIGNED_BYTE, img.data);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
glBindTexture(GL_TEXTURE_2D, 0);
setOpenGlDrawCallback("OpenGL", draw, &data);
for (;;)
{
updateWindow("OpenGL");
char key = (char)waitKey(40);
if (key == 27)
break;
}
setOpenGlDrawCallback("OpenGL", 0, 0);
destroyAllWindows();
return 0;
}