基于OpenCV的深度学习Mask-RCNN对象检测和实例分割

文章目录[隐藏]

什么是图像分割?
什么是实例分割?
Mask-RCNN是如何工作的?
基于Mask-RCNN对象检测和实例分割(c++ /Python)
参考

在这篇文章中，我们将展示如何使用一个名为Mask RCNN(基于区域的卷积神经网络)的卷积神经网络模型来进行目标检测和分割。使用mask - rcnn，我们不仅检测对象，我们还获得一个灰度或二进制mask对象。

Mask rcnn最初是在2017年11月由facebook的人工智能研究团队使用Python和caffe2推出的。

我们将在c++和Python中共享OpenCV代码来加载和使用模型。

The minimum required version of OpenCV is 3.4.3.

什么是图像分割?

在计算机视觉中，术语“图像分割”或简称“分割”是指根据某些标准将图像划分为若干像素组。您可以根据颜色、纹理或其他您决定的标准进行分组。这些组有时也被称为超像素。

什么是实例分割?

在实例分割中，目标是检测图像中的特定对象，并在感兴趣的对象周围创建一个遮罩。实例分割也可以被认为是对象检测，其中输出是一个mask，而不仅仅是一个bounding box。语义分割试图对图像中的每个像素进行分类，而实例分割的目标并不是对图像中的每个像素进行标记。

下面我们看到一个实例分割的两只羊在一个非常相似的颜色背景

在这里插入图片描述

Mask-RCNN是如何工作的?

Mask-RCNN是对R-CNN论文(由R. Girshick等人，CVPR 2014)的一系列改进的结果，用于对象检测。R-CNN基于选择性搜索生成区域推荐，然后对每个提议的区域逐个进行处理，使用卷积网络输出一个目标标签及其bounding box。

Fast R-CNN (R. Girshik, ICCV 2015)通过在他们的CNN中使用ROIPool层处理所有提议的区域，使R-CNN算法更快。

Faster R-CNN (S. Run等人，PAMI, 2017)通过使用一种称为区域建议网络(RPN)的ConvNet来执行区域建议步骤，将其进一步推进。RPN和分类以及bounding-box预测网络都是在common特征映射上工作的，因此推理速度更快。在GPU上，Faster R-CNN可以以5fps运行。

Mask R-CNN (He et al.， ICCV 2017)是对Faster RCNN的改进，包括一个与类标签平行的Mask预测分支和边界框预测分支，如下图所示。它只给Faster R-CNN网络增加了很小的开销，因此在GPU上仍然可以以5帧每秒的速度运行。

在这里插入图片描述
Mask-RCNN网络有两个主要部分。

第一个是区域提议网络，每个图像生成大约300个区域提议。在训练过程中，每个提议(roi)都经过了第二部分，即目标检测和mask预测网络，如上所示。注意，由于mask预测分支与标签和框预测分支并行运行，对于每个给定的ROI，该网络预测属于所有类的mask。

推理时对区域建议进行非最大抑制，mask预测分支只处理得分最高的100个检测框。因此，对于100个roi区域和90个目标，网络的mask预测部分输出大小为100x90x15x15的4D张量，其中每个mask的大小为15×15。

基于Mask-RCNN对象检测和实例分割(c++ /Python)

现在让我们看看如何使用OpenCV运行Mask-RCNN。

第一步:下载模型
下载tensorflow模型到当前的工作目录,下载完成后，我们提取模型文件frozen_inference_graph.pb得到模型的权重。

wget http://download.tensorflow.org/models/object_detection/mask_rcnn_inception_v2_coco_2018_01_28.tar.gz
tar zxvf mask_rcnn_inception_v2_coco_2018_01_28.tar.gz

步骤2:初始化参数
Mask-RCNN算法产生预测的检测输出作为bounding boxes。每个bounding box都与一个置信分数相关联。置信度阈值参数以下的所有框将被忽略以进行进一步处理。

