feat 区分残点来源，日志+存图

AlgorithmModule/include/ImageAllResult.h

@@ -44,6 +44,13 @@ public:
         cv::Mat AI_mask;
     };
 
+    // 单个检测模型输出的 全图 mask，用于追溯 残点(blob) 由哪个模型检出
+    struct AI_Model_MaskImg
+    {
+        std::string strModelName; // 模型名称
+        cv::Mat ModelMask;        // 该模型输出的 全图 mask
+    };
+
 private:
     /* data */
 public:
@@ -87,6 +94,8 @@ public:
     std::shared_ptr<CameraBaseResult> cameraBaseResult;   // 相机相关的基本结果信息
 
     std::vector<std::shared_ptr<AI_Det_MaskImg>> AI_Qx_MaskList;
+    // 各检测模型独立的全图 mask 列表（与检测模型一一对应）
+    std::vector<std::shared_ptr<AI_Model_MaskImg>> AI_Model_MaskList;
     std::mutex mtx_Det; // 互斥量
 private:
     PRINT_LOG_ m_PrintLog;

AlgorithmModule/include/ImageDetConfig.h

@@ -27,6 +27,7 @@ struct QX_ERROR_INFO_
 	float fbreadth;
 	int nconfig_qx_type;
 	std::string qx_name;
+	std::string strModelName; // 检出该残点(blob)的模型名称
 	int maxValue;
 	int whiteOrBlack;
 	float grayDis;
@@ -53,6 +54,7 @@ struct QX_ERROR_INFO_
 		flen = 0;
 		nconfig_qx_type = 0;
 		qx_name = "";
+		strModelName = "";
 		maxValue = 0;
 		grayDis = 0;
 		fUpIou = 0;
@@ -79,6 +81,7 @@ struct QX_ERROR_INFO_
 				  << ", Flen: " << flen
 				  << ", nconfig_qx_type: " << nconfig_qx_type
 				  << ", QX Name: " << qx_name
+				  << ", Model Name: " << strModelName
 				  << ", Max Value: " << maxValue
 				  << ", Gray Dis: " << grayDis
 				  << ", fUpIou: " << fUpIou

AlgorithmModule/include/ImgCheckAnalysisy.hpp

@@ -198,6 +198,9 @@ private:
     // 把blob 汇总成  检测结果。
     int BLobToDetResult();
 
+    // 获取指定 残点(blob) 是由哪个(哪些)检测模型检出的
+    std::string GetBlobModelName(const cv::Rect &roi);
+
     //自适应参数区域更新
     int Adapt_Config(cv::RotatedRect tplOuterRect, cv::RotatedRect curOuterRect, cv::Mat& det_img);
 

AlgorithmModule/include/ImgCheckConfig.h

@@ -270,6 +270,13 @@ struct DetectInfo
 	}
 };
 
+// 残点检测模型名称：用于区分残点由哪个模型检出（存图分文件夹 + 日志追溯）
+#define AI_DET_MODEL_NAME_Defect "Defect"
+#define AI_DET_MODEL_NAME_QueXi "Defect_QueXi"
+#define AI_DET_MODEL_NAME_UnKnown "UnKnown"
+// 多个模型都检出同一个残点时的连接符
+#define AI_DET_MODEL_NAME_JOIN "+"
+
 struct QXImageResult
 {
 	int type;				 // 缺陷类型

AlgorithmModule/src/CheckResultJson.cpp

@@ -38,6 +38,7 @@ Json::Value CheckResultJson::toJsonValue()
 			value["flen"] = p->flen;
 			value["nconfig_qx_type"] = p->nconfig_qx_type;
 			value["qx_name"] = p->qx_name;
+			value["det_model_name"] = p->strModelName;
 			value["maxValue"] = p->maxValue;
 			value["grayDis"] = p->grayDis;
 			value["fUpIou"] = p->fUpIou;
@@ -117,6 +118,11 @@ void CheckResultJson::toObjectFromValue(Json::Value root)
 				tem.flen = errorJson["flen"].asFloat();
 				tem.nconfig_qx_type = errorJson["nconfig_qx_type"].asInt();
 				tem.qx_name = errorJson["qx_name"].asString();
+				// 旧版本 json 可能没有该字段
+				if (errorJson.isMember("det_model_name"))
+				{
+					tem.strModelName = errorJson["det_model_name"].asString();
+				}
 				tem.maxValue = errorJson["maxValue"].asInt();
 				tem.grayDis = errorJson["grayDis"].asFloat();
 				tem.fUpIou = errorJson["fUpIou"].asFloat();

