如何在高維Mat：Class中使用C++讀取特定座標處的數據？

Question

我正嘗試在OpenCV中使用MobileNet SSD +深度神經網絡（dnn）模塊進行對象檢測。我成功加載並使用了模型。作爲net.forward的輸出，我獲得了包含關於檢測到的對象的信息的Mat對象。不幸的是，我在與「易於工作的一部分」鬥爭，閱讀究竟是什麼被發現。

這是我知道的輸出墊目標信息：

• 它有4種尺寸。
• 的大小是1×1×number_of_objects_detected X 7.
• 七條關於每個對象的信息的有：第一是類ID，所述第二是信心，所述第三-第七是邊界框的值。

我找不到任何C++的例子，但我發現了很多python的例子。他們讀取這樣的數據：

for i in np.arange(0, detections.shape[2]):  
    confidence = detections[0, 0, i, 2] 

如何在C++中做到這一點最簡單的方法是什麼？即我需要讀取高維Mat：class中特定座標的數據。

謝謝你的幫助。我在C++中很新，有時會發現它壓倒性的...

我正在使用OpenCV 3.3.0。我正在使用MobileNet SSD的GitHub：https://github.com/chuanqi305/MobileNet-SSD。

我的程序的代碼：

#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(); 

} 

Answer 1

檢查出how to scan images官方OpenCV的教程。

你訪問將使用3信道（即顏色）Mat方式Mat類，它在很大程度上重載各種訪問選項的Mat::at()方法的正常方式。具體而言，您可以發送array of indices或vector of indices。

---

這裏有一個最簡單的例子創建一個4D Mat和訪問特定的元素：

#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 

Answer 2

有人可能會發現在使用MobileNet SSD的背景下，這個問題+ OpenCV中的深度神經網絡（dnn）模塊用於對象檢測。所以在這裏我發佈了已經實現的對象檢測代碼。亞歷山大雷諾茲感謝你的幫助。

#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(); 

}