C++使用OpenCV进行物体识别与检测的三种方法

#include <opencv2/opencv.hpp>
using namespace cv;
 
int main() {
    // 读取输入图像
    Mat image = imread("people.jpg");
 
    if (image.empty()) {
        std::cout << "Error loading image!" << std::endl;
        return -1;
    }
 
    // 将图像转换为灰度图
    Mat grayImage;
    cvtColor(image, grayImage, COLOR_BGR2GRAY);
 
    // 加载预训练的人脸分类器
    CascadeClassifier faceCascade;
    if (!faceCascade.load("haarcascade_frontalface_default.xml")) {
        std::cout << "Error loading cascade file!" << std::endl;
        return -1;
    }
 
    // 检测人脸
    std::vector<Rect> faces;
    faceCascade.detectMultiScale(grayImage, faces);
 
    // 绘制矩形框标记人脸
    for (size_t i = 0; i < faces.size(); i++) {
        rectangle(image, faces[i], Scalar(0, 255, 0), 2);
    }
 
    // 显示检测结果
    imshow("Detected Faces", image);
    waitKey(0);
 
    return 0;
}

CascadeClassifier eyeCascade;
eyeCascade.load("haarcascade_eye.xml");
eyeCascade.detectMultiScale(grayImage, eyes);

#include <opencv2/opencv.hpp>
#include <opencv2/objdetect.hpp>
using namespace cv;
 
int main() {
    // 读取输入图像
    Mat image = imread("people.jpg");
 
    if (image.empty()) {
        std::cout << "Error loading image!" << std::endl;
        return -1;
    }
 
    // 创建 HOG 描述符
    HOGDescriptor hog;
    hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());
 
    // 检测图像中的行人
    std::vector<Rect> foundLocations;
    hog.detectMultiScale(image, foundLocations);
 
    // 在图像中绘制检测到的行人位置
    for (size_t i = 0; i < foundLocations.size(); i++) {
        rectangle(image, foundLocations[i], Scalar(0, 255, 0), 2);
    }
 
    // 显示检测结果
    imshow("Detected People", image);
    waitKey(0);
 
    return 0;
}

#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
using namespace cv;
using namespace cv::dnn;
 
int main() {
    // 加载 YOLO 模型
    Net net = readNet("yolov3.weights", "yolov3.cfg");
    std::vector<String> outNames = net.getUnconnectedOutLayersNames();
 
    // 加载类别名称
    std::ifstream ifs("coco.names");
    std::vector<std::string> classes;
    std::string line;
    while (getline(ifs, line)) {
        classes.push_back(line);
    }
 
    // 读取输入图像
    Mat image = imread("image.jpg");
 
    // 转换图像为 YOLO 输入格式
    Mat blob = blobFromImage(image, 1 / 255.0, Size(416, 416), Scalar(), true, false);
 
    // 设置网络输入
    net.setInput(blob);
 
    // 获取 YOLO 输出
    std::vector<Mat> outs;
    net.forward(outs, outNames);
 
    // 处理输出
    for (size_t i = 0; i < outs.size(); i++) {
        Mat detectionMat = outs[i];
        for (int j = 0; j < detectionMat.rows; j++) {
            // 提取检测框信息（置信度、类标签、边界框）
            float confidence = detectionMat.at<float>(j, 4);
            if (confidence > 0.5) {  // 只显示置信度大于 0.5 的检测结果
                int classId = -1;
                float maxClassConf = -1;
                for (int k = 5; k < detectionMat.cols; k++) {
                    if (detectionMat.at<float>(j, k) > maxClassConf) {
                        maxClassConf = detectionMat.at<float>(j, k);
                        classId = k - 5;
                    }
                }
 
                // 计算边界框
                int x = int(detectionMat.at<float>(j, 0) * image.cols);
                int y = int(detectionMat.at<float>(j, 1) * image.rows);
                int width = int(detectionMat.at<float>(j, 2) * image.cols);
                int height = int(detectionMat.at<float>(j, 3) * image.rows);
 
                // 绘制边界框
                rectangle(image, Rect(x, y, width, height), Scalar(0, 255, 0), 2);
                putText(image, classes[classId], Point(x, y - 5), FONT_HERSHEY_SIMPLEX, 1, Scalar(0, 255, 0), 2);
            }
        }
    }
 
    // 显示检测结果
    imshow("YOLO Object Detection", image);
    waitKey(0);
 
    return 0;
}