def import_video(video_mp4): # Video import cap = cv2.VideoCapture(video_mp4) # video is a series of images while True: success, img = cap.read() cv2.imgshow("Video", img) if cv2.waitkey(1) & 0xFF == ord('q'): # if q pressed, break out break
def run(self): """Runs the worm tracking algorithm indefinitely""" while True: #Grab image and display ret, img = self.camera.read() cv2.imgshow('Preview', img) #Threshold then compute contours ret, img_thresh = cv2.threshold(img, self.threshold, 255, cv2.THRESH_BINARY_INV) contours, hierarchy = cv2.findContours(img_thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) #Find the biggest contour worm_area = 0 for contour in contours: area = cv2.contourArea(contour) if area > worm_area: worm = contour worm_area = area #Compute the centroid of the worm contour moments = cv2.moments(worm) cx = int(moments['m10']/moments['m00']) cy = int(moments['m01']/moments['m00']) #If centroid within margin of image edge, move stage width = img.shape[0] height = img.shape[1] if cx < self.margin: self.microscope.move('x', -1*self.step_size) if cx > (width - self.margin): self.microscope.move('x', self.step_size) if cy < self.margin: self.microscope.move('y', -1*self.step_size) if cy > (height - self.margin): self.microscope.move('y', self.step_size)
import cv2 import sys cascPath = 'haarcascade_frontalface_default.xml' faceCascade = cv2.CascadeClassifier(cascPath) video_capture = cv2.VideoCapture(0) while True: ret, frame = video_capture.read() gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) faces = faceCascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30)) for (x, y, w, h) in faces: cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2) cv2.imgshow('image', frame) if cv2.waitKey(1) & 0xFF == ord('q'): break video_capture.release() cv2.destroyAllWindows()
output_dict['detection_scores'] = output_dict['detection_scores'][0] if 'detection_masks' in output_dict: output_dict['detection_masks'] = output_dict['detection_masks'][0] return output_dict # In[ ]: while True: ret,image_np = cap.read() # Expand dimensions since the model expects images to have shape: [1, None, None, 3] image_np_expanded = np.expand_dims(image_np, axis=0) # Actual detection. output_dict = run_inference_for_single_image(image_np, detection_graph) # Visualization of the results of a detection. vis_util.visualize_boxes_and_labels_on_image_array( image_np, output_dict['detection_boxes'], output_dict['detection_classes'], output_dict['detection_scores'], category_index, instance_masks=output_dict.get('detection_masks'), use_normalized_coordinates=True, line_thickness=8) cv2.imgshow('Obj detection', cv2.resize(800,400)) if cv2.waitKey(25)&0xFF == ord('q'): cv2.destroyAllWindows() cap.release() break
def callback(self, data): img_rgb = self.cvb.imgmsg_to_cv2(data, "bgr8") cv2.namedWindow('Camera_Feed') cv2.imgshow('Camera_Feed', img_rgb) cv2.imwrite('weapon_snapshot_colmustard.png', img_rgb)
# activate webcam to see the real moving object to be matched with the image database cap = cv2.VideoCapture(0) while True: success, img2 = cap.read() # copy img2 to new variable called imgOriginal imgOriginal = img2.copy() img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY) id = findID(img2, desList) if id != -1: cv2.putText(imgOriginal, classNames[id], (50, 50), cv2.FONT_HERSHEY_PLAIN, 1, (0, 0, 255), 2) cv2.imgshow("IMAGE TO BE TRAIN / DETECTED", imgOriginal) cv2.waitKey(1) # # see how many good matches the software got # # if the number is big then it is a good match (the img and the imgTrain) # print(len(good)) # # img3 = cv2.drawMatchesKnn(img, kpimg, imgTrain, kpimgTrain, good, None, flags=2) # # imgKpOri = cv2.drawKeypoints(img, kpimg, None) # imgKpTrain = cv2.drawKeypoints(imgTrain, kpimgTrain, None) # # # show the Keypoints that the orb algorithm found to be useful for matching process # # cv2.imshow("imgKpOri", imgKpOri) # # cv2.imshow("imgKpTrain", imgKpTrain) #
import cv2 import numpy as np filename = 'dog.jpg' img = cv2.imread(filename, 0) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) gray = np.float32(gray) dst = cv2.cornerHarris(gray, 2, 3, 0.04) dst = cv2.dilate(dst, None) img[dst > 0.01 * dst.max()] = [0, 0, 225] cv2.imgshow('dst', img) if cv2.waitKey(0) & 0xff == 27: cv2.destroyAllWindows()