Python

# Initialize the parameters
confThreshold = 0.5  #Confidence threshold
maskThreshold = 0.3  # Mask threshold

C++

// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float maskThreshold = 0.3; // Mask threshold

步骤3:加载模型和类
mscoco_labels.names文件包含模型为之训练的所有对象。我们读取类名。然后我们读取并加载colors.txt文件，该文件包含了所有用于mask对象的颜色。

接下来，我们使用这两个文件加载网络

frozen_inference_graph.pb :预备训练的权重。
mask_rcnn_inception_v2_coco_2018_01_28.ppbtxt:由OpenCV的DNN支持组调优的文本图形文件，以便使用OpenCV加载网络。

我们在这里将DNN backend设置为OpenCV，处理器设置为CPU。您可以尝试将首选目标设置为cv.dnn。DNN_TARGET_OPENCL在GPU上运行。但请记住，当前OpenCV版本的DNN模块仅在英特尔的gpu上进行过测试。

Python

# Load names of classes
classesFile = "mscoco_labels.names";
classes = None
with open(classesFile, 'rt') as f:
   classes = f.read().rstrip('\n').split('\n')

# Load the colors
colorsFile = "colors.txt";
with open(colorsFile, 'rt') as f:
    colorsStr = f.read().rstrip('\n').split('\n')
colors = []
for i in range(len(colorsStr)):
    rgb = colorsStr[i].split(' ')
    color = np.array([float(rgb[0]), float(rgb[1]), float(rgb[2])])
    colors.append(color)

# Give the textGraph and weight files for the model
textGraph = "./mask_rcnn_inception_v2_coco_2018_01_28.pbtxt";
modelWeights = "./mask_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb";

# Load the network
net = cv.dnn.readNetFromTensorflow(modelWeights, textGraph);
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)

C++

// Load names of classes
string classesFile = "mscoco_labels.names";
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);

// Load the colors
vector<Scalar> colors;
string colorsFile = "colors.txt";
ifstream colorFptr(colorsFile.c_str());
while (getline(colorFptr, line)) {
    char* pEnd;
    double r, g, b;
    r = strtod (line.c_str(), &pEnd);
    g = strtod (pEnd, NULL);
    b = strtod (pEnd, NULL);
    colors.push_back(Scalar(r, g, b, 255.0));
}

// Give the configuration and weight files for the model
String textGraph = "./mask_rcnn_inception_v2_coco_2018_01_28.pbtxt";
String modelWeights = "./mask_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb";

// Load the network
Net net = readNetFromTensorflow(modelWeights, textGraph);
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setPreferableTarget(DNN_TARGET_CPU);

Step 4 : Read the input
在这个步骤中，我们读取图像、视频流或网络摄像头。此外，我们保存检测到带有bounding box的帧。

Python

outputFile = "mask_rcnn_out_py.avi"
if (args.image):
    # Open the image file
    if not os.path.isfile(args.image):
        print("Input image file ", args.image, " doesn't exist")
        sys.exit(1)
    cap = cv.VideoCapture(args.image)
    outputFile = args.image[:-4]+'_mask_rcnn_out_py.jpg'
elif (args.video):
    # Open the video file
    if not os.path.isfile(args.video):
        print("Input video file ", args.video, " doesn't exist")
        sys.exit(1)
    cap = cv.VideoCapture(args.video)
    outputFile = args.video[:-4]+'_mask_rcnn_out_py.avi'
else:
    # Webcam input
    cap = cv.VideoCapture(0)

# Get the video writer initialized to save the output video
if (not args.image):
    vid_writer = cv.VideoWriter(outputFile, cv.VideoWriter_fourcc('M','J','P','G'), 28, (round(cap.get(cv.CAP_PROP_FRAME_WIDTH)),round(cap.get(cv.CAP_PROP_FRAME_HEIGHT))))

