c++如何读取高维Mat:class中特定坐标的数据?
How to read data at the specific coordinates in high-dimensional Mat:class using c++?
我正在尝试使用 OpenCV 中的 MobileNet SSD + 深度神经网络 ( dnn ) 模块进行对象检测。我成功加载并使用了该模型。作为 net.forward 的输出,我获得了 Mat 对象,其中包含有关检测到的对象的信息。不幸的是,我在阅读检测到的内容时遇到了 "the easy part of work"。
这是我知道的关于输出 Mat 对象的信息:
- 它有 4 个维度。
- 尺寸为 1 x 1 x number_of_objects_detected x 7。
- 每个对象的七项信息是:第一项是 class ID,第二项是置信度,第三到第七项是边界框值。
我找不到任何 C++ 示例,但我找到了很多 python 示例。他们这样读取数据:
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
在 C++ 中执行此操作的最简单方法是什么? IE。我需要读取高维特定坐标的数据 Mat:class.
感谢您的热心帮助。我是 c++ 的新手,有时发现它不知所措...
我正在使用 OpenCV 3.3.0。我使用的 MobileNet SSD GitHub:https://github.com/chuanqi305/MobileNet-SSD.
我的程序代码:
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <fstream>
#include <iostream>
using namespace cv;
using namespace cv::dnn;
using namespace std;
// function to create vector of class names
std::vector<String> createClaseNames() {
std::vector<String> classNames;
classNames.push_back("background");
classNames.push_back("aeroplane");
classNames.push_back("bicycle");
classNames.push_back("bird");
classNames.push_back("boat");
classNames.push_back("bottle");
classNames.push_back("bus");
classNames.push_back("car");
classNames.push_back("cat");
classNames.push_back("chair");
classNames.push_back("cow");
classNames.push_back("diningtable");
classNames.push_back("dog");
classNames.push_back("horse");
classNames.push_back("motorbike");
classNames.push_back("person");
classNames.push_back("pottedplant");
classNames.push_back("sheep");
classNames.push_back("sofa");
classNames.push_back("train");
classNames.push_back("tvmonitor");
return classNames;
}
// main function
int main(int argc, char **argv)
{
// set inputs
String modelTxt = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/python/object-detection-deep-learning/MobileNetSSD_deploy.prototxt";
String modelBin = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/python/object-detection-deep-learning/MobileNetSSD_deploy.caffemodel";
String imageFile = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/puppies.jpg";
std::vector<String> classNames = createClaseNames();
//read caffe model
Net net;
try {
net = dnn::readNetFromCaffe(modelTxt, modelBin);
}
catch (cv::Exception& e) {
std::cerr << "Exception: " << e.what() << std::endl;
if (net.empty())
{
std::cerr << "Can't load network." << std::endl;
exit(-1);
}
}
// read image
Mat img = imread(imageFile);
// create input blob
resize(img, img, Size(300, 300));
Mat inputBlob = blobFromImage(img, 0.007843, Size(300, 300), Scalar(127.5)); //Convert Mat to dnn::Blob image batch
// apply the blob on the input layer
net.setInput(inputBlob); //set the network input
// classify the image by applying the blob on the net
Mat detections = net.forward("detection_out"); //compute output
// print some information about detections
std::cout << "dims: " << detections.dims << endl;
std::cout << "size: " << detections.size << endl;
//show image
String winName("image");
imshow(winName, img);
// Wait for keypress
waitKey();
}
查看 how to scan images 上的官方 OpenCV 教程。
您访问 3 通道(即颜色)Mat
的正常方式是使用 Mat::at()
method of the Mat
class, which is heavily overloaded for all sorts of accessor options. Specifically, you can send in an array of indices or a vector of indices.
