前言

在前面两篇关于火焰检测的文章中，最终的效果不是很好，为了提高火焰检测的效果，又搜集了一些火焰数据，训练的网络由之前的yolov3-tiny改为mobilev2-yolov3，最终在树莓派上利用NCNN推算框架，比之前的效果要好很多，如图：

在这里插入图片描述

下面把实现的步骤和大家分享下：

在darknet下训练

训练的cfg和model文件如果需要联系笔者

在树莓派上部署NCNN

官方提供了在树莓派上的编译说明，按照这个说明是可以编译起来的。这里可以参考这篇文章来安装依赖：

sudo apt-get install git cmake
sudo apt-get install -y gfortran
sudo apt-get install -y libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
sudo apt-get install -y libgflags-dev libgoogle-glog-dev liblmdb-dev libatlas

然后下载NCNN：

git clone https://github.com/Tencent/ncnn.git
cd ncnn

编辑CMakeList.txt文件，添加examples和benchmark：

add_subdirectory(examples)
add_subdirectory(benchmark)
add_subdirectory(tools)

然后就可以按照官方文档进行编译了，官方提供的pi3 toolchain在4代Raspbian上可以直接使用，最新版的NCNN会自动使用OpenMP：

cd <ncnn-root-dir>
mkdir -p build
cd build
cmake -DCMAKE_TOOLCHAIN_FILE=../toolchains/pi3.toolchain.cmake -DPI3=ON ..
make -j4

模型转换

cd <ncnn-root-dir>
cd build
cd tools/darknet
./darknet2ncnn mobilenetV2-yolov3.cfg mobilenetV2-yolov3.weights mobilenetV2-yolov3.param mobilenetV2-yolov3.bin 1

运行

cd <ncnn-root-dir>
cd build
cd example
./mobilenetV2-yolov3

部分代码


#include "net.h"

#include "platform.h"


#include <opencv2/core/core.hpp>

#include <opencv2/highgui/highgui.hpp>

#include <opencv2/imgproc/imgproc.hpp>

#include <stdio.h>

#include <vector>

#include <sys/time.h>

#include <stdio.h>

#include <string.h>

#if NCNN_VULKAN

#include "gpu.h"

#endif // NCNN_VULKAN


#define MobileNetV2-yolov3_TINY 1 //0 or undef for MobileNetV2-yolov3


struct Object

{

    cv::Rect_<float> rect;

    int label;

    float prob;

};


double what_time_is_it_now()
{

    struct timeval time;

    if (gettimeofday(&time,NULL)){

        return 0;

    }

    return (double)time.tv_sec + (double)time.tv_usec * .000001;

}

ncnn::Net MobileNetV2-yolov3;

static int detect_MobileNetV2-yolov3(const cv::Mat& bgr, std::vector<Object>& objects)

{

    double time;

#if NCNN_VULKAN

    MobileNetV2-yolov3.opt.use_vulkan_compute = true;

#endif // NCNN_VULKAN


    const int target_size = 320;

    time = what_time_is_it_now();

    int img_w = bgr.cols;

    int img_h = bgr.rows;

    //PIXEL_BGR

    ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, bgr.cols, bgr.rows, target_size, target_size);


    const float mean_vals[3] = {0, 0, 0};

    const float norm_vals[3] = {1 / 255.f, 1 / 255.f, 1 / 255.f};

    in.substract_mean_normalize(mean_vals, norm_vals);


    ncnn::Extractor ex = MobileNetV2-yolov3.create_extractor();

    ex.set_num_threads(4);


    ex.input("data", in);


    ncnn::Mat out;

    ex.extract("output", out);

    printf("Predicted in %f seconds.11\n", what_time_is_it_now()-time);

    printf("%d %d %d\n", out.w, out.h, out.c);

    objects.clear();

    for (int i = 0; i < out.h; i++)

    {

        const float* values = out.row(i);


        Object object;

        object.label = values[0];

        object.prob = values[1];

        object.rect.x = values[2] * img_w;

        object.rect.y = values[3] * img_h;

        object.rect.width = values[4] * img_w - object.rect.x;

        object.rect.height = values[5] * img_h - object.rect.y;


        objects.push_back(object);

    }


    return 0;

}


void draw_objects(cv::Mat& image, const std::vector<Object>& objects)
{

    static const char* class_names[] = {"background", "fire"};


    //cv::Mat image = bgr.clone();


    for (size_t i = 0; i < objects.size(); i++)

    {

        const Object& obj = objects[i];


        fprintf(stderr, "%d = %.5f at %.2f %.2f %.2f x %.2f\n", obj.label, obj.prob,

                obj.rect.x, obj.rect.y, obj.rect.width, obj.rect.height);


        cv::rectangle(image, obj.rect, cv::Scalar(255, 0, 0));


        char text[256];

        sprintf(text, "%s %.1f%%", class_names[obj.label], obj.prob * 100);


        int baseLine = 0;

        cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);


        int x = obj.rect.x;

        int y = obj.rect.y - label_size.height - baseLine;

        if (y < 0)

            y = 0;

        if (x + label_size.width > image.cols)

            x = image.cols - label_size.width;


        cv::rectangle(image, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)),

                      cv::Scalar(255, 255, 255), -1);


        cv::putText(image, text, cv::Point(x, y + label_size.height),

                    cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));

    }

}


int main(int argc, char** argv)
{

    MobileNetV2-yolov3.load_param("MobileNetV2-YOLOv3-Lite.param");

    MobileNetV2-yolov3.load_model("MobileNetV2-YOLOv3-Lite.bin");

    cv::VideoCapture cap(0);

    if(!cap.isOpened()){

        printf("capture err");

        return -1;

    }

    cv::Mat cv_img;

    std::vector<Object> objects;

    while(true){

        if(!cap.read(cv_img)){

            printf("cv_img err");

            return -1;

        }

        detect_MobileNetV2-yolov3(cv_img, objects);

        draw_objects(cv_img, objects);

        cv::imshow("video", cv_img);

        cv::waitKey(1);

    }

    cap.release();

    return 0;

}

THE END

目前测试效果还比较满意，但是每帧处理的时间需要0.3s左右，还不能实时，接下来的目标是达到实时检测，并尝试别推理框架，比如MNN和TNN。