当前位置：首页 > news >正文

电动车进入电梯数据集、自行车进入电梯数据集电动车进入电梯VOC数据标注数据集

news 2024/12/29 23:58:34

一、项目来源

本项目作为一个小科研课题，分析当前电梯禁入电动车和自行车监控情况，搜集市场上的一些关键性，且有用的数据集，并对数据集进行了标注工作，数据集的格式声明：

数据集格式：Pascal VOC格式+YOLO格式(不包含分割路径的txt文件，仅仅包含jpg图片以及对应的VOC格式xml文件和yolo格式txt文件)：

图片数量(jpg文件个数)：7106
标注数量(xml文件个数)：7106
标注数量(txt文件个数)：7106
标注类别数：3
标注类别名称:["bicycle","motorcycle","person"]
每个类别标注的框数：
bicycle 框数 = 489
motorcycle 框数 = 5881
person 框数 = 8224
总框数：14594
使用标注工具：labelImg
标注规则：对类别进行画矩形框

二、项目实施

1、数据展示：

2、数据训练：

数据训练采用yolov8，训练过程可以参考我的另一个博客：

yolov8的模型训练

训练过程：

3、训练结果：

4、算法部署：

算法已经在windows和ubuntu的平台进行了部署工作，这里只对windows平台进行介绍：

工具准备：opencv4.9和Visual Studio Enterprise 2019

C++的检测代码如下，windows和ubuntu的区分标志为ON_M_WINDOWS：

代码的头文件：

#pragma once#define ON_M_WINDOWS 1#if ON_M_WINDOWS
#define  AIM_DetectAPI_DLL __declspec(dllexport)
#endif#define  MAX_M_Detect_COUNT 200
#define  MAX_M_POLY_POINT_COUNT 10
#define  MAX_M_POLYS_COUNT 5
typedef void* AIM_Engine;//错误信息标识
typedef enum
{AI_ERROR_SUCESS = 0,//成功AI_ERROR_NULLRETURN = 1, //空指针返回AI_ERROR_SOFTDOG = 2, //加密狗异常AI_ERROR_GPU_PROCESS, //GPU处理空间申请错误AI_ERROR_MODELSPACE,//模型空间申请错误AI_ERROR_RULESPARAMER,//规则参数错误AI_ERROR_IMAGEPARAMER,//图像参数错误AI_ERROR_IMAGE_FILE,图片路径参数错误AI_ERROR_MODELPATH//模型路径错误
}AIM_Error;typedef struct _AIM_PointF
{float x;float y;
}AIM_PointF;typedef struct _AIM_Poly
{int nPoints;AIM_PointF points[MAX_M_POLY_POINT_COUNT];
}AIM_Poly;typedef struct _AIM_InParam
{int n_CameraID; //相机IDint n_ImageID; //图像ID唯一float f_Confidence; //检测到目标的置信度(0.0-1.0),默认0.5int n_MinObjectSize; //检查的最小目标尺寸(取值范围：50-100010),默认100int nPolyCount; //设置检测区域 其中nPolyCount=0，表示全图像分析AIM_Poly polys[MAX_M_POLYS_COUNT];
}AIM_InParam;typedef struct _AIM_InImage
{int imageType; //0--bgrbgr...,1--rgbrgb...int width; //图像宽 ,需要4的倍数int height; //图像高int channels; //图像通道数，只支持1-gray和3-rgb通道char* data; //图像数据bgrbgr...
}AIM_InImage;typedef struct _AIM_Rect
{float f_Confidence; //检测到目标的置信度int n_Type; //0-'bicycle', 1-'motorcycle',2-'person'int n_Left; //目标rect--左上点x的相对坐标int n_Right; //目标rect--左上点y的相对坐标int n_Top; //目标rect--右下点x的相对坐标int n_Bottom; //目标rect--右下点y的相对坐标int n_CentreX; //rect 中心xint n_CentreY; //rect 中心y
}AIM_Rect;typedef struct _AIM_ResultInfo
{int n_CameraID;//相机IDint n_ImageID;//图像ID唯一int n_ObjectCount;AIM_Rect rects[MAX_M_Detect_COUNT];
}AIM_ResultInfo;#ifdef __cplusplus
extern "C"
{
#endif#if ON_M_WINDOWS/******新接口调用*****先创建一个算法句柄，注：程序开始时只需调用一次n_UseGPU; //cpu = 0,gpu需要N卡且需要重新编译opencv库，默认0 ---- 若申请GPU处理失败，会改用CPU处理n_GPU_ID--指定在哪个GPU卡上运行（n_UseGPU设置为0时，该值不考虑），从0开始，如0，1，2....pModel_Path; //文件名字为AIDetect.modelpError; //状态返回值，需要查看一下，看看模型和GPU是否错误AIM_DetectAPI_DLL AIM_Engine AIM_EngineCreate(int n_UseGPU, int n_GPU_ID, char *pModel_Path, AIM_Error *pError);//先调用1算法执行程序pEngine算法句柄inParam算法输入参数outInfo算法输出参数AIM_DetectAPI_DLL AIM_Error AIM_EngineImageFileAnalyze(AIM_Engine pEngine, AIM_InParam*inParam, AIM_InImage *pImage,AIM_ResultInfo *outInfo);//再调用2算法销毁注：程序结束时只需调用一次AIM_DetectAPI_DLL AIM_Error AIM_EngineDestroy(AIM_Engine pEngine);//最后调用3#else/******新接口调用*****先创建一个算法句柄，注：程序开始时只需调用一次AIM_Engine AIM_EngineCreate(int n_UseGPU, int n_GPU_ID, char* pModel_Path, AIM_Error* pError);//先调用1算法执行程序pEngine算法句柄inParam算法输入参数outInfo算法输出参数AIM_Error AIM_EngineImageFileAnalyze(AIM_Engine pEngine, AIM_InParam* inParam, AIM_InImage* pImage, AIM_ResultInfo* outInfo);//再调用2算法销毁注：程序结束时只需调用一次AIM_Error AIM_EngineDestroy(AIM_Engine pEngine);//最后调用3#endif#ifdef __cplusplus
}
#endif