这是创建 4D Mat
和访问特定元素的最基本示例:
#include <opencv2/opencv.hpp>
#include <iostream>
int main() {
int size[4] = { 2, 2, 5, 7 };
cv::Mat M(4, size, CV_32FC1, cv::Scalar(1));
int indx[4] = { 0, 0, 2, 3 };
std::cout << "M[0, 0, 2, 3] = " << M.at<float>(indx) << std::endl;
}
M[0, 0, 2, 3] = 1
有人可能会在使用 OpenCV 中的 MobileNet SSD + 深度神经网络 ( dnn ) 模块进行对象检测的上下文中发现这个问题。所以这里我 post 对象检测的功能代码。 Alexander Reynolds 感谢您的帮助。
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <fstream>
#include <iostream>
using namespace cv;
using namespace cv::dnn;
using namespace std;
// function to create vector of class names
std::vector<String> createClaseNames() {
std::vector<String> classNames;
classNames.push_back("background");
classNames.push_back("aeroplane");
classNames.push_back("bicycle");
classNames.push_back("bird");
classNames.push_back("boat");
classNames.push_back("bottle");
classNames.push_back("bus");
classNames.push_back("car");
classNames.push_back("cat");
classNames.push_back("chair");
classNames.push_back("cow");
classNames.push_back("diningtable");
classNames.push_back("dog");
classNames.push_back("horse");
classNames.push_back("motorbike");
classNames.push_back("person");
classNames.push_back("pottedplant");
classNames.push_back("sheep");
classNames.push_back("sofa");
classNames.push_back("train");
classNames.push_back("tvmonitor");
return classNames;
}
// main function
int main(int argc, char **argv)
{
// set inputs
String modelTxt = "Path to MobileNetSSD_deploy.prototxt";
String modelBin = "Path to MobileNetSSD_deploy.caffemodel";
String imageFile = "Path to test image";
std::vector<String> classNames = createClaseNames();
//read caffe model
Net net;
try {
net = dnn::readNetFromCaffe(modelTxt, modelBin);
}
catch (cv::Exception& e) {
std::cerr << "Exception: " << e.what() << std::endl;
if (net.empty())
{
std::cerr << "Can't load network." << std::endl;
exit(-1);
}
}
// read image
Mat img = imread(imageFile);
Size imgSize = img.size();
// create input blob
Mat img300;
resize(img, img300, Size(300, 300));
Mat inputBlob = blobFromImage(img300, 0.007843, Size(300, 300), Scalar(127.5)); //Convert Mat to dnn::Blob image batch
// apply the blob on the input layer
net.setInput(inputBlob); //set the network input
// classify the image by applying the blob on the net
Mat detections = net.forward("detection_out"); //compute output
// look what the detector found
for (int i=0; i < detections.size[2]; i++) {
// print information into console
cout << "-----------------" << endl;
cout << "Object nr. " << i + 1 << endl;
// detected class
int indxCls[4] = { 0, 0, i, 1 };
int cls = detections.at<float>(indxCls);
std::cout << "class: " << classNames[cls] << endl;
// confidence
int indxCnf[4] = { 0, 0, i, 2 };
float cnf = detections.at<float>(indxCnf);
std::cout << "confidence: " << cnf * 100 << "%" << endl;
// bounding box
int indxBx[4] = { 0, 0, i, 3 };
int indxBy[4] = { 0, 0, i, 4 };
int indxBw[4] = { 0, 0, i, 5 };
int indxBh[4] = { 0, 0, i, 6 };
int Bx = detections.at<float>(indxBx) * imgSize.width;
int By = detections.at<float>(indxBy) * imgSize.height;
int Bw = detections.at<float>(indxBw) * imgSize.width - Bx;
int Bh = detections.at<float>(indxBh) * imgSize.height - By;
std::cout << "bounding box [x, y, w, h]: " << Bx << ", " << By << ", " << Bw << ", " << Bh << endl;
// draw bounding box to image
Rect bbox(Bx, By, Bw, Bh);
rectangle(img, bbox, Scalar(255,0,255),1,8,0);
}
//show image
String winName("image");
imshow(winName, img);
// Wait for keypress
waitKey();
}
我正在尝试使用 OpenCV 中的 MobileNet SSD + 深度神经网络 ( dnn ) 模块进行对象检测。我成功加载并使用了该模型。作为 net.forward 的输出,我获得了 Mat 对象,其中包含有关检测到的对象的信息。不幸的是,我在阅读检测到的内容时遇到了 "the easy part of work"。
这是我知道的关于输出 Mat 对象的信息:
- 它有 4 个维度。
- 尺寸为 1 x 1 x number_of_objects_detected x 7。
- 每个对象的七项信息是:第一项是 class ID,第二项是置信度,第三到第七项是边界框值。
我找不到任何 C++ 示例,但我找到了很多 python 示例。他们这样读取数据:
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
在 C++ 中执行此操作的最简单方法是什么? IE。我需要读取高维特定坐标的数据 Mat:class.
