#include <fstream>
#include <iostream>
#include <map>
#include <sstream>
#include <vector>
#include <chrono>
#include <opencv2/opencv.hpp>
#include <opencv2/videoio.hpp>
#include <opencv2/videoio.hpp>
#include <dirent.h>
#include <string>
#include "NvInfer.h"
#include "cuda_runtime_api.h"
#include "logging.h"
#include "yololayer.h"
#include "serialPort.h"

#define ENABLE_UART

#define CHECK(status) \
    do\
    {\
        auto ret = (status);\
        if (ret != 0)\
        {\
            std::cerr << "Cuda failure: " << ret << std::endl;\
            abort();\
        }\
    } while (0)

#define USE_FP16  // comment out this if want to use FP32
#define DEVICE 0  // GPU id
#define NMS_THRESH 0.5
#define BBOX_CONF_THRESH 0.4
#define UART_DEVICE "/dev/ttyTHS0"

typedef enum{
	LASER_ON,
	LASER_OFF,
} laser_status_t;

char uart_buff[32];

using namespace nvinfer1;

// stuff we know about the network and the input/output blobs
static const int INPUT_H = Yolo::INPUT_H;
static const int INPUT_W = Yolo::INPUT_W;
static const int OUTPUT_SIZE = 1000 * 7 + 1;  // we assume the yololayer outputs no more than 1000 boxes that conf >= 0.1
const char* INPUT_BLOB_NAME = "data";
const char* OUTPUT_BLOB_NAME = "prob";
static Logger gLogger;

cv::Mat preprocess_img(cv::Mat& img) {
    int w, h, x, y;
    float r_w = INPUT_W / (img.cols*1.0);
    float r_h = INPUT_H / (img.rows*1.0);
    if (r_h > r_w) {
        w = INPUT_W;
        h = r_w * img.rows;
        x = 0;
        y = (INPUT_H - h) / 2;
    } else {
        w = r_h* img.cols;
        h = INPUT_H;
        x = (INPUT_W - w) / 2;
        y = 0;
    }
    cv::Mat re(h, w, CV_8UC3);
    cv::resize(img, re, re.size(), 0, 0, cv::INTER_CUBIC);
    cv::Mat out(INPUT_H, INPUT_W, CV_8UC3, cv::Scalar(128, 128, 128));
    re.copyTo(out(cv::Rect(x, y, re.cols, re.rows)));
    return out;
}

cv::Rect get_rect(cv::Mat& img, float bbox[4]) {
    int l, r, t, b;
    float r_w = INPUT_W / (img.cols * 1.0);
    float r_h = INPUT_H / (img.rows * 1.0);
    if (r_h > r_w) {
        l = bbox[0] - bbox[2]/2.f;
        r = bbox[0] + bbox[2]/2.f;
        t = bbox[1] - bbox[3]/2.f - (INPUT_H - r_w * img.rows) / 2;
        b = bbox[1] + bbox[3]/2.f - (INPUT_H - r_w * img.rows) / 2;
        l = l / r_w;
        r = r / r_w;
        t = t / r_w;
        b = b / r_w;
    } else {
        l = bbox[0] - bbox[2]/2.f - (INPUT_W - r_h * img.cols) / 2;
        r = bbox[0] + bbox[2]/2.f - (INPUT_W - r_h * img.cols) / 2;
        t = bbox[1] - bbox[3]/2.f;
        b = bbox[1] + bbox[3]/2.f;
        l = l / r_h;
        r = r / r_h;
        t = t / r_h;
        b = b / r_h;
    }
    return cv::Rect(l, t, r-l, b-t);
}

float iou(float lbox[4], float rbox[4]) {
    float interBox[] = {
        std::max(lbox[0] - lbox[2]/2.f , rbox[0] - rbox[2]/2.f), //left
        std::min(lbox[0] + lbox[2]/2.f , rbox[0] + rbox[2]/2.f), //right
        std::max(lbox[1] - lbox[3]/2.f , rbox[1] - rbox[3]/2.f), //top
        std::min(lbox[1] + lbox[3]/2.f , rbox[1] + rbox[3]/2.f), //bottom
    };