AlgorithmModule/src/ImageResultJudge.cpp

@@ -173,9 +173,9 @@ int ImageResultJudge::ResultJudge(std::shared_ptr<ImageAllResult> pImageResult)
 		std::string qx_wb = WHITE_BLCAK_Names[QX_whiteBLACK];
 
 		pQxLog->AddCheckstr(PrintLevel_1,
-							"", "qxidx: %d   roi[%d %d  %d  %d]  qx %d %s %s JudgArea %f  hj %f len %f breadth %f energy %d region num %ld",
+							"", "qxidx: %d   roi[%d %d  %d  %d]  qx %d %s %s JudgArea %f  hj %f len %f breadth %f energy %d region num %ld  detModel: %s",
 							qxidx, roi.x, roi.y, roi.width, roi.height, config_qx_type, qx_name.c_str(), qx_wb.c_str(),
-							JudgArea, grayDis, flen, fbreadth, energy, QX_info->detRegionidxList.size());
+							JudgArea, grayDis, flen, fbreadth, energy, QX_info->detRegionidxList.size(), QX_info->strModelName.c_str());
 
 		cv::Point pCenter;
 		pCenter.x = roi.x + roi.width * 0.5;
@@ -559,7 +559,7 @@ int ImageResultJudge::ResultJudge(std::shared_ptr<ImageAllResult> pImageResult)
 
 				GetAIDetImg(pImageResult, pCenter, tem.AI_in_Img, tem.AI_out_img);
 				m_CheckResult_shareP->qxImageResult.push_back(tem);
-				pQxLog->AddCheckstr(PrintLevel_4, DET_LOG_LEVEL_3, " result ", " ---name: %s ---code: %s  ---srcImgroi.x: %d  ---srcImgroi.y: %d\n", tem.strTypeName.c_str(), tem.qx_Code.c_str(), tem.srcImgroi.x, tem.srcImgroi.y);
+				pQxLog->AddCheckstr(PrintLevel_4, DET_LOG_LEVEL_3, " result ", " ---name: %s ---code: %s  ---detModel: %s  ---srcImgroi.x: %d  ---srcImgroi.y: %d\n", tem.strTypeName.c_str(), tem.qx_Code.c_str(), QX_info->strModelName.c_str(), tem.srcImgroi.x, tem.srcImgroi.y);
 			}
 			else
 			{
@@ -572,6 +572,8 @@ int ImageResultJudge::ResultJudge(std::shared_ptr<ImageAllResult> pImageResult)
 				GetAIDetImg(pImageResult, pCenter, tem.AI_in_Img, tem.AI_out_img);
 
 				m_CheckResult_shareP->YS_ImageResult.push_back(tem);
+				// 疑似小图 也需要能追溯 是哪个模型检出的残点
+				pQxLog->AddCheckstr(PrintLevel_4, DET_LOG_LEVEL_3, " YS result ", " ---name: %s ---code: %s  ---detModel: %s  ---srcImgroi.x: %d  ---srcImgroi.y: %d\n", tem.strTypeName.c_str(), tem.qx_Code.c_str(), QX_info->strModelName.c_str(), tem.srcImgroi.x, tem.srcImgroi.y);
 			}
 		}
 	}
@@ -673,6 +675,8 @@ int ImageResultJudge::ResultJudge(std::shared_ptr<ImageAllResult> pImageResult)
 				
 					GetAIDetImg(pImageResult, pCenter, tem.AI_in_Img, tem.AI_out_img);
 					m_CheckResult_shareP->qxImageResult.push_back(tem);
+					// YS 转 NG 的残点也需要能追溯 是哪个模型检出的
+					pQxLog->AddCheckstr(PrintLevel_3, DET_LOG_LEVEL_3, " YS to NG img ", " ---name: %s ---code: %s  ---detModel: %s  ---srcImgroi.x: %d  ---srcImgroi.y: %d\n", tem.strTypeName.c_str(), tem.qx_Code.c_str(), QX_info->strModelName.c_str(), tem.srcImgroi.x, tem.srcImgroi.y);
 				}
 			}		
 		}