感谢您的热心帮助。我是 c++ 的新手,有时发现它不知所措...
我正在使用 OpenCV 3.3.0。我使用的 MobileNet SSD GitHub:https://github.com/chuanqi305/MobileNet-SSD.
我的程序代码:
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <fstream>
#include <iostream>
using namespace cv;
using namespace cv::dnn;
using namespace std;
// function to create vector of class names
std::vector<String> createClaseNames() {
std::vector<String> classNames;
classNames.push_back("background");
classNames.push_back("aeroplane");
classNames.push_back("bicycle");
classNames.push_back("bird");
classNames.push_back("boat");
classNames.push_back("bottle");
classNames.push_back("bus");
classNames.push_back("car");
classNames.push_back("cat");
classNames.push_back("chair");
classNames.push_back("cow");
classNames.push_back("diningtable");
classNames.push_back("dog");
classNames.push_back("horse");
classNames.push_back("motorbike");
classNames.push_back("person");
classNames.push_back("pottedplant");
classNames.push_back("sheep");
classNames.push_back("sofa");
classNames.push_back("train");
classNames.push_back("tvmonitor");
return classNames;
}
// main function
int main(int argc, char **argv)
{
// set inputs
String modelTxt = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/python/object-detection-deep-learning/MobileNetSSD_deploy.prototxt";
String modelBin = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/python/object-detection-deep-learning/MobileNetSSD_deploy.caffemodel";
String imageFile = "C:/Users/acer/Desktop/kurz_OCV/cv4faces/project/puppies.jpg";
std::vector<String> classNames = createClaseNames();
//read caffe model
Net net;
try {
net = dnn::readNetFromCaffe(modelTxt, modelBin);
}
catch (cv::Exception& e) {
std::cerr << "Exception: " << e.what() << std::endl;
if (net.empty())
{
std::cerr << "Can't load network." << std::endl;
exit(-1);
}
}
// read image
Mat img = imread(imageFile);
// create input blob
resize(img, img, Size(300, 300));
Mat inputBlob = blobFromImage(img, 0.007843, Size(300, 300), Scalar(127.5)); //Convert Mat to dnn::Blob image batch
// apply the blob on the input layer
net.setInput(inputBlob); //set the network input
// classify the image by applying the blob on the net
Mat detections = net.forward("detection_out"); //compute output
// print some information about detections
std::cout << "dims: " << detections.dims << endl;
std::cout << "size: " << detections.size << endl;
//show image
String winName("image");
imshow(winName, img);
// Wait for keypress
waitKey();
}
查看 how to scan images 上的官方 OpenCV 教程。
您访问 3 通道(即颜色)Mat
的正常方式是使用 Mat::at()
method of the Mat
class, which is heavily overloaded for all sorts of accessor options. Specifically, you can send in an array of indices or a vector of indices.
