【发布时间】：2020-10-15 23:14:30
【问题描述】：
如何读取相机并以相机帧速率显示图像？
我想从我的网络摄像头连续读取图像（进行一些快速预处理），然后在窗口中显示图像。这应该以我的网络摄像头提供的帧速率 (29 fps) 运行。 似乎 OpenCV GUI 和 Tkinter GUI 太慢了，无法以这样的帧速率显示图像。这些显然是我实验中的瓶颈。即使没有预处理，图像的显示速度也不够快。我在 MacBook Pro 2018 上。
这是我尝试过的。始终使用 OpenCV 读取网络摄像头：
- 一切都发生在主线程中，图像以 OpenCV 显示：12 fps
- 读取相机并在单独的线程中进行预处理，在主线程中使用 OpenCV 显示图像：20 fps
- 多线程如上，但不显示图像：29 fps
- 像上面一样多线程，但是用 Tkinter 显示图像：不知道确切的 fps，但感觉就像
代码如下：
单循环，OpenCV GUI：
import cv2
import time
def main():
cap = cv2.VideoCapture(0)
window_name = "FPS Single Loop"
cv2.namedWindow(window_name, cv2.WINDOW_NORMAL)
start_time = time.time()
frames = 0
seconds_to_measure = 10
while start_time + seconds_to_measure > time.time():
success, img = cap.read()
img = img[:, ::-1] # mirror
time.sleep(0.01) # simulate some processing time
cