import time from PyQt5.QtGui import QPixmap, QImage from PyQt5.QtWidgets import QWidget, QFileDialog,QMainWindow, QLabel, QSizePolicy, QApplication, QAction, QHBoxLayout from PyQt5.QtCore import * from PyQt5 import QtCore, QtGui, QtWidgets import sys import traceback import ctypes as C import numpy as np import cv2 import os from test_0415_ui import Ui_MainWindow from pyueye import ueye import numpy as np import cv2 # 串口通信 import serial import time import threading import torch from Class.Camera import Camera_class from Class.Motor import Motor_class from Class.Pan import Pan_class from Class.Yolo import yolo_class class img_yolo(QtCore.QThread): sinOut = pyqtSignal(str) # 聲明一個帶字串參數的信號 def __init__(self,yolo_model,parent=None): super().__init__(parent) self.yolo = yolo_model def normalize_image(self, img): if img is not None: normalized_image = cv2.normalize(img, None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX) return normalized_image return None def run(self): print('run') self.img_list = [] self.filename_list = [] for filename in os.listdir(r"./image_folder"): if filename.endswith('.jpg') or filename.endswith('.bmp'): img = cv2.imread('image_folder' + "/" + filename) self.img_list.append(img) self.filename_list.append(filename) # self.img_test(img, filename) print(f'img讀取完成') for i in range(0,len(self.filename_list)): img = self.img_list[i] file_name = self.filename_list[i] t1 = time.time() results = self.yolo.YoloDetect(img) t2 = time.time() print(f'推論時間 = {t2 - t1}') # print(results) print(f'{file_name}') # 檢查是否有預測結果 if results.pred[0] is None or len(results.pred[0]) == 0: continue # 獲取預測的信心值和類別 conf = results.pred[0][0, 4] # 取最高信心度 predicted_classes = results.names[int(results.pred[0][0, -1])] # 獲取 bounding box 的座標 box = results.pred[0][0, :4].cpu().numpy().astype(int) # 提取ROI (Region of Interest) roi = img[box[1]:box[3], box[0]:box[2]] # 正規化ROI圖像 normalized_roi = self.normalize_image(roi) # 將正規化的ROI轉換為灰度圖像 gray_roi = cv2.cvtColor(normalized_roi, cv2.COLOR_BGR2GRAY) # 創建CLAHE對象 clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(3, 3)) # 對灰度圖像應用CLAHE clahe_image = clahe.apply(gray_roi) # # 二值化處理 # _, binary_image = cv2.threshold(sharpened_image, 30, 255, cv2.THRESH_BINARY) # 形態學膨脹 # kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (8, 8)) #用這個 # dilated_image = cv2.dilate(binary_image, kernel, iterations=2) # closed_image = cv2.morphologyEx(binary_image, cv2.MORPH_CLOSE, kernel) #用這個 # opened_image = cv2.morphologyEx(binary_image, cv2.MORPH_OPEN, kernel) # 將圖像轉換為灰度格式 # gray_image = cv2.cvtColor(closed_image, cv2.COLOR_BGR2GRAY) # 找到輪廓 # contours, _ = cv2.findContours(closed_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 取得原圖檔名稱 base_name, ext = os.path.splitext(file_name) # 另存繪製後的ROI，檔名加上 '_2' new_file_name = f'{base_name}_2{ext}' print(f'Saving {new_file_name}') cv2.imwrite(f'img_2/{new_file_name}', clahe_image) # # 獲取最外圍輪廓 # if len(contours) > 0: # # 擬合最外圍輪廓為橢圓 # ellipse = cv2.fitEllipse(contours[0]) # # # 在原圖上繪製橢圓 # contour_image = roi.copy() # cv2.ellipse(contour_image, ellipse, (0, 255, 0), 1) # 使用綠色線條繪製橢圓 # # # 取得原圖檔名稱 # base_name, ext = os.path.splitext(file_name) # # # 另存繪製後的ROI，檔名加上 '_2' # new_file_name = f'{base_name}_2{ext}' # print(f'Saving {new_file_name}') # cv2.imwrite(f'img_2/{new_file_name}', sharpened_image) # # # 