算法的测试部分：

// AlgTest.cpp : Defines the entry point for the console application.
//#include <fstream>
#include <sstream>
#include "opencv2/opencv.hpp"
#include "MotorcycleDetectAPI.h"#if ON_M_WINDOWS
#include "stdafx.h"
#include <windows.h>
#include <stdio.h>
#include <io.h>
#include <thread>
#include <vector>
#else
#include <chrono>
#include <iomanip>
#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
#include <dirent.h>
#include <unistd.h>
#endifusing namespace std;
using namespace cv;AIM_Engine g_AIEngine;#if ON_M_WINDOWS
int getFiles(std::string path, std::vector<std::string>& files, std::vector<std::string>& names)
{int i = 0;intptr_t hFile = 0;struct _finddata_t c_file;std::string imageFile = path + "*.*";if ((hFile = _findfirst(imageFile.c_str(), &c_file)) == -1L){_findclose(hFile);return -1;}else{while (true){std::string strname(c_file.name);if (std::string::npos != strname.find(".jpg") || std::string::npos != strname.find(".png") || std::string::npos != strname.find(".bmp")){std::string fullName = path + c_file.name;files.push_back(fullName);std::string cutname = strname.substr(0, strname.rfind("."));names.push_back(cutname);}if (_findnext(hFile, &c_file) != 0){_findclose(hFile);break;}}}return 0;
}
#else
int getFiles(char* path, std::vector<std::string>& files, std::vector<std::string>& names)
{DIR* dir;dir = opendir(path);struct dirent* ptr;files.clear();while ((ptr = readdir(dir)) != NULL){if (ptr->d_name[0] == '.') { continue; }std::string fullpath = path;fullpath = fullpath + ptr->d_name;printf("path = %s\n", fullpath.c_str());files.push_back(fullpath);names.push_back(ptr->d_name);}closedir(dir);return 0;
}
#endifvoid imageTest(int argc, char *argv[])
{AIM_Error error = AI_ERROR_SUCESS;AIM_InParam inParam;AIM_InImage inImage;AIM_ResultInfo outInfo;//使用前先初始化一下memset(&inParam,0,sizeof(AIM_InParam));memset(&inImage, 0, sizeof(AIM_InImage));memset(&outInfo, 0, sizeof(AIM_ResultInfo));//char* pClasses[5] = { "person", "car", "cat", "dog", "ladder" };char* pClasses[3] = {"bicycle","motorcycle","person"};std::vector<std::string> classes;for (int i = 0; i < 1; i++){classes.push_back(pClasses[i]);}//初始化函数句柄，可以在函数开始阶段创建多个句柄g_AIEngine = AIM_EngineCreate(0, 0, "../bin/Moctorcycle.onnx", &error);//1if (error != AI_ERROR_SUCESS)//注意是否返回异常{printf("error id = %d\n", error);}std::vector<std::string> files;std::vector<std::string> names;char* path = "./test/";std::string save_path = "./result/";getFiles(path, files, names);//加载文加下的图像路径//对参数进行赋值inParam.n_CameraID = 123456;inParam.n_ImageID = 5678;inParam.f_Confidence = 0.25;inParam.n_MinObjectSize = 50;inParam.nPolyCount = 0;inParam.polys[0].nPoints = 4;inParam.polys[0].points[0].x = 0.2;inParam.polys[0].points[0].y = 0.2;inParam.polys[0].points[1].x = 0.8;inParam.polys[0].points[1].y = 0.2;inParam.polys[0].points[2].x = 0.8;inParam.polys[0].points[2].y = 0.8;inParam.polys[0].points[3].x = 0.2;inParam.polys[0].points[3].y = 0.8;inParam.polys[1].nPoints = 5;inParam.polys[1].points[0].x = 0.1;inParam.polys[1].points[0].y = 0.2;inParam.polys[1].points[1].x = 0.5;inParam.polys[1].points[1].y = 0.2;inParam.polys[1].points[2].x = 0.85;inParam.polys[1].points[2].y = 0.15;inParam.polys[1].points[3].x = 0.9;inParam.polys[1].points[3].y = 0.9;inParam.polys[1].points[4].x = 0.1;inParam.polys[1].points[4].y = 0.9;int i = 0, j = 0;for (i = 0; i < files.size(); i++){cv::Mat image = cv::imread(files[i]);if (image.empty()){continue;}//对图像数据进行赋值inImage.width = image.cols;inImage.height = image.rows;inImage.channels = image.channels();inImage.data = (char*)image.data;inImage.imageType = 0;clock_t start, end;float time;start = clock();//函数分析，基于函数句柄进行分析int ret_Ana = AIM_EngineImageFileAnalyze(g_AIEngine,  &inParam, &inImage, &outInfo);//2printf("ret_Ana value = %d\n", ret_Ana);end = clock();time = (float)(end - start);//CLOCKS_PER_SEC; printf("timeCount = %f\n", time);//测试时间int step = 10;for (int j = 0; j < outInfo.n_ObjectCount; j++)//结果解析{step = j*step;AIM_Rect*rect = &outInfo.rects[j];int txtLeft = rect->n_Left;int txtTop = rect->n_Top + step;txtTop = txtTop < 20 ? 20 : txtTop;txtLeft = txtLeft < 20 ? 20 : txtLeft;txtTop = txtTop > image.rows - 20 ? image.rows - 20 : txtTop;txtLeft = txtLeft > image.cols - 20 ? image.cols - 20 : txtLeft;if (0 == rect->n_Type){cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(0, 0, 255), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(0, 0, 255), 1, 8);}else if (1 == rect->n_Type){cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(0, 255, 0), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(0, 255, 0), 1, 8);}else if (2 == rect->n_Type){cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(0, 255, 255), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(0, 255, 255), 1, 8);}else if (3 == rect->n_Type){cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(255, 255, 0), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(255, 255, 0), 1, 8);}else if (4 == rect->n_Type){cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(255, 0, 255), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(255, 0, 255), 1, 8);}else{cv::putText(image, pClasses[rect->n_Type], cv::Point(txtLeft, txtTop), cv::FONT_HERSHEY_SIMPLEX, 0.8, cv::Scalar(250, 11, 230), 1);rectangle(image, Point(rect->n_Left, rect->n_Top), Point(rect->n_Right, rect->n_Bottom), Scalar(250, 11, 230), 1, 8);}}cout << "image -- " << names[i] << " -- process OK!!!" << endl;std::string save_name = save_path + names[i] + ".jpg";cv::imwrite(save_name, image);#if ON_WINDOWScv::Mat resieImage;cv::resize(image, resieImage, cv::Size(image.cols, image.rows));cv::imshow("image", resieImage);cv::waitKey(100);
#endif}结束时销毁句柄AIM_EngineDestroy(g_AIEngine);//3
}int main(int argc, char *argv[])
{imageTest(argc, argv);return 0;
}

算法的工程测试部分截图：