C++

outputFile = "mask_rcnn_out_cpp.avi";
if (parser.has("image"))
{
    // Open the image file
    str = parser.get<String>("image");
    ifstream ifile(str);
    if (!ifile) throw("error");
    cap.open(str);
    str.replace(str.end()-4, str.end(), "_mask_rcnn_out.jpg");
    outputFile = str;
}
else if (parser.has("video"))
{
    // Open the video file
    str = parser.get<String>("video");
    ifstream ifile(str);
    if (!ifile) throw("error");
    cap.open(str);
    str.replace(str.end()-4, str.end(), "_mask_rcnn_out.avi");
    outputFile = str;
}
// Open the webcam
else cap.open(parser.get<int>("device"));

// Get the video writer initialized to save the output video
if (!parser.has("image")) {
   video.open(outputFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH),          cap.get(CAP_PROP_FRAME_HEIGHT)));
}

Step 4 : Process each frame
输入到神经网络的图像需要采用一种称为blob的特定格式。

从输入图像或视频流读取帧后，通过blobFromImage函数将其转换为用于神经网络的输入blob格式。在这个过程中，它以原始大小接收输入图像帧，并将swapRGB参数设置为true。

然后将blob作为输入传入网络，并运行一个前向传递，从网络中名为“detection_out_final”和“detection_masks”的输出层中获得一列预测的bounding boxes和目标mask。这些bounding boxes经过后期处理步骤，并过滤掉可信度低bounding boxes。我们将在下一节中更详细地介绍后期处理步骤。每一帧的推理时间打印在左上角。带有最终边界框和相应mask的图像然后保存到磁盘。

Python

while cv.waitKey(1) < 0:

    # Get frame from the video
    hasFrame, frame = cap.read()

    # Stop the program if reached end of video
    if not hasFrame:
        print("Done processing !!!")
        print("Output file is stored as ", outputFile)
        cv.waitKey(3000)
        break

    # Create a 4D blob from a frame.
    blob = cv.dnn.blobFromImage(frame, swapRB=True, crop=False)

    # Set the input to the network
    net.setInput(blob)

    # Run the forward pass to get output from the output layers
    boxes, masks = net.forward(['detection_out_final', 'detection_masks'])

    # Extract the bounding box and mask for each of the detected objects
    postprocess(boxes, masks)

    # Put efficiency information.
    t, _ = net.getPerfProfile()
    label = 'Mask-RCNN : Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
    cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    # Write the frame with the detection boxes
    if (args.image):
        cv.imwrite(outputFile, frame.astype(np.uint8));
    else:
        vid_writer.write(frame.astype(np.uint8))

    cv.imshow(winName, frame)

C++

// Process frames.
while (waitKey(1) < 0)
{
    // get frame from the video
    cap >> frame;

    // Stop the program if reached end of video
    if (frame.empty()) {
        cout << "Done processing !!!" << endl;
        cout << "Output file is stored as " << outputFile << endl;
        waitKey(3000);
        break;
    }
    // Create a 4D blob from a frame.
     blobFromImage(frame, blob, 1.0, Size(frame.cols, frame.rows), Scalar(), true, false);

    //Sets the input to the network
    net.setInput(blob);

    // Runs the forward pass to get output from the output layers
    std::vector<String> outNames(2);
    outNames[0] = "detection_out_final";
    outNames[1] = "detection_masks";
    vector<Mat> outs;
    net.forward(outs, outNames);

    // Extract the bounding box and mask for each of the detected objects
    postprocess(frame, outs);

    // Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
    vector<double> layersTimes;
    double freq = getTickFrequency() / 1000;
    double t = net.getPerfProfile(layersTimes) / freq;
    string label = format("Mask-RCNN : Inference time for a frame : %.2f ms", t);
    putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0));

    // Write the frame with the detection boxes
    Mat detectedFrame;
    frame.convertTo(detectedFrame, CV_8U);
    if (parser.has("image")) imwrite(outputFile, detectedFrame);
    else video.write(detectedFrame);

    imshow(kWinName, frame);
}

现在，让我们详细讨论一下上面使用的一些后处理函数。

步骤4a:对网络的输出进行后处理
网络的输出mask对象是一个四维对象，其中第一维表示帧中检测到的bounding boxed的数量，第二维表示模型中类的数量，第三维和第四维表示我们示例中的掩码形状(15×15)。