如果信心值超過0.6，則保存圖片 # if conf > 0.6: # resized_frame_high_conf = cv2.resize(results.render()[0], (1280, 1280)) # print(f'Saving {file_name}') # cv2.imwrite(f'img_2/{file_name}', resized_frame_high_conf) # else: # print("No contours found.") # # 如果信心值超過0.6，則保存圖片 # if conf > 0.6: # # 獲取 bounding box 的座標 # box = results.pred[0][0, :4].cpu().numpy().astype(int) # # # 保留原本的推論結果，另存原圖像 # print(f'Saving {file_name}') # cv2.imwrite(f'img_2/{file_name}', img) # # # 繪製 bounding box 在原圖上 # cv2.rectangle(img, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2) # 使用綠色線條繪製 # # # 調整圖像大小 # resized_frame = cv2.resize(img, (1280, 1280)) # # # 取得原圖檔名稱 # base_name, ext = os.path.splitext(file_name) # # # 另存繪製後的圖像，檔名加上 '_2' # new_file_name = f'{base_name}_2{ext}' # print(f'Saving {new_file_name}') # cv2.imwrite(f'img_2/{new_file_name}', resized_frame) # # else: # # 保留原本的推論結果，另存原圖像 # resized_frame = cv2.resize(results.render()[0], (1280, 1280)) # print(f'Saving {file_name}') # cv2.imwrite(f'img_2/{file_name}', resized_frame) def img_to_view(img):#原圖 img= cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # QT顏色顯示轉換 Ny, Nx, _ = img.shape img = QtGui.QImage(img.data, Nx, Ny,Nx*3, QtGui.QImage.Format_RGB888) #須改格式 return img class MainWindow(QMainWindow,Ui_MainWindow): def __init__(self, parent=None): #按鍵設定 super(MainWindow, self).__init__(parent) self.setupUi(self) # self.view_1.setScaledContents(True) # self.view_2.setScaledContents(True) # self.view_3.setScaledContents(True) # self.view_4.setScaledContents(True) self.bt_1.clicked.connect(self.bt_1_clicked) # self.bt_2.clicked.connect(self.bt_2_clicked) # 連接按鈕到新的功能 self.bt_3.clicked.connect(self.bt_3_clicked) self.cam = Camera_class() self.cam.start() self.cam.rawdata.connect(self.show_img) self.run_flag = True self.com5 = Motor_class() self.com5.start() self.com5.sinOut.connect(self.com5_str) self.com4 = Pan_class() self.com4.start() self.com4.sinOut.connect(self.com4_str) self.count = 0 self.img_count=0 self.yolo = yolo_class('weight/best.pt') #self.yolo.start() # self.img_test_2() def show_img(self,img): self.img = img h,w,_ = self.img.shape img= img_to_view(img) self.view_1.setPixmap(QtGui.QPixmap.fromImage(img)) def bt_1_clicked(self): self.time_2= time.time() self.com5.start_run() self.run_flag = True self.time_1 = time.time() def com5_str(self,str_1): if str_1 =='move': self.count = self.count+1 if self.count< 6: print(self.count) if str_1 == 'move': self.img_count = 0 self.com4.move() if self.count == 5: self.run_flag = False if str_1 =='2': # self.img_test() #self.time_1 = time.time() #print(f's={self.time_1-self.time_2}') # print('save_img') self.img_count = self.img_count+1 cv2.imwrite(f'image_folder\\{str(self.count)}_{self.img_count}.jpg',self.img) #self.time_2= time.time() def com4_str(self,str_1): if str_1 =='move_end' and self.run_flag == True: self.com5.start_run() if str_1 == 'Motor emergency stop 010': print('010') self.run_flag = False self.count = 0 time_2 = time.time() print(f'all_time - {time_2 - self.time_1}') self.bt_3_clicked() # def bt_3_clicked(self): # options = QFileDialog.Options() # options |= QFileDialog.ReadOnly # filePath, _ = QFileDialog.getOpenFileName(self, "選擇圖片", "", "圖片文件 (*.bmp *.jpg *.png);;所有文件 (*)", # options=options) # # print(filePath) # img = cv2.imread(filePath) # t1 = time.time() # results = self.yolo.YoloDetect(img) # t2=time.time() # # print(f'推論時間 = {t2-t1}') # # print(results) # # 檢查是否有預測結果 # if results.pred[0] is None or len(results.pred[0]) == 0: # # self.label1.setText("沒有瑕疵物件") # return # # # 獲取預測的類別 # predicted_classes = results.names[int(results.pred[0][0, -1])] # 取最高信心度的類別 # resized_frame = cv2.resize(results.render()[0], (1920, 1280)) # # print(resized_frame) # img = img_to_view(resized_frame) # self.view_2.setPixmap(QtGui.QPixmap.fromImage(img)) # # def img_test(self,img,file_name): # t1 = time.time() # results = self.yolo.YoloDetect(img) # t2 = time.time() # print(f'推論時間 = {t2 - t1}') # # print(results) # print(f'{file_name}') # # # 檢查是否有預測結果 # if results.pred[0] is None or len(results.pred[0]) == 0: # # self.label1.setText("沒有瑕疵物件") # return # # # 獲取預測的類別 # predicted_classes = results.names[int(results.pred[0][0, -1])] # 取最高信心度的類別 # resized_frame = cv2.resize(results.render()[0], (1920, 1280)) # # print(resized_frame) # # img = img_to_view(resized_frame) # # self.view_2.setPixmap(QtGui.QPixmap.fromImage(img)) # print(f'{file_name}') # cv2.imwrite(f'img_2/{file_name}', resized_frame) def img_test_2(self): img_list=[] for filename in os.listdir(r"./image_folder"): if filename.endswith('.jpg'): img = cv2.imread('image_folder' + "/" + filename) img_list.append(img) # self.img_test(img, filename) print(f'img讀取完成') run_list=[] for img in img_list: run_list.append(img_yolo( self.yolo,img)) for i in range (0,len(run_list)): run_list[i].start() def bt_3_clicked(self): self.T1 = img_yolo(self.yolo) self.T1.finished.connect(self.on_yolo_finished) # Connect to finished signal self.T1.start() def on_yolo_finished(self): img_confidence = {} # Dictionary to store confidence values for images # Load images from img_3 folder for filename in os.listdir(r"./img_2"): if filename.endswith('.jpg'): img_path = os.path.join("./img_2", filename) img = cv2.imread(img_path) img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) h, w, _ = img_rgb.shape qimg = QtGui.QImage(img_rgb.data, w, h, w * 3, QtGui.QImage.Format_RGB888) # Perform YOLO detection and get confidence value results = self.yolo.YoloDetect(img) if results.pred[0] is not None and len(results.pred[0]) > 0: conf = results.pred[0][0, 4] # Confidence value else: conf = 0 img_confidence[filename] = conf # Sort images by confidence value in descending order sorted_imgs = sorted(img_confidence.items(), key=lambda x: x[1], reverse=True) count = 0 # Count the number of displayed images # Display images in view_2, view_3, and view_4 based on confidence value for filename, _ in sorted_imgs: img_path = os.path.join("./img_2", filename) img = cv2.imread(img_path) img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) h, w, _ = img_rgb.shape qimg = QtGui.QImage(img_rgb.data, w, h, w * 3, QtGui.QImage.Format_RGB888) if not self.view_2.pixmap(): self.view_2.setPixmap(QtGui.QPixmap.fromImage(qimg)) count += 1 elif not self.view_3.pixmap(): self.view_3.setPixmap(QtGui.QPixmap.fromImage(qimg)) count += 1 elif not self.view_4.pixmap(): self.view_4.setPixmap(QtGui.QPixmap.fromImage(qimg)) count += 1 # Break the loop if displayed 3 images if count == 3: break if __name__ == "__main__": app = QApplication(sys.argv) window = MainWindow() window.show() sys.exit(app.exec_())