feat 初步添加传统检测

AlgorithmModule/include/ImgCheckAnalysisy.hpp

@@ -163,8 +163,12 @@ private:
     int ConfigCheck(cv::Mat img);
     // 多线程方式处理
     int AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg);
+    // 传统检测
+    int Traditional_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg);
     // 缺陷分类
     int AI_QX_Class_Thread();
+    // 传统分类
+    int Traditional_QX_Class_Thread();
 
     // 多线程 任务运行管理器
     int ThreadTask(int nId); // 运行;

AlgorithmModule/src/ImgCheckAnalysisy.cpp

@@ -678,7 +678,7 @@ int ImgCheckAnalysisy::CheckRun()
 	{
 		m_pImageAllResult->detImg = image(m_CutRoi).clone();
 	}
-	// 多线程开启 AI 推理检测
+	// 多线程开启 传统/AI 推理检测
 	long time_AI_s = CheckUtil::getcurTime();
 	m_AItask = std::make_shared<TaskInfo>();
 	m_AItask->taskname = Task_AI;
@@ -1294,6 +1294,40 @@ int ImgCheckAnalysisy::AIMaskDet()
 	m_ImgBlobHFlagData = new unsigned char[m_pImageAllResult->detImg.rows];
 	memset(m_ImgBlobHFlagData, 0, sizeof(unsigned char) * m_pImageAllResult->detImg.rows);
 
+	// 传统检测路径：等待异步任务完成后，计算HFlag
+	if(m_pBasicConfig->bTraditionalDetect)
+	{
+		m_AItask->waitComplate();
+		int rec = m_AItask->nresult;
+		if (rec != CHECK_OK)
+		{
+			return rec;
+		}
+		if (!m_pImageAllResult->AIMaskImg.empty())
+		{
+			unsigned char *pGrayErrordata = (unsigned char *)m_pImageAllResult->AIMaskImg.data;
+			int width = m_pImageAllResult->AIMaskImg.cols;
+			int height = m_pImageAllResult->AIMaskImg.rows;
+			for (int y = 0; y < height; y++)
+			{
+				if (m_ImgBlobHFlagData[y] == 0)
+				{
+					unsigned char *p = pGrayErrordata + y * width;
+					for (int x = 0; x < width; x++)
+					{
+						if (p[x] != 0)
+						{
+							m_ImgBlobHFlagData[y] = 1;
+							break;
+						}
+					}
+				}
+			}
+		}
+		m_CheckResult_shareP->resultMaskImg = m_pImageAllResult->AIMaskImg;
+		return 0;
+	}
+
 	while (true)
 	{
 		std::this_thread::sleep_for(std::chrono::milliseconds(1));
@@ -1577,6 +1611,25 @@ int ImgCheckAnalysisy::AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
 	return 0;
 }
 
+// ======================== 传统检测 ========================
+int ImgCheckAnalysisy::Traditional_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
+{
+	std::string strBaseLog = "Traditional_Detect";
+	m_pdetlog->AddCheckstr(PrintLevel_0, DET_LOG_LEVEL_3, strBaseLog, "Traditional_Detect  Start (placeholder)");
+
+	// 输出与AI推理相同格式的二值mask图 (CV_8UC1)
+	ResultImg = cv::Mat::zeros(img.size(), CV_8UC1);
+
+	// ===== TODO: 在此处调用传统检测算法库 =====
+	// 示例：cv::threshold(img, ResultImg, 128, 255, cv::THRESH_BINARY);
+	// 输入:  img (单通道灰度图, CV_8UC1)
+	// 输出:  ResultImg (二值mask, CV_8UC1, 0/255)
+	// ==========================================
+
+	m_pdetlog->AddCheckstr(PrintLevel_0, DET_LOG_LEVEL_3, strBaseLog, "Traditional_Detect  End (placeholder)");
+	return 0;
+}
+
 int ImgCheckAnalysisy::AI_QX_Class_Thread()
 {
 
@@ -1742,6 +1795,35 @@ int ImgCheckAnalysisy::AI_QX_Class_Thread()
 	return 0;
 }
 
+// ======================== 传统分类 ========================
+int ImgCheckAnalysisy::Traditional_QX_Class_Thread()
+{
+	m_pdetlog->AddCheckstr(PrintLevel_1, DET_LOG_LEVEL_3, "Traditional_Class", " Start (placeholder)");
+
+	int totalTasks = blobs.blobCount;
+	for (int i = 0; i < totalTasks; i++)
+	{
+		ERROR_DOTS_BLOB_DATA *pblob = &blobs.blobTab[i];
+
+		if (pblob->ErrType == ERR_TYPE_2)
+		{
+			pblob->AIclasstype = CONFIG_QX_NAME_cell_ymhs;
+		}
+		else
+		{
+			// ===== TODO: 在此处调用传统分类算法库 =====
+			// 输入:  pblob->minx/maxy/miny/maxy 定位的blob区域
+			//        m_pImageAllResult->detImg 原始检测图
+			// 输出:  pblob->AIclasstype (CONFIG_QX_NAME_cell_xxx)
+			// ==========================================
+			pblob->AIclasstype = CONFIG_QX_NAME_cell_other;
+		}
+	}
+
+	m_pdetlog->AddCheckstr(PrintLevel_1, DET_LOG_LEVEL_3, "Traditional_Class", " End (placeholder), classified %d blobs", totalTasks);
+	return 0;
+}
+
 int ImgCheckAnalysisy::ThreadTask(int nId)
 {
 