    if(interBox[2] > interBox[3] || interBox[0] > interBox[1])
        return 0.0f;

    float interBoxS =(interBox[1]-interBox[0])*(interBox[3]-interBox[2]);
    return interBoxS/(lbox[2]*lbox[3] + rbox[2]*rbox[3] -interBoxS);
}

bool cmp(const Yolo::Detection& a, const Yolo::Detection& b) {
    return a.det_confidence > b.det_confidence;
}

void nms(std::vector<Yolo::Detection>& res, float *output, float nms_thresh = NMS_THRESH) {
    std::map<float, std::vector<Yolo::Detection>> m;
    for (int i = 0; i < output[0] && i < 1000; i++) {
        if (output[1 + 7 * i + 4] <= BBOX_CONF_THRESH) continue;
        Yolo::Detection det;
        memcpy(&det, &output[1 + 7 * i], 7 * sizeof(float));
        if (m.count(det.class_id) == 0) m.emplace(det.class_id, std::vector<Yolo::Detection>());
        m[det.class_id].push_back(det);
    }
    for (auto it = m.begin(); it != m.end(); it++) {
        //std::cout << it->second[0].class_id << " --- " << std::endl;
        auto& dets = it->second;
        std::sort(dets.begin(), dets.end(), cmp);
        for (size_t m = 0; m < dets.size(); ++m) {
            auto& item = dets[m];
            res.push_back(item);
            for (size_t n = m + 1; n < dets.size(); ++n) {
                if (iou(item.bbox, dets[n].bbox) > nms_thresh) {
                    dets.erase(dets.begin()+n);
                    --n;
                }
            }
        }
    }
}

// TensorRT weight files have a simple space delimited format:
// [type] [size] <data x size in hex>
std::map<std::string, Weights> loadWeights(const std::string file) {
    std::cout << "Loading weights: " << file << std::endl;
    std::map<std::string, Weights> weightMap;

    // Open weights file
    std::ifstream input(file);
    assert(input.is_open() && "Unable to load weight file.");

    // Read number of weight blobs
    int32_t count;
    input >> count;
    assert(count > 0 && "Invalid weight map file.");

    while (count--)
    {
        Weights wt{DataType::kFLOAT, nullptr, 0};
        uint32_t size;

        // Read name and type of blob
        std::string name;
        input >> name >> std::dec >> size;
        wt.type = DataType::kFLOAT;

        // Load blob
        uint32_t* val = reinterpret_cast<uint32_t*>(malloc(sizeof(val) * size));
        for (uint32_t x = 0, y = size; x < y; ++x)
        {
            input >> std::hex >> val[x];
        }
        wt.values = val;
        
        wt.count = size;
        weightMap[name] = wt;
    }

    return weightMap;
}

IScaleLayer* addBatchNorm2d(INetworkDefinition *network, std::map<std::string, Weights>& weightMap, ITensor& input, std::string lname, float eps) {
    float *gamma = (float*)weightMap[lname + ".weight"].values;
    float *beta = (float*)weightMap[lname + ".bias"].values;
    float *mean = (float*)weightMap[lname + ".running_mean"].values;
    float *var = (float*)weightMap[lname + ".running_var"].values;
    int len = weightMap[lname + ".running_var"].count;

    float *scval = reinterpret_cast<float*>(malloc(sizeof(float) * len));
    for (int i = 0; i < len; i++) {
        scval[i] = gamma[i] / sqrt(var[i] + eps);
    }
    Weights scale{DataType::kFLOAT, scval, len};
    
    float *shval = reinterpret_cast<float*>(malloc(sizeof(float) * len));
    for (int i = 0; i < len; i++) {
        shval[i] = beta[i] - mean[i] * gamma[i] / sqrt(var[i] + eps);
    }
    Weights shift{DataType::kFLOAT, shval, len};

    float *pval = reinterpret_cast<float*>(malloc(sizeof(float) * len));
    for (int i = 0; i < len; i++) {
        pval[i] = 1.0;
    }
    Weights power{DataType::kFLOAT, pval, len};

    weightMap[lname + ".scale"] = scale;
    weightMap[lname + ".shift"] = shift;
    weightMap[lname + ".power"] = power;
    IScaleLayer* scale_1 = network->addScale(input, ScaleMode::kCHANNEL, shift, scale, power);
    assert(scale_1);
    return scale_1;
}