import cv2 import numpy as np img = cv2.imread("image.jpg") # Dönüştürülecek resim boyutları width = 600 height = 700 # Çapraz bir resmin köşe pikselleri tespit edilir. points_1 = np.float32([[230, 1], [1, 472], [540, 150], [338, 617]]) points_2 = np.float32([[0, 0], [0, height], [width, 0], [width, height]]) # Perspeftif alma matrix = cv2.getPerspectiveTransform(points_1, points_2) # Dönüştürülmüş resim img_output = cv2.warpPerspective(img, matrix, (width, height)) cv2.imgshow("Yeni Resim", img_output)
# Video içe aktar cap = cv2.VideoCapture(video_name) print("Genişlik:", cap.get(3)) #Video genişliği print("Yükseklik:", cap.get(4)) #Video genişliği # Video açılmadığında veya boş olduğunda if cap.isOpened() == False: print("Hata") # Videoyu sürekli okuyabilmek için döngüye alınır. while True: # Frame = Video içerisinde oynayan her bir resim # Return = İşlemin başarılı, başarısız olduğunu döner. (True,False) ret, frame = cap.read() if ret == True: # Video hızlı aktığı için yavaşlatıyoruz. time.sleep(0.01) cv2.imgshow("Video:", frame) else: break # Klavyeden q tuşuna basıldığında videodan çıkar. if cv2.waitKey(1) & 0xFF == ord("q"): break # Video yakalama bırakılır. cap.relaese() cv2.destroyAllWindows()
import cv2 cap = cv2.VideoCapture(0) while(cap.isOpened()): ret, frame = cap.read() cv2.imgshow('frame', frame) if cv2.waitKey(1) & 0xFF == ord('q'): break cap.release() cv2.destroyAllWindows()
import cv2 # Dosya yolu yazılır. img = cv2.imread("image.jpg") # Resmi siyah beyaz (grayscale) aktarmak için 0 yazılır. img = cv2.imread("image.jpg", 0) # Görselleştirme cv2.imgshow("Resim Adi", img) # Esc tuşuna basıldığında resim kapanır. # s tuşuna basıldığında resim kaydedilir ve kapanır. close_key = cv2.waitKey(0) & 0xFF if close_key == 27: cv2.destroyAllWindows() elif close_key == ord('s'): cv2.imwrite("image_gray.png", img) cv2.destroyAllWindows()
import cv2 import numpy as np # path = r'C:\Users\Rebec\Projetos\Ficha 03 - PDI\Dark_Moon.jpg' # imagem = cv2.imread('Dark_Moon.jpg') #seleciona a imagem desejado imagem = cv2.imread('Dark_Moon.jpg') cv2.imgshow("Original", imagem) y = 0 x = 0 #cv2_imshow(im) #mostra a imagem no programa heigth = int(input("insira o valor da altura ", )) width = int(input("insir o valor da largura ", )) #dimensoes = (heigth, width) #essa parte daqui é para redimensionar a imagem mas não é oque a questao pede #image_resize = cv2.resize(imagem, dimensoes, interpolation = cv2.INTER_AREA) #cv2_imshow(image_resize) crop = imagem[y:y + heigth, x:x + width] cv2.imshow(crop, 'imagem')
# distance calculation # equations d = abs(Red – RedColor) + (Green – GreenColor) + (Blue – BlueColor) def getColorName(R, G, B): minimum = 10000 for i in range(len(csv)): d = abs(R - int(csv.loc[i, "R"])) + abs(G - int(csv.loc[i, "G"])) + abs(B - int(csv.loc[i, "B"])) if d <= minimum: minimum = d cname = csv.loc[i, "color_name"] return cname # display image on window for user to interact with while True: cv2.imgshow("image", img) if (clicked): # cv2.rectangle(image, startpoint, endpoint, color, thickness) -1 thickness fills rectangle entirely cv2.rectangle(img, (20, 20), (750, 60), (b, g, r), -1) # creates text string to display (color name and RGB values text = getColorName(r, g, b) + ' R=' + str(r) + ' G=' + str(g) + 'B=' + str(b) # cvs.putText(img,text,start,font(0-7),frontScale, color, thickness, lineType cv2.putText((img, text, (50, 50), 2, 0.8, (255, 255, 255), 2, cv2.LINE_AA)) # for very light colors txt will show in black cv2.putText(img, text, (50, 50), 2, 0.8, (0, 0, 0), 2, cv2.LINE_AA) if r + g + b >= 600: cv2.putText((img, text, (50, 50), 2, 0.8, (0, 0, 0), 2, cv2.LINE_AA)) clicked = False # break loop if user hits 'esc' key if cv2.waitKey(20): break
import cv2 # pip install opencv-python # https://github.com/opencv/opencv/blob/master/data/haarcascades/haarcascade_frontalface_default.xml face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') img = cv2.imread(r'C:\Users\Dell\Desktop\profile.jpg') img = cv2.resize(img, (500, 500)) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Detect faces faces = face_cascade.detectMultiScale(gray, 1.1, 4) # Draw rectangle around the faces for (x, y, w, h) in faces: cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2) cv2.imgshow('image', img) cv2.waitKey()