如何使用cv2.resize（）放大圖像時保持較高的FPS

Question

我正在運行一個簡單的代碼來測量我的實時流的FPS（使用網絡攝像頭）。 當我將圖像調整為較大的幀時，FPS會降低。 有什么方法可以同時放大框架（通過調整大小功能）來維持FPS。 還是不可避免的權衡？

這是使用face_recognition庫進行人臉識別的代碼。 當我將尺寸調整為較大尺寸時，FPS（每秒幀數）變慢。 有什么方法可以維持較高的FPS，同時也可以使用cv2.resize()放大圖像嗎？

import face_recognition
import cv2

video_capture = cv2.VideoCapture(0)
#video_capture.set(cv2.CAP_PROP_FPS, 30)
# Load a sample picture and learn how to recognize it.
obama_image = face_recognition.load_image_file("osama LinkedIN.jpg")

obama_face_encoding = face_recognition.face_encodings(obama_image)[0]


# Load a second sample picture and learn how to recognize it.
imran_shafqat_image = face_recognition.load_image_file("haris intern3.jpg")
imran_shafqat_face_encoding = face_recognition.face_encodings(imran_shafqat_image)[0]


# Create arrays of known face encodings and their names
known_face_encodings = [
    obama_face_encoding,
    imran_shafqat_face_encoding,
   # obama_face_encoding2
   # biden_face_encoding
]
known_face_names = [
    "Osama Naeem",
    "Imran Shafqat"
 #   "random guy2"
]

# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True
fxx = 1.5
fyy = 1.5
while True:
    # Grab a single frame of video
    ret, frame = video_capture.read()

    # Resize frame of video to 1/4 size for faster face recognition processing
    small_frame = cv2.resize(frame, (0, 0), fx=fxx, fy=fyy)

    # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
    rgb_small_frame = small_frame[:, :, ::-1]
    #rgb_small_frame = frame[:, :, ::-1]
    # Only process every other frame of video to save time
    if process_this_frame:
        # Find all the faces and face encodings in the current frame of video
        face_locations = face_recognition.face_locations(rgb_small_frame)
        face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

        face_names = []
        for face_encoding in face_encodings:
            # See if the face is a match for the known face(s)
            matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
            print ("match = ", matches)
            name = "Unknown"

            # If a match was found in known_face_encodings, just use the first one.
            if True in matches:
                first_match_index = matches.index(True)
                name = known_face_names[first_match_index]

            face_names.append(name)

    process_this_frame = not process_this_frame


    # Display the results
    for (top, right, bottom, left), name in zip(face_locations, face_names):
        # Scale back up face locations since the frame we detected in was scaled to 1/4 size
        top *= (1/fxx)
        right *= (1/fxx)
        bottom *= (1/fyy)
        left *= (1/fyy)

        # Draw a box around the face
        cv2.rectangle(frame, (round(left), round(top)), (round(right), round(bottom)), (0, 0, 255), 2)

        # Draw a label with a name below the face

        #cv2.rectangle(frame, (round(left) - 35, round(bottom) - 40), (round(right), round(bottom)), (0, 0, 255), cv2.FILLED)
        font = cv2.FONT_HERSHEY_DUPLEX
        cv2.putText(frame, name, (round(left) + 6, round(bottom) - 6), font, 0.5, (255, 255, 255), 1)

    # Display the resulting image
    cv2.imshow('Video', frame)

    # Hit 'q' on the keyboard to quit!
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()

代碼工作正常，但是當我將FPS放大到更大的尺寸時，我想以相同的速率保持FPS。

Answer 1

使用cv2.resize()放大圖像時，會創建一個較大的圖像，這會增加每幀的處理時間。 本質上，您的程序必須做其他工作才能處理更多像素。 但是，可能允許您提高FPS的解決方案是使用多線程 。 通過這種方法，您可以通過減少I / O延遲來提高FPS，而不是減少處理每個調整大小的幀所需的時間。 這個想法是在您在主線程中進行處理時，將閱讀框分成自己的獨立線程。 這是一個小部件，顯示了如何將閱讀框和處理分成單獨的線程。

from threading import Thread
import cv2, time

class VideoStreamWidget(object):
    def __init__(self, src=0):
        self.capture = cv2.VideoCapture(src)
        # Start the thread to read frames from the video stream
        self.thread = Thread(target=self.update, args=())
        self.thread.daemon = True
        self.thread.start()

    def update(self):
        # Read the next frame from the stream in a different thread
        while True:
            if self.capture.isOpened():
                (self.status, self.frame) = self.capture.read()
            time.sleep(.01)

    def show_frame(self):
        # Display frames in main program
        cv2.imshow('frame', self.frame)
        key = cv2.waitKey(1)
        if key == ord('q'):
            self.capture.release()
            cv2.destroyAllWindows()
            exit(1)

if __name__ == '__main__':
    video_stream_widget = VideoStreamWidget()
    while True:
        try:
            video_stream_widget.show_frame()
        except AttributeError:
            pass