ILayer* convBnLeaky(INetworkDefinition *network, std::map<std::string, Weights>& weightMap, ITensor& input,  int outch, int ksize, int s, int p, int linx) {
    Weights emptywts{DataType::kFLOAT, nullptr, 0};
    IConvolutionLayer* conv1 = network->addConvolutionNd(input, outch, DimsHW{ksize, ksize}, weightMap["module_list." + std::to_string(linx) + ".Conv2d.weight"], emptywts);
    assert(conv1);
    conv1->setStrideNd(DimsHW{s, s});
    conv1->setPaddingNd(DimsHW{p, p});

    IScaleLayer* bn1 = addBatchNorm2d(network, weightMap, *conv1->getOutput(0), "module_list." + std::to_string(linx) + ".BatchNorm2d", 1e-4);

    auto lr = network->addActivation(*bn1->getOutput(0), ActivationType::kLEAKY_RELU);
    lr->setAlpha(0.1);

    return lr;
}

// Creat the engine using only the API and not any parser.
ICudaEngine* createEngine(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt) {
    INetworkDefinition* network = builder->createNetworkV2(0U);

    // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
    ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{3, INPUT_H, INPUT_W});
    assert(data);

    std::map<std::string, Weights> weightMap = loadWeights("../laser_detect.wts");
    Weights emptywts{DataType::kFLOAT, nullptr, 0};

    auto lr0 = convBnLeaky(network, weightMap, *data, 16, 3, 1, 1, 0);
    auto pool1 = network->addPoolingNd(*lr0->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool1->setStrideNd(DimsHW{2, 2});
    auto lr2 = convBnLeaky(network, weightMap, *pool1->getOutput(0), 32, 3, 1, 1, 2);
    auto pool3 = network->addPoolingNd(*lr2->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool3->setStrideNd(DimsHW{2, 2});
    auto lr4 = convBnLeaky(network, weightMap, *pool3->getOutput(0), 64, 3, 1, 1, 4);
    auto pool5 = network->addPoolingNd(*lr4->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool5->setStrideNd(DimsHW{2, 2});
    auto lr6 = convBnLeaky(network, weightMap, *pool5->getOutput(0), 128, 3, 1, 1, 6);
    auto pool7 = network->addPoolingNd(*lr6->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool7->setStrideNd(DimsHW{2, 2});
    auto lr8 = convBnLeaky(network, weightMap, *pool7->getOutput(0), 256, 3, 1, 1, 8);
    auto pool9 = network->addPoolingNd(*lr8->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool9->setStrideNd(DimsHW{2, 2});
    auto lr10 = convBnLeaky(network, weightMap, *pool9->getOutput(0), 512, 3, 1, 1, 10);
    auto pad11 = network->addPaddingNd(*lr10->getOutput(0), DimsHW{0, 0}, DimsHW{1, 1});
    auto pool11 = network->addPoolingNd(*pad11->getOutput(0), PoolingType::kMAX, DimsHW{2, 2});
    pool11->setStrideNd(DimsHW{1, 1});
    auto lr12 = convBnLeaky(network, weightMap, *pool11->getOutput(0), 1024, 3, 1, 1, 12);
    auto lr13 = convBnLeaky(network, weightMap, *lr12->getOutput(0), 256, 1, 1, 0, 13);
    auto lr14 = convBnLeaky(network, weightMap, *lr13->getOutput(0), 512, 3, 1, 1, 14);
    IConvolutionLayer* conv15 = network->addConvolutionNd(*lr14->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{1, 1}, weightMap["module_list.15.Conv2d.weight"], weightMap["module_list.15.Conv2d.bias"]);
    // 16 is yolo
    auto l17 = lr13;
    auto lr18 = convBnLeaky(network, weightMap, *l17->getOutput(0), 128, 1, 1, 0, 18);

    float *deval = reinterpret_cast<float*>(malloc(sizeof(float) * 128 * 2 * 2));
    for (int i = 0; i < 128 * 2 * 2; i++) {
        deval[i] = 1.0;
    }
    Weights deconvwts19{DataType::kFLOAT, deval, 128 * 2 * 2};
    IDeconvolutionLayer* deconv19 = network->addDeconvolutionNd(*lr18->getOutput(0), 128, DimsHW{2, 2}, deconvwts19, emptywts);
    assert(deconv19);
    deconv19->setStrideNd(DimsHW{2, 2});
    deconv19->setNbGroups(128);
    weightMap["deconv19"] = deconvwts19;