如果一个框的置信度小于给定的阈值，则丢弃该边界框，不考虑进行进一步处理。

Python

# For each frame, extract the bounding box and mask for each detected object
def postprocess(boxes, masks):
    # Output size of masks is NxCxHxW where
    # N - number of detected boxes
    # C - number of classes (excluding background)
    # HxW - segmentation shape
    numClasses = masks.shape[1]
    numDetections = boxes.shape[2]

    frameH = frame.shape[0]
    frameW = frame.shape[1]

    for i in range(numDetections):
        box = boxes[0, 0, i]
        mask = masks[i]
        score = box[2]
        if score > confThreshold:
            classId = int(box[1])

            # Extract the bounding box
            left = int(frameW * box[3])
            top = int(frameH * box[4])
            right = int(frameW * box[5])
            bottom = int(frameH * box[6])

            left = max(0, min(left, frameW - 1))
            top = max(0, min(top, frameH - 1))
            right = max(0, min(right, frameW - 1))
            bottom = max(0, min(bottom, frameH - 1))

            # Extract the mask for the object
            classMask = mask[classId]

            # Draw bounding box, colorize and show the mask on the image
            drawBox(frame, classId, score, left, top, right, bottom, classMask)

C++

// For each frame, extract the bounding box and mask for each detected object
void postprocess(Mat& frame, const vector<Mat>& outs)
{
    Mat outDetections = outs[0];
    Mat outMasks = outs[1];

    // Output size of masks is NxCxHxW where
    // N - number of detected boxes
    // C - number of classes (excluding background)
    // HxW - segmentation shape
    const int numDetections = outDetections.size[2];
    const int numClasses = outMasks.size[1];

    outDetections = outDetections.reshape(1, outDetections.total() / 7);
    for (int i = 0; i < numDetections; ++i)
    {
        float score = outDetections.at<float>(i, 2);
        if (score > confThreshold)
        {
            // Extract the bounding box
            int classId = static_cast<int>(outDetections.at<float>(i, 1));
            int left = static_cast<int>(frame.cols * outDetections.at<float>(i, 3));
            int top = static_cast<int>(frame.rows * outDetections.at<float>(i, 4));
            int right = static_cast<int>(frame.cols * outDetections.at<float>(i, 5));
            int bottom = static_cast<int>(frame.rows * outDetections.at<float>(i, 6));

            left = max(0, min(left, frame.cols - 1));
            top = max(0, min(top, frame.rows - 1));
            right = max(0, min(right, frame.cols - 1));
            bottom = max(0, min(bottom, frame.rows - 1));
            Rect box = Rect(left, top, right - left + 1, bottom - top + 1);

            // Extract the mask for the object
            Mat objectMask(outMasks.size[2], outMasks.size[3],CV_32F, outMasks.ptr<float>(i,classId));

            // Draw bounding box, colorize and show the mask on the image
            drawBox(frame, classId, score, box, objectMask);

        }
    }
}

步骤4c:绘制预测框
最后，我们在输入帧上绘制经过后处理步骤过滤的框，它们带有指定的类标签和置信度分数。我们也覆盖了彩色mask及他轮廓在bounding box里。在这段代码中，我们为属于同一类的所有对象使用了相同的颜色，但您也可以为不同的实例使用不同的颜色。

Python

# Draw the predicted bounding box, colorize and show the mask on the image
def drawBox(frame, classId, conf, left, top, right, bottom, classMask):
    # Draw a bounding box.
    cv.rectangle(frame, (left, top), (right, bottom), (255, 178, 50), 3)

    # Print a label of class.
    label = '%.2f' % conf
    if classes:
        assert(classId < len(classes))
        label = '%s:%s' % (classes[classId], label)

    # Display the label at the top of the bounding box
    labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
    top = max(top, labelSize[1])
    cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
    cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 1)