@@ -1791,11 +1873,19 @@ void ImgCheckAnalysisy::TaskFun_AIDet(std::shared_ptr<TaskInfo> task)
 {
 	task->SetStatus(TaskStep_run);
 	long t1, t2;
-	// AI 推理生成
+	// 检测：传统检测 / AI推理
 	{
 		t1 = CheckUtil::getcurTime();
 
-		int rec = AI_Detect_Thread(m_pImageAllResult->detImg, m_pImageAllResult->AIMaskImg);
+		int rec;
+		if(m_pBasicConfig->bTraditionalDetect)
+		{
+			rec = Traditional_Detect_Thread(m_pImageAllResult->detImg, m_pImageAllResult->AIMaskImg);
+		}
+		else
+		{
+			rec = AI_Detect_Thread(m_pImageAllResult->detImg, m_pImageAllResult->AIMaskImg);
+		}
 
 		t2 = CheckUtil::getcurTime();
 		task->nresult = rec;
@@ -1807,11 +1897,19 @@ void ImgCheckAnalysisy::TaskFun_QxClass(std::shared_ptr<TaskInfo> task)
 {
 	task->SetStatus(TaskStep_run);
 	long t1, t2;
-	// AI 推理生成
+	// 缺陷分类：传统检测 / AI推理
 	{
 		t1 = CheckUtil::getcurTime();
 
-		int rec = AI_QX_Class_Thread();
+		int rec;
+		if(m_pBasicConfig->bTraditionalDetect)
+		{
+			rec = Traditional_QX_Class_Thread();
+		}
+		else
+		{
+			rec = AI_QX_Class_Thread();
+		}
 
 		t2 = CheckUtil::getcurTime();
 		task->nresult = rec;

ConfigModule/include/CheckConfigDefine.h

@@ -407,6 +407,7 @@ struct BasicConfig
 	float Product_Size_Height_mm; // 产品尺寸 高度 mm
 	float fImage_Scale_x;		  // 成像精度
 	float fImage_Scale_y;		  // 成像精度
+	bool bTraditionalDetect;	  // 使用传统算法检测
 	std::string strCamName;		  //
 
 	float density_R_mm; // 密度计算半径 像素
@@ -427,6 +428,7 @@ struct BasicConfig
 		Product_Size_Height_mm = 1000;
 		fImage_Scale_x = 0.03;
 		fImage_Scale_y = 0.03;
+		bTraditionalDetect = false;
 		density_R_mm = 5;
 		strCamName = "";
 		strCamearName = EMPTY_CONFIG_NAME;
@@ -450,6 +452,7 @@ struct BasicConfig
 		this->Product_Size_Height_mm = tem.Product_Size_Height_mm;
 		this->fImage_Scale_x = tem.fImage_Scale_x;
 		this->fImage_Scale_y = tem.fImage_Scale_y;
+		this->bTraditionalDetect = tem.bTraditionalDetect;
 		this->density_R_mm = tem.density_R_mm;
 		this->strCamearName = tem.strCamearName;
 	}
@@ -458,6 +461,7 @@ struct BasicConfig
 		printf("============================↓↓↓↓↓↓%s↓↓ %s ↓↓↓↓↓=========================\n", str.c_str(), strCamearName.c_str());
 		printf("bCal_ImageScale %d  Product_Size_Width =%f Product_Size_Height =%f \n", bCal_ImageScale, Product_Size_Width_mm, Product_Size_Height_mm);
 		printf("fImage_Scale_x =%f fImage_Scale_y=%f \n", fImage_Scale_x, fImage_Scale_y);
+		printf("bTraditionalDetect %d  density_R_mm=%f \n", bTraditionalDetect, density_R_mm);
 		// printf("height_min =%d height_max=%d \n", height_min, height_max);
 		printf("bDrawShieldRoi  %d  bShield_ZF %d DrawPreRoi %d fUP_IOU %f  density_R_mm %f\n", bDrawShieldRoi, bShield_ZF, bDrawPreRoi, fUP_IOU, density_R_mm);
 		printf("============================↑↑↑↑↑↑%s↑↑↑↑↑↑=========================\n", str.c_str());

ConfigModule/src/JsonConfig.cpp

@@ -57,6 +57,7 @@ void CommonParamToCheckConfigJson::toObjectFromValue(Json::Value root)
                 _config.baseConfig.Product_Size_Height_mm = value["Product_Size_H"].asFloat();
                 _config.baseConfig.fImage_Scale_x = value["Image_Scale_X"].asFloat();
                 _config.baseConfig.fImage_Scale_y = value["Image_Scale_Y"].asFloat();
+                _config.baseConfig.bTraditionalDetect = value["bTraditionalDetect"].asFloat();
                 if (value["Density_R"])
                 {
                     _config.baseConfig.density_R_mm = value["Density_R"].asFloat();