AlgorithmModule/src/ImgCheckAnalysisy.cpp

@@ -1346,6 +1346,11 @@ int ImgCheckAnalysisy::AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
 	pAIDetList.push_back(AI_Factory->Defect);
 	pAIDetList.push_back(AI_Factory->Defect_QueXi);
 
+	// 与 pAIDetList 一一对应的模型名称，用于区分残点由哪个模型检出
+	std::vector<std::string> pAIDetNameList;
+	pAIDetNameList.push_back(AI_DET_MODEL_NAME_Defect);
+	pAIDetNameList.push_back(AI_DET_MODEL_NAME_QueXi);
+
 
 	std::string strBaseLog = "AI_Detect";
 	m_pdetlog->AddCheckstr(PrintLevel_0, DET_LOG_LEVEL_3, strBaseLog, "AI_Detect  Start");
@@ -1396,6 +1401,14 @@ int ImgCheckAnalysisy::AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
 
 	ResultImg = cv::Mat::zeros(img.size(), CV_8UC1);
 
+	// 每个模型单独保存一份全图 mask，便于后续追溯残点由哪个模型检出
+	m_pImageAllResult->AI_Model_MaskList.clear();
+	std::vector<cv::Mat> modelMaskList(pAIDetList.size());
+	for (size_t m = 0; m < pAIDetList.size(); m++)
+	{
+		modelMaskList[m] = cv::Mat::zeros(img.size(), CV_8UC1);
+	}
+
 	const int totalTasks = SmallRoiList.size();
 
 	// std::string str_Root = m_strRootPath + pDetConfig->strProductID + "_" + pDetConfig->strchannel + "_";
@@ -1440,6 +1453,28 @@ int ImgCheckAnalysisy::AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
 					// 多个模型的结果取并集
 					cv::Mat roiMat = ResultImg(result->roi);
 					cv::bitwise_or(roiMat, outimg, roiMat);
+
+					// 当前模型自己的 mask 单独记录一份
+					if (m < modelMaskList.size() && !modelMaskList[m].empty())
+					{
+						cv::Mat modelRoiMat = modelMaskList[m](result->roi);
+						cv::bitwise_or(modelRoiMat, outimg, modelRoiMat);
+					}
+
+					// AI 检测残点图存图：每个模型的结果都存，并增加一级 模型名称 目录，
+					// 用以区分该残点是由哪个模型检出的
+					// 目录结构：/home/aidlux/BOE/ZB_SOCKET/AI_Detect/<模型名称>/<产品ID>/
+					if (m_pbaseCheckFunction->saveImg.bSaveAIDetImg)
+					{
+						std::string strModelName = (m < pAIDetNameList.size()) ? pAIDetNameList[m] : std::string(AI_DET_MODEL_NAME_UnKnown);
+						std::string roi_ext = "[" + std::to_string(result->roi.x) + "," + std::to_string(result->roi.y) + "]";
+						std::string strSaveDir = "/home/aidlux/BOE/ZB_SOCKET/AI_Detect/" + strModelName + "/" + DetImgInfo_shareP->strImgProductID + "/";
+						CheckUtil::CreateDir(strSaveDir);
+						std::string strSavePath_in = strSaveDir + m_strCurDetChannel + "_" + roi_ext + "_in.png";
+						std::string strSavePath_out = strSaveDir + m_strCurDetChannel + "_" + roi_ext + "_out.png";
+						cv::imwrite(strSavePath_in, result->input);
+						cv::imwrite(strSavePath_out, outimg);
+					}
 				}
 