    ITensor* inputTensors[] = {deconv19->getOutput(0), lr8->getOutput(0)};
    auto cat20 = network->addConcatenation(inputTensors, 2);
    auto lr21 = convBnLeaky(network, weightMap, *cat20->getOutput(0), 256, 3, 1, 1, 21);
    IConvolutionLayer* conv22 = network->addConvolutionNd(*lr21->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{1, 1}, weightMap["module_list.22.Conv2d.weight"], weightMap["module_list.22.Conv2d.bias"]);
    // 22 is yolo

    auto creator = getPluginRegistry()->getPluginCreator("YoloLayer_TRT", "1");
    const PluginFieldCollection* pluginData = creator->getFieldNames();
    IPluginV2 *pluginObj = creator->createPlugin("yololayer", pluginData);
    ITensor* inputTensors_yolo[] = {conv15->getOutput(0), conv22->getOutput(0)};
    auto yolo = network->addPluginV2(inputTensors_yolo, 2, *pluginObj);

    yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
    network->markOutput(*yolo->getOutput(0));

    // Build engine
    builder->setMaxBatchSize(maxBatchSize);
    config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
#ifdef USE_FP16
    config->setFlag(BuilderFlag::kFP16);
#endif
    std::cout << "Building engine, please wait for a while..." << std::endl;
    ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
    std::cout << "Build engine successfully!" << std::endl;

    // Don't need the network any more
    network->destroy();

    // Release host memory
    for (auto& mem : weightMap)
    {
        free((void*) (mem.second.values));
    }

    return engine;
}

void APIToModel(unsigned int maxBatchSize, IHostMemory** modelStream) {
    // Create builder
    IBuilder* builder = createInferBuilder(gLogger);
    IBuilderConfig* config = builder->createBuilderConfig();

    // Create model to populate the network, then set the outputs and create an engine
    ICudaEngine* engine = createEngine(maxBatchSize, builder, config, DataType::kFLOAT);
    assert(engine != nullptr);

    // Serialize the engine
    (*modelStream) = engine->serialize();

    // Close everything down
    engine->destroy();
    builder->destroy();
}

void doInference(IExecutionContext& context, float* input, float* output, int batchSize) {
    const ICudaEngine& engine = context.getEngine();

    // Pointers to input and output device buffers to pass to engine.
    // Engine requires exactly IEngine::getNbBindings() number of buffers.
    assert(engine.getNbBindings() == 2);
    void* buffers[2];

    // In order to bind the buffers, we need to know the names of the input and output tensors.
    // Note that indices are guaranteed to be less than IEngine::getNbBindings()
    const int inputIndex = engine.getBindingIndex(INPUT_BLOB_NAME);
    const int outputIndex = engine.getBindingIndex(OUTPUT_BLOB_NAME);

    // Create GPU buffers on device
    CHECK(cudaMalloc(&buffers[inputIndex], batchSize * 3 * INPUT_H * INPUT_W * sizeof(float)));
    CHECK(cudaMalloc(&buffers[outputIndex], batchSize * OUTPUT_SIZE * sizeof(float)));

    // Create stream
    cudaStream_t stream;
    CHECK(cudaStreamCreate(&stream));

    // DMA input batch data to device, infer on the batch asynchronously, and DMA output back to host
    CHECK(cudaMemcpyAsync(buffers[inputIndex], input, batchSize * 3 * INPUT_H * INPUT_W * sizeof(float), cudaMemcpyHostToDevice, stream));
    context.enqueue(batchSize, buffers, stream, nullptr);
    CHECK(cudaMemcpyAsync(output, buffers[outputIndex], batchSize * OUTPUT_SIZE * sizeof(float), cudaMemcpyDeviceToHost, stream));
    cudaStreamSynchronize(stream);