    # Resize the mask, threshold, color and apply it on the image
    classMask = cv.resize(classMask, (right - left + 1, bottom - top + 1))
    mask = (classMask > maskThreshold)
    roi = frame[top:bottom+1, left:right+1][mask]

    color = colors[classId%len(colors)]
    # Comment the above line and uncomment the two lines below to generate different instance colors
    #colorIndex = random.randint(0, len(colors)-1)
    #color = colors[colorIndex]

    frame[top:bottom+1, left:right+1][mask] = ([0.3*color[0], 0.3*color[1], 0.3*color[2]] + 0.7 * roi).astype(np.uint8)

    # Draw the contours on the image
    mask = mask.astype(np.uint8)
    im2, contours, hierarchy = cv.findContours(mask,cv.RETR_TREE,cv.CHAIN_APPROX_SIMPLE)
    cv.drawContours(frame[top:bottom+1, left:right+1], contours, -1, color, 3, cv.LINE_8, hierarchy, 100)

C++

// Draw the predicted bounding box, colorize and show the mask on the image
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask)
{
    //Draw a rectangle displaying the bounding box
    rectangle(frame, Point(box.x, box.y), Point(box.x+box.width, box.y+box.height), Scalar(255, 178, 50), 3);

    //Get the label for the class name and its confidence
    string label = format("%.2f", conf);
    if (!classes.empty())
    {
        CV_Assert(classId < (int)classes.size());
        label = classes[classId] + ":" + label;
    }

    //Display the label at the top of the bounding box
    int baseLine;
    Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
    box.y = max(box.y, labelSize.height);
    rectangle(frame, Point(box.x, box.y - round(1.5*labelSize.height)), Point(box.x + round(1.5*labelSize.width), box.y + baseLine), Scalar(255, 255, 255), FILLED);
    putText(frame, label, Point(box.x, box.y), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1);

    Scalar color = colors[classId%colors.size()];
    // Comment the above line and uncomment the two lines below to generate different instance colors
    //int colorInd = rand() % colors.size();
    //Scalar color = colors[colorInd];

    // Resize the mask, threshold, color and apply it on the image
    resize(objectMask, objectMask, Size(box.width, box.height));
    Mat mask = (objectMask > maskThreshold);
    Mat coloredRoi = (0.3 * color + 0.7 * frame(box));
    coloredRoi.convertTo(coloredRoi, CV_8UC3);

    // Draw the contours on the image
    vector<Mat> contours;
    Mat hierarchy;
    mask.convertTo(mask, CV_8U);
    findContours(mask, contours, hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);
    drawContours(coloredRoi, contours, -1, color, 5, LINE_8, hierarchy, 100);
    coloredRoi.copyTo(frame(box), mask);
}

C++完整代码

// Copyright (C) 2018-2019, BigVision LLC (LearnOpenCV.com), All Rights Reserved. 
// Author : Sunita Nayak
// Article : https://www.learnopencv.com/deep-learning-based-object-detection-and-instance-segmentation-using-mask-r-cnn-in-opencv-python-c/
// License: BSD-3-Clause-Attribution (Please read the license file.)

// Usage example:  ./mask_rcnn.out --video=run.mp4
//                 ./mask_rcnn.out --image=bird.jpg
#include <fstream>
#include <sstream>
#include <iostream>
#include <string.h>

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>

const char* keys =
"{help h usage ? | | Usage examples: \n\t\t./mask-rcnn.out --image=traffic.jpg \n\t\t./mask-rcnn.out --video=sample.mp4}"
"{image i        |<none>| input image   }"
"{video v       |<none>| input video   }"
"{device d       |<none>| device }"
;
using namespace cv;
using namespace dnn;
using namespace std;

// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float maskThreshold = 0.3; // Mask threshold

vector<string> classes;
vector<Scalar> colors;

// Draw the predicted bounding box
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask);