 				// 同一 roi 的多个模型结果取并集后存入 AI_Qx_MaskList
@@ -1474,6 +1509,18 @@ int ImgCheckAnalysisy::AI_Detect_Thread(const cv::Mat &img, cv::Mat &ResultImg)
 	float mean_AI = (t3 - t2) / (SmallRoiList.size() * pAIDetList.size());
 	m_pdetlog->AddCheckstr(PrintLevel_1, DET_LOG_LEVEL_3, strBaseLog, " AI Run Time: sum  %ld  pre %ld Run %ld mean One Small Img %f", t3 - t1, t2 - t1, t3 - t2, mean_AI);
 
+	// 保存各模型的 全图 mask，并输出各模型检出的残点像素数量，便于追溯
+	for (size_t m = 0; m < modelMaskList.size(); m++)
+	{
+		std::shared_ptr<ImageAllResult::AI_Model_MaskImg> temModelMask = std::make_shared<ImageAllResult::AI_Model_MaskImg>();
+		temModelMask->strModelName = (m < pAIDetNameList.size()) ? pAIDetNameList[m] : std::string(AI_DET_MODEL_NAME_UnKnown);
+		temModelMask->ModelMask = modelMaskList[m];
+		m_pImageAllResult->AI_Model_MaskList.push_back(temModelMask);
+
+		m_pdetlog->AddCheckstr(PrintLevel_0, DET_LOG_LEVEL_3, strBaseLog, " Det Model: %s  mask pixel num  %d",
+							temModelMask->strModelName.c_str(), cv::countNonZero(temModelMask->ModelMask));
+	}
+
 	m_pdetlog->AddCheckstr(PrintLevel_0, DET_LOG_LEVEL_3, strBaseLog, "AI_Detect  End");
 
 	// 临时存图
@@ -2058,6 +2105,53 @@ int ImgCheckAnalysisy::Pin_Qx_Det(const cv::Mat &img)
 	return 0;
 }
 
+// 获取指定 残点(blob) 是由哪个(哪些)检测模型检出的
+// 做法：对各模型自己输出的全图 mask，在 blob 的 roi 内统计非零像素；
+// 非零则说明该模型在该残点区域有检出。多个模型都检出时用 "+" 连接。
+std::string ImgCheckAnalysisy::GetBlobModelName(const cv::Rect &roi)
+{
+	std::string strModelName = "";
+	if (!m_pImageAllResult)
+	{
+		return AI_DET_MODEL_NAME_UnKnown;
+	}
+
+	for (auto &pModelMask : m_pImageAllResult->AI_Model_MaskList)
+	{
+		if (!pModelMask || pModelMask->ModelMask.empty())
+		{
+			continue;
+		}
+
+		cv::Rect imgRoi = cv::Rect(0, 0, pModelMask->ModelMask.cols, pModelMask->ModelMask.rows);
+		cv::Rect cutRoi = roi & imgRoi;
+		if (cutRoi.width <= 0 || cutRoi.height <= 0)
+		{
+			continue;
+		}
+
+		cv::Mat roiMask = pModelMask->ModelMask(cutRoi);
+		if (cv::countNonZero(roiMask) > 0)
+		{
+			if (strModelName.empty())
+			{
+				strModelName = pModelMask->strModelName;
+			}
+			else
+			{
+				strModelName += AI_DET_MODEL_NAME_JOIN + pModelMask->strModelName;
+			}
+		}
+	}
+
+	if (strModelName.empty())
+	{
+		strModelName = AI_DET_MODEL_NAME_UnKnown;
+	}
+
+	return strModelName;
+}
+
 int ImgCheckAnalysisy::BLobToDetResult()
 {
 	long t1 = CheckUtil::getcurTime();
@@ -2078,6 +2172,9 @@ int ImgCheckAnalysisy::BLobToDetResult()
 		float fsecondArea = JudgArea;
 		std::string qx_name = CONFIG_QX_NAME_Names[config_qx_type];
 
+		// 追溯该残点(blob) 是由哪个检测模型检出的
+		std::string strModelName = GetBlobModelName(roi);
+
 		if (true)
 		{
 			QX_ERROR_INFO_ temerror;
@@ -2091,6 +2188,7 @@ int ImgCheckAnalysisy::BLobToDetResult()
 			temerror.fbreadth = blobs.blobTab[i].breadth;
 			temerror.nconfig_qx_type = config_qx_type;
 			temerror.qx_name = qx_name;
+			temerror.strModelName = strModelName;
 			temerror.maxValue = blobs.blobTab[i].maxValue;
 			temerror.grayDis = blobs.blobTab[i].grayDis;
 			temerror.density = blobs.blobTab[i].density;
@@ -2138,6 +2236,11 @@ int ImgCheckAnalysisy::BLobToDetResult()
 
 			m_pDetResult->pQx_ErrorList->push_back(temerror);
 
