我正在尝试做一个图像识别项目,我唯一的问题是当我运行程序时视频/实时摄像头冻结,这只给我一帧可以使用。循环很可能会帮助我解决这个问题,但我试图将它添加到我的代码中,但我惨遭失败。我怎样才能正确地做到这一点,以免出现错误?
def show_vid():
cap1 = cv2.VideoCapture(0)
if not cap1.isOpened():
print("cant open the camera1")
flag1, frame1 = cap1.read()
frame1 = cv2.resize(frame1,(600,500))
bounding_box = cv2.CascadeClassifier('C:/Users/Andreea/anaconda3/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml')
gray_frame = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
num_faces = bounding_box.detectMultiScale(gray_frame,scaleFactor=1.3, minNeighbors=5)
for (x, y, w, h) in num_faces:
cv2.rectangle(frame1, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)
roi_gray_frame = gray_frame[y:y + h, x:x + w]
cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray_frame, (48, 48)), -1), 0)
prediction = emotion_model.predict(cropped_img)
maxindex = int(np.argmax(prediction))
cv2.putText(frame1, emotion_dict[maxindex], (x+20, y-60), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
show_text[0]=maxindex
if flag1 is None:
print ("Major error!")
elif flag1:
global last_frame1
last_frame1 = frame1.copy()
pic = cv2.cvtColor(last_frame1, cv2.COLOR_BGR2RGB)
img = Image.fromarray(pic)
imgtk = ImageTk.PhotoImage(image=img)
lmain.imgtk = imgtk
lmain.configure(image=imgtk)
lmain.after(10, show_vid)
if cv2.waitKey(1) & 0xFF == ord('q'):
exit()
我是新手,所以我不知道如何解决这个问题,我还在学习中。谢谢!
您遇到的问题是因为您没有连续读取相机的帧。您应该将帧读取和处理步骤移动到一个循环中。为此,我建议使用 while 循环。
这是带有 while 循环的修改后的代码:
def show_vid():
cap1 = cv2.VideoCapture(0)
if not cap1.isOpened():
print("cant open the camera1")
bounding_box = cv2.CascadeClassifier('C:/Users/Andreea/anaconda3/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml')
while True:
flag1, frame1 = cap1.read()
frame1 = cv2.resize(frame1,(600,500))
gray_frame = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
num_faces = bounding_box.detectMultiScale(gray_frame,scaleFactor=1.3, minNeighbors=5)
for (x, y, w, h) in num_faces:
cv2.rectangle(frame1, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)
roi_gray_frame = gray_frame[y:y + h, x:x + w]
cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray_frame, (48, 48)), -1), 0)
prediction = emotion_model.predict(cropped_img)
maxindex = int(np.argmax(prediction))
cv2.putText(frame1, emotion_dict[maxindex], (x+20, y-60), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
show_text[0]=maxindex
if flag1 is None:
print ("Major error!")
elif flag1:
global last_frame1
last_frame1 = frame1.copy()
pic = cv2.cvtColor(last_frame1, cv2.COLOR_BGR2RGB)
img = Image.fromarray(pic)
imgtk = ImageTk.PhotoImage(image=img)
lmain.imgtk = imgtk
lmain.configure(image=imgtk)
lmain.update_idletasks()
lmain.update()
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap1.release()
cv2.destroyAllWindows()