目标识别与区域入侵检测

#include "YoloOnnx.h" size_t utils::vectorProduct(const std::vector<int64_t>& vector) { if (vector.empty()) return 0; size_t product = 1; for (const auto& element : vector) product *= element; return product; } std::wstring utils::charToWstring(const char* str) { typedef std::codecvt_utf8<wchar_t> convert_type; std::wstring_convert<convert_type, wchar_t> converter; return converter.from_bytes(str); } std::vector<std::string> utils::loadNames(const std::string& path) { // load class names std::vector<std::string> classNames; std::ifstream infile(path); if (infile.good()) { std::string line; while (getline(infile, line)) { if (line.back() == '\r') line.pop_back(); classNames.emplace_back(line); } infile.close(); } else { std::cerr << "ERROR: Failed to access class name path: " << path << std::endl; } return classNames; } void utils::visualizeDetection(cv::Mat& image, std::vector<Detection>& detections, const std::vector<std::string>& classNames) { for (const Detection& detection : detections) { cv::rectangle(image, detection.box, cv::Scalar(229, 160, 21), 1); int x = detection.box.x; int y = detection.box.y; int conf = (int)std::round(detection.conf * 100); int classId = detection.classId; std::string label = classNames[classId]; int baseline = 0; cv::Size size = cv::getTextSize(label, cv::FONT_ITALIC, 0.8, 1, &baseline); cv::rectangle(image, cv::Point(x, y - 25), cv::Point(x + size.width, y), cv::Scalar(229, 160, 21), -1); cv::putText(image, label, cv::Point(x, y - 3), cv::FONT_ITALIC, 0.8, cv::Scalar(255, 255, 255), 1); } } void utils::letterbox(const cv::Mat& image, cv::Mat& outImage, const cv::Size& newShape = cv::Size(640, 640), const cv::Scalar& color = cv::Scalar(114, 114, 114), bool auto_ = true, bool scaleFill = false, bool scaleUp = true, int stride = 32) { cv::Size shape = image.size(); float r = std::min((float)newShape.height / (float)shape.height, (float)newShape.width / (float)shape.width); if (!scaleUp) r = std::min(r, 1.0f); float ratio[2]{ r, r }; int newUnpad[2]{ (int)std::round((float)shape.width * r), (int)std::round((float)shape.height * r) }; auto dw = (float)(newShape.width - newUnpad[0]); auto dh = (float)(newShape.height - newUnpad[1]); if (auto_) { dw = (float)((int)dw % stride); dh = (float)((int)dh % stride); } else if (scaleFill) { dw = 0.0f; dh = 0.0f; newUnpad[0] = newShape.width; newUnpad[1] = newShape.height; ratio[0] = (float)newShape.width / (float)shape.width; ratio[1] = (float)newShape.height / (float)shape.height; } dw /= 2.0f; dh /= 2.0f; if (shape.width != newUnpad[0] && shape.height != newUnpad[1]) { cv::resize(image, outImage, cv::Size(newUnpad[0], newUnpad[1])); } int top = int(std::round(dh - 0.1f)); int bottom = int(std::round(dh + 0.1f)); int left = int(std::round(dw - 0.1f)); int right = int(std::round(dw + 0.1f)); cv::copyMakeBorder(outImage, outImage, top, bottom, left, right, cv::BORDER_CONSTANT, color); } void utils::scaleCoords(const cv::Size& imageShape, cv::Rect& coords, const cv::Size& imageOriginalShape) { float gain = std::min((float)imageShape.height / (float)imageOriginalShape.height, (float)imageShape.width / (float)imageOriginalShape.width); int pad[2] = { (int)(((float)imageShape.width - (float)imageOriginalShape.width * gain) / 2.0f), (int)(((float)imageShape.height - (float)imageOriginalShape.height * gain) / 2.0f) }; coords.x = (int)std::round(((float)(coords.x - pad[0]) / gain)); coords.y = (int)std::round(((float)(coords.y - pad[1]) / gain)); coords.width = (int)std::round(((float)coords.width / gain)); coords.height = (int)std::round(((float)coords.height / gain)); } template <typename T> T utils::clip(const T& n, const T& lower, const T& upper) { return std::max(lower, std::min(n, upper)); } YoloOnnx::YoloOnnx(const std::string& modelPath, const bool& isGPU = true, const cv::Size& inputSize = cv::Size(640, 640)) { env = Ort::Env(OrtLoggingLevel::ORT_LOGGING_LEVEL_WARNING, "ONNX_DETECTION"); sessionOptions = Ort::SessionOptions(); std::vector<std::string> availableProviders = Ort::GetAvailableProviders(); auto cudaAvailable = std::find(availableProviders.begin(), availableProviders.end(), "CUDAExecutionProvider"); OrtCUDAProviderOptions cudaOption; if (isGPU && (cudaAvailable == availableProviders.end())) { std::cout << "GPU is not supported by your ONNXRuntime build. Fallback to CPU." << std::endl; std::cout << "Inference device: CPU" << std::endl; } else if (isGPU && (cudaAvailable != availableProviders.end())) { std::cout << "Inference device: GPU" << std::endl; sessionOptions.AppendExecutionProvider_CUDA(cudaOption); } else { std::cout << "Inference device: CPU" << std::endl; } #ifdef _WIN32 std::wstring w_modelPath = utils::charToWstring(modelPath.c_str()); session = Ort::Session(env, w_modelPath.c_str(), sessionOptions); #else session = Ort::Session(env, modelPath.c_str(), sessionOptions); #endif Ort::AllocatorWithDefaultOptions allocator; Ort::TypeInfo inputTypeInfo = session.GetInputTypeInfo(0); std::vector<int64_t> inputTensorShape = inputTypeInfo.GetTensorTypeAndShapeInfo().GetShape(); this->isDynamicInputShape = false; // checking if width and height are dynamic if (inputTensorShape[2] == -1 && inputTensorShape[3] == -1) { std::cout << "Dynamic input shape" << std::endl; this->isDynamicInputShape = true; } for (auto shape : inputTensorShape) std::cout << "Input shape: " << shape << std::endl; inputNames.push_back(session.GetInputName(0, allocator)); outputNames.push_back(session.GetOutputName(0, allocator)); std::cout << "Input name: " << inputNames[0] << std::endl; std::cout << "Output name: " << outputNames[0] << std::endl; this->inputImageShape = cv::Size2f(inputSize); } void YoloOnnx::getBestClassInfo(std::vector<float>::iterator it, const int& numClasses, float& bestConf, int& bestClassId) { // first 5 element are box and obj confidence bestClassId = 5; bestConf = 0; for (int i = 5; i < numClasses + 5; i++) { if (it[i] > bestConf) { bestConf = it[i]; bestClassId = i - 5; } } } void YoloOnnx::preprocessing(cv::Mat &image, float*& blob, std::vector<int64_t>& inputTensorShape) { cv::Mat resizedImage, floatImage; cv::cvtColor(image, resizedImage, cv::COLOR_BGR2RGB); utils::letterbox(resizedImage, resizedImage, this->inputImageShape, cv::Scalar(114, 114, 114), this->isDynamicInputShape, false, true, 32); inputTensorShape[2] = resizedImage.rows; inputTensorShape[3] = resizedImage.cols; resizedImage.convertTo(floatImage, CV_32FC3, 1 / 255.0); blob = new float[floatImage.cols * floatImage.rows * floatImage.channels()]; cv::Size floatImageSize {floatImage.cols, floatImage.rows}; // hwc -> chw std::vector<cv::Mat> chw(floatImage.channels()); for (int i = 0; i < floatImage.channels(); ++i)