// Postprocess the neural network's output for each frame
void postprocess(Mat& frame, const vector<Mat>& outs);

int main(int argc, char** argv)
{
    CommandLineParser parser(argc, argv, keys);
    parser.about("Use this script to run object detection using YOLO3 in OpenCV.");
    if (parser.has("help"))
    {
        parser.printMessage();
        return 0;
    }
    // Load names of classes
    string classesFile = "mscoco_labels.names";
    ifstream ifs(classesFile.c_str());
    string line;
    while (getline(ifs, line)) classes.push_back(line);

    string device = parser.get<String>("device");
    
    // Load the colors
    string colorsFile = "colors.txt";
    ifstream colorFptr(colorsFile.c_str());
    while (getline(colorFptr, line)) {
        char* pEnd;
        double r, g, b;
        r = strtod (line.c_str(), &pEnd);
        g = strtod (pEnd, NULL);
        b = strtod (pEnd, NULL);
        Scalar color = Scalar(r, g, b, 255.0);
        colors.push_back(Scalar(r, g, b, 255.0));
    }

    // Give the configuration and weight files for the model
    String textGraph = "/home/SMCV/einrj/my_projects/Cxx/DeepLearnCV/MaskRCNN/mask_rcnn_inception_v2_coco_2018_01_28.pbtxt";
    String modelWeights = "/home/SMCV/einrj/my_projects/Cxx/DeepLearnCV/MaskRCNN/mask_rcnn_inception/frozen_inference_graph.pb";

    // Load the network
    Net net = readNetFromTensorflow(modelWeights, textGraph);

    if (device == "cpu")
    {
        cout << "Using CPU device" << endl;
        net.setPreferableBackend(DNN_TARGET_CPU);
    }
    else if (device == "gpu")
    {
        cout << "Using GPU device" << endl;
        net.setPreferableBackend(DNN_BACKEND_CUDA);
        net.setPreferableTarget(DNN_TARGET_CUDA);
    }
    
    // Open a video file or an image file or a camera stream.
    string str, outputFile;
    VideoCapture cap;
    VideoWriter video;
    Mat frame, blob;
    
    try {
        
        outputFile = "mask_rcnn_out_cpp.avi";
        if (parser.has("image"))
        {
            // Open the image file
            str = parser.get<String>("image");

            cout << "Image file input : " << str << endl;
            ifstream ifile(str);
            if (!ifile) throw("error");
            cap.open(str);
            str.replace(str.end()-4, str.end(), "_mask_rcnn_out.jpg");
            outputFile = str;
        }
        else if (parser.has("video"))
        {
            // Open the video file
            str = parser.get<String>("video");
            ifstream ifile(str);
            if (!ifile) throw("error");
            cap.open(str);
            str.replace(str.end()-4, str.end(), "_mask_rcnn_out.avi");
            outputFile = str;
        }
        // Open the webcam
        else cap.open(parser.get<int>("webcam"));
        
    }
    catch(...) {
        cout << "Could not open the input image/video stream" << endl;
        return 0;
    }
    
    // Get the video writer initialized to save the output video
    if (!parser.has("image")) {
        video.open(outputFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH), cap.get(CAP_PROP_FRAME_HEIGHT)));
    }

    // Create a window
    static const string kWinName = "Deep learning object detection in OpenCV";
    namedWindow(kWinName, WINDOW_NORMAL);

    // Process frames.
    while (waitKey(1) < 0)
    {
        // get frame from the video
        cap >> frame;
        
        // Stop the program if reached end of video
        if (frame.empty()) {
            cout << "Done processing !!!" << endl;
            cout << "Output file is stored as " << outputFile << endl;
            waitKey(3000);
            break;
        }
        // Create a 4D blob from a frame.
         blobFromImage(frame, blob, 1.0, Size(frame.cols, frame.rows), Scalar(), true, false);
        //blobFromImage(frame, blob);
        
        //Sets the input to the network
        net.setInput(blob);

        // Runs the forward pass to get output from the output layers
        std::vector<String> outNames(2);
        outNames[0] = "detection_out_final";
        outNames[1] = "detection_masks";
        vector<Mat> outs;
        net.forward(outs, outNames);
        
        // Extract the bounding box and mask for each of the detected objects
        postprocess(frame, outs);
        
        // Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
        vector<double> layersTimes;
        double freq = getTickFrequency() / 1000;
        double t = net.getPerfProfile(layersTimes) / freq;
        string label = format("Mask-RCNN on 2.5 GHz Intel Core i7 CPU, Inference time for a frame : %0.0f ms", t);
        putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0));
        
        // Write the frame with the detection boxes
        Mat detectedFrame;
        frame.convertTo(detectedFrame, CV_8U);
        if (parser.has("image")) imwrite(outputFile, detectedFrame);
        else video.write(detectedFrame);
        
        imshow(kWinName, frame);

    }
    
    cap.release();
    if (!parser.has("image")) video.release();

    return 0;
}

// For each frame, extract the bounding box and mask for each detected object
void postprocess(Mat& frame, const vector<Mat>& outs)
{
    Mat outDetections = outs[0];
    Mat outMasks = outs[1];
    
    // Output size of masks is NxCxHxW where
    // N - number of detected boxes
    // C - number of classes (excluding background)
    // HxW - segmentation shape
    const int numDetections = outDetections.size[2];
    const int numClasses = outMasks.size[1];
    
    outDetections = outDetections.reshape(1, outDetections.total() / 7);
    for (int i = 0; i < numDetections; ++i)
    {
        float score = outDetections.at<float>(i, 2);
        if (score > confThreshold)
        {
            // Extract the bounding box
            int classId = static_cast<int>(outDetections.at<float>(i, 1));
            int left = static_cast<int>(frame.cols * outDetections.at<float>(i, 3));
            int top = static_cast<int>(frame.rows * outDetections.at<float>(i, 4));
            int right = static_cast<int>(frame.cols * outDetections.at<float>(i, 5));
            int bottom = static_cast<int>(frame.rows * outDetections.at<float>(i, 6));
            
            left = max(0, min(left, frame.cols - 1));
            top = max(0, min(top, frame.rows - 1));
            right = max(0, min(right, frame.cols - 1));
            bottom = max(0, min(bottom, frame.rows - 1));
            Rect box = Rect(left, top, right - left + 1, bottom - top + 1);
            
            // Extract the mask for the object
            Mat objectMask(outMasks.size[2], outMasks.size[3],CV_32F, outMasks.ptr<float>(i,classId));
            
            // Draw bounding box, colorize and show the mask on the image
            drawBox(frame, classId, score, box, objectMask);
            
        }
    }
}

// Draw the predicted bounding box, colorize and show the mask on the image
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask)
{
    //Draw a rectangle displaying the bounding box
    rectangle(frame, Point(box.x, box.y), Point(box.x+box.width, box.y+box.height), Scalar(255, 178, 50), 3);
    
    //Get the label for the class name and its confidence
    string label = format("%.2f", conf);
    if (!classes.empty())
    {
        CV_Assert(classId < (int)classes.size());
        label = classes[classId] + ":" + label;
    }
    
    //Display the label at the top of the bounding box
    int baseLine;
    Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
    box.y = max(box.y, labelSize.height);
    rectangle(frame, Point(box.x, box.y - round(1.5*labelSize.height)), Point(box.x + round(1.5*labelSize.width), box.y + baseLine), Scalar(255, 255, 255), FILLED);
    putText(frame, label, Point(box.x, box.y), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1);

    Scalar color = colors[classId%colors.size()];
    
    // Resize the mask, threshold, color and apply it on the image
    resize(objectMask, objectMask, Size(box.width, box.height));
    Mat mask = (objectMask > maskThreshold);
    Mat coloredRoi = (0.3 * color + 0.7 * frame(box));
    coloredRoi.convertTo(coloredRoi, CV_8UC3);

    // Draw the contours on the image
    vector<Mat> contours;
    Mat hierarchy;
    mask.convertTo(mask, CV_8U);
    findContours(mask, contours, hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);
    drawContours(coloredRoi, contours, -1, color, 5, LINE_8, hierarchy, 100);
    coloredRoi.copyTo(frame(box), mask);

}