    // Release stream and buffers
    cudaStreamDestroy(stream);
    CHECK(cudaFree(buffers[inputIndex]));
    CHECK(cudaFree(buffers[outputIndex]));
}

int read_files_in_dir(const char *p_dir_name, std::vector<std::string> &file_names) {
    DIR *p_dir = opendir(p_dir_name);
    if (p_dir == nullptr) {
        return -1;
    }

    struct dirent* p_file = nullptr;
    while ((p_file = readdir(p_dir)) != nullptr) {
        if (strcmp(p_file->d_name, ".") != 0 &&
                strcmp(p_file->d_name, "..") != 0) {
            //std::string cur_file_name(p_dir_name);
            //cur_file_name += "/";
            //cur_file_name += p_file->d_name;
            std::string cur_file_name(p_file->d_name);
            file_names.push_back(cur_file_name);
        }
    }

    closedir(p_dir);
    return 0;
}

int get_car_speed(char *speed_in_str)
{
	int res = 0;
	char *ptr = speed_in_str;
	while(ptr)
	{
		int tmp = *ptr - '0';
		std::cout << "transform: " << tmp << std::endl;
		res = res * 10 + tmp;
		ptr += 1;
	}

	return res;
}


int update_car_speed(int speed)
{
	return speed;
}

int update_obj_dist(int dist)
{
	return dist;
}


int main(int argc, char** argv) {
	if(argc != 2)
	{
		std::cerr << "please give in the viehle speed" << std::endl;
		return -1;
	}

	int car_speed = std::stoi(std::string(argv[1]));
	int obj_dist = 450;
	int obj_detected = 0;

    cudaSetDevice(DEVICE);
	// setting for the camera
	cv::VideoCapture cap;
	cap.open(0);
	// cap.open("../videos/laser_detect_test_video.avi");

	if(!cap.isOpened())
	{
		std::cerr << "the camera can not be opened" << std::endl;
		return -1;
	}

	//cap.set(cv::CAP_PROP_FRAME_WIDTH, 1024);
	//cap.set(cv::CAP_PROP_FRAME_HEIGHT, 768);

	// setting for the serial port
#ifdef ENABLE_UART
	serialPort myserial;
	int numUartToSend, numUartWrited;

	if(myserial.OpenPort(UART_DEVICE) < 0)
	{
		std::cerr << "can not open the uart deice" << std::endl;
		return -1;
	}

	if(myserial.setup(115200, 0, 8, 1, 'N') < 0)
	{
		std::cerr << "setup for the uart deivec failed" << std::endl;
		return -1;
	}
#endif

    // create a model using the API directly and serialize it to a stream
    char *trtModelStream{nullptr};
    size_t size{0};

	std::ifstream file("yolov3-tiny.engine", std::ios::binary);
	if (file.good()) {
		file.seekg(0, file.end);
		size = file.tellg();
		file.seekg(0, file.beg);
		trtModelStream = new char[size];
		assert(trtModelStream);
		file.read(trtModelStream, size);
		file.close();
	}

    // prepare input data ---------------------------
    static float data[3 * INPUT_H * INPUT_W];
    //for (int i = 0; i < 3 * INPUT_H * INPUT_W; i++)
    //    data[i] = 1.0;
    static float prob[OUTPUT_SIZE];
    IRuntime* runtime = createInferRuntime(gLogger);
    assert(runtime != nullptr);
    ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size);
    assert(engine != nullptr);
    IExecutionContext* context = engine->createExecutionContext();
    assert(context != nullptr);
    delete[] trtModelStream;

    int fcount = 0;
	cv::Mat img;
	int num_cnt = 0;
	std::vector<Yolo::Detection> last_obj_info;
	laser_status_t laser_status = LASER_ON;
	int up_limit = 2, bottom_limit = -5;
	while(true){
		cap.read(img);
		if(img.empty()) break;

        cv::Mat pr_img = preprocess_img(img);
        for (int i = 0; i < INPUT_H * INPUT_W; i++) {
            data[i] = pr_img.at<cv::Vec3b>(i)[2] / 255.0;
            data[i + INPUT_H * INPUT_W] = pr_img.at<cv::Vec3b>(i)[1] / 255.0;
            data[i + 2 * INPUT_H * INPUT_W] = pr_img.at<cv::Vec3b>(i)[0] / 255.0;
        }