这是创建 4D Mat
和访问特定元素的最基本示例:
#include <opencv2/opencv.hpp>
#include <iostream>
int main() {
int size[4] = { 2, 2, 5, 7 };
cv::Mat M(4, size, CV_32FC1, cv::Scalar(1));
int indx[4] = { 0, 0, 2, 3 };
std::cout << "M[0, 0, 2, 3] = " << M.at<float>(indx) << std::endl;
}
M[0, 0, 2, 3] = 1
有人可能会在使用 OpenCV 中的 MobileNet SSD + 深度神经网络 ( dnn ) 模块进行对象检测的上下文中发现这个问题。所以这里我 post 对象检测的功能代码。 Alexander Reynolds 感谢您的帮助。
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <fstream>
#include <iostream>
using namespace cv;
using namespace cv::dnn;
using namespace std;
// function to create vector of class names
std::vector<String> createClaseNames() {
std::vector<String> classNames;
classNames.push_back("background");
classNames.push_back("aeroplane");
classNames.push_back("bicycle");
classNames.push_back("bird");
classNames.push_back("boat");
classNames.push_back("bottle");
classNames.push_back("bus");
classNames.push_back("car");
classNames.push_back("cat");
classNames.push_back("chair");
classNames.push_back("cow");
classNames.push_back("diningtable");
classNames.push_back("dog");
classNames.push_back("horse");
classNames.push_back("motorbike");
classNames.push_back("person");
classNames.push_back("pottedplant");
classNames.push_back("sheep");
classNames.push_back("sofa");
classNames.push_back("train");
classNames.push_back("tvmonitor");
return classNames;
}
// main function
int main(int argc, char **argv)
{
// set inputs
String modelTxt = "Path to MobileNetSSD_deploy.prototxt";
String modelBin = "Path to MobileNetSSD_deploy.caffemodel";
String imageFile = "Path to test image";
std::vector<String> classNames = createClaseNames();
//read caffe model
Net net;
try {
net = dnn::readNetFromCaffe(modelTxt, modelBin);
}
catch (cv::Exception& e) {
std::cerr << "Exception: " << e.what() << std::endl;
if (net.empty())
{
std::cerr << "Can't load network." << std::endl;
exit(-1);
}
}
// read image
Mat img = imread(imageFile);
Size imgSize = img.size();
// create input blob
Mat img300;
resize(img, img300, Size(300, 300));
Mat inputBlob = blobFromImage(img300, 0.007843, Size(300, 300), Scalar(127.5)); //Convert Mat to dnn::Blob image batch
// apply the blob on the input layer
net.setInput(inputBlob); //set the network input
// classify the image by applying the blob on the net
Mat detections = net.forward("detection_out"); //compute output
// look what the detector found
for (int i=0; i < detections.size[2]; i++) {
// print information into console
cout << "-----------------" << endl;
cout << "Object nr. " << i + 1 << endl;
// detected class
int indxCls[4] = { 0, 0, i, 1 };
int cls = detections.at<float>(indxCls);
std::cout << "class: " << classNames[cls] << endl;
// confidence
int indxCnf[4] = { 0, 0, i, 2 };
float cnf = detections.at<float>(indxCnf);
std::cout << "confidence: " << cnf * 100 << "%" << endl;
// bounding box
int indxBx[4] = { 0, 0, i, 3 };
int indxBy[4] = { 0, 0, i, 4 };
int indxBw[4] = { 0, 0, i, 5 };
int indxBh[4] = { 0, 0, i, 6 };
int Bx = detections.at<float>(indxBx) * imgSize.width;
int By = detections.at<float>(indxBy) * imgSize.height;
int Bw = detections.at<float>(indxBw) * imgSize.width - Bx;
int Bh = detections.at<float>(indxBh) * imgSize.height - By;
std::cout << "bounding box [x, y, w, h]: " << Bx << ", " << By << ", " << Bw << ", " << Bh << endl;
// draw bounding box to image
Rect bbox(Bx, By, Bw, Bh);
rectangle(img, bbox, Scalar(255,0,255),1,8,0);
}
//show image
String winName("image");
imshow(winName, img);
// Wait for keypress
waitKey();
}