+			m_pdetlog->AddCheckstr(PrintLevel_1, DET_LOG_LEVEL_3, "BLobToDetResult",
+								   "blob idx %d  Qx Idx %d  qx %d %s  detModel %s  roi[%d %d %d %d]",
+								   i, temerror.Idx, config_qx_type, qx_name.c_str(), strModelName.c_str(),
+								   roi.x, roi.y, roi.width, roi.height);
+
 			// printf("- %s idx %d  a %f v %d h %f l %f\n", DetImgInfo_shareP->strChannel.c_str(), i, JudgArea, blobs.blobTab[i].maxValue, blobs.blobTab[i].grayDis, flen);
 		}
 	}

ConfigModule/include/CheckConfigDefine.h

@@ -1063,6 +1063,7 @@ struct Base_Function_SaveImg
 	bool bSaveMarkImg;	// mark 存图
 	bool bSaveClsImg;	// 分类 存图
 	bool bSaveAlginImg; // 分类 存图
+	bool bSaveAIDetImg; // AI 检测残点图 存图（每个模型单独一级目录）
 
 	Base_Function_SaveImg()
 	{
@@ -1074,6 +1075,7 @@ struct Base_Function_SaveImg
 		bSaveMarkImg = false;
 		bSaveClsImg = false;
 		bSaveAlginImg = false;
+		bSaveAIDetImg = false;
 	}
 
 	void copy(Base_Function_SaveImg tem)
@@ -1083,17 +1085,18 @@ struct Base_Function_SaveImg
 		this->bSaveMarkImg = tem.bSaveMarkImg;
 		this->bSaveClsImg = tem.bSaveClsImg;
 		this->bSaveAlginImg = tem.bSaveAlginImg;
+		this->bSaveAIDetImg = tem.bSaveAIDetImg;
 	}
 	void print(std::string str)
 	{
-		printf("%s>>bOpen %d  bSaveMarkImg %d bSaveClsImg %d bSaveAlginImg %d \n", str.c_str(),
+		printf("%s>>bOpen %d  bSaveMarkImg %d bSaveClsImg %d bSaveAlginImg %d bSaveAIDetImg %d \n", str.c_str(),
-			   bOpen, bSaveMarkImg, bSaveClsImg, bSaveAlginImg);
+			   bOpen, bSaveMarkImg, bSaveClsImg, bSaveAlginImg, bSaveAIDetImg);
 	}
 	std::string GetInfo(std::string str)
 	{
 		char buffer[256];
-		sprintf(buffer, "%s>>bOpen %d   bSaveMarkImg %d bSaveClsImg %d bSaveAlginImg %d \n", str.c_str(),
+		sprintf(buffer, "%s>>bOpen %d   bSaveMarkImg %d bSaveClsImg %d bSaveAlginImg %d bSaveAIDetImg %d \n", str.c_str(),
-				bOpen, bSaveMarkImg, bSaveClsImg, bSaveAlginImg);
+				bOpen, bSaveMarkImg, bSaveClsImg, bSaveAlginImg, bSaveAIDetImg);
 		std::string str123 = buffer;
 		return str123;
 	}

ConfigModule/src/JsonConfig.cpp

@@ -846,6 +846,10 @@ int BaseFuntonConfigJson::GetFunction(Json::Value value)
             {
                 _config.saveImg.bSaveAlginImg = value_f["form"]["SaveImg_Config"]["Align_Big_Save"].asBool();
             }
+            if (value_f["form"]["SaveImg_Config"]["AI_Det_Save"])
+            {
+                _config.saveImg.bSaveAIDetImg = value_f["form"]["SaveImg_Config"]["AI_Det_Save"].asBool();
+            }
         }
         else
         {