        // Run inference
        auto start = std::chrono::system_clock::now();
        doInference(*context, data, prob, 1);
        auto end = std::chrono::system_clock::now();
        //std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms" << std::endl;
        std::vector<Yolo::Detection> res;
        nms(res, prob);
		
		// display and send msg
		int detected_obj_nums = res.size();
		if(detected_obj_nums > 0)
		{
			num_cnt = num_cnt >= up_limit? up_limit : num_cnt + 1;

			if(num_cnt >= up_limit)
			{
				for (size_t j = 0; j < res.size(); j++) {
					cv::Rect r = get_rect(img, res[j].bbox);
					cv::rectangle(img, r, cv::Scalar(0x27, 0xC1, 0x36), 2);
					cv::putText(img, "night_car", cv::Point(r.x, r.y - 1), cv::FONT_HERSHEY_PLAIN, 1.2, cv::Scalar(0xFF, 0xFF, 0xFF), 2);

				}
				last_obj_info = res;
				obj_detected = 1;
			}

		}
		else
		{
			num_cnt = (num_cnt <= bottom_limit)? bottom_limit : num_cnt -1;

			if(num_cnt <= bottom_limit)
			{
				obj_detected = 0;
			}
			else
			{
				if(last_obj_info.size() > 0)
				{
					for (size_t j = 0; j < last_obj_info.size(); j++) {
						cv::Rect r = get_rect(img, last_obj_info[j].bbox);
						cv::rectangle(img, r, cv::Scalar(0x27, 0xC1, 0x36), 2);
						cv::putText(img, "night_car", cv::Point(r.x, r.y - 1), cv::FONT_HERSHEY_PLAIN, 1.2, cv::Scalar(0xFF, 0xFF, 0xFF), 2);
					}
				}
			}
		}

		// control the laser
		if(!obj_detected && car_speed >= 50)
		{
			if(laser_status == LASER_OFF)
			{
				numUartToSend = sprintf(uart_buff, "ro\n");
				myserial.writeBuffer(uart_buff, numUartToSend);
				laser_status = LASER_ON;
				std::cout << "ro\n" << std::endl;
			}
		}
		else
		{
			if(laser_status == LASER_ON)
			{
				numUartToSend = sprintf(uart_buff, "rc\n");
				myserial.writeBuffer(uart_buff, numUartToSend);
				laser_status = LASER_OFF;
				std::cout << "rc\n" << std::endl;
			}
		}

		// add info to imgs
		if(obj_detected)
		{
			std::string detect_info = "dist: " + std::to_string(update_obj_dist(obj_dist)) + " m";
			cv::putText(img, detect_info, cv::Point(10, 90), cv::FONT_HERSHEY_PLAIN, 1.0, cv::Scalar(0x0, 0xff, 0x0), 2);
		}

		std::string car_speed_info = "speed: " + std::to_string(car_speed);
		std::string laser_status_info ="laser: " + std::string((laser_status == LASER_ON)? "ON" : "off");
		cv::putText(img, car_speed_info, cv::Point(10, 30), cv::FONT_HERSHEY_PLAIN, 1.0, cv::Scalar(0x0, 0xff, 0x0), 2);
		cv::putText(img, laser_status_info, cv::Point(10, 60), cv::FONT_HERSHEY_PLAIN, 1.0, cv::Scalar(0x0, 0xff, 0x0), 2);
		
		cv::imshow("cam", img);
		if(cv::waitKey(10) >= 0)
			break;
    }

    // Destroy the engine
    context->destroy();
    engine->destroy();
    runtime->destroy();

	// close uart and cap
	cap.release();
#ifdef ENABLE_UART
	myserial.ClosePort();
#endif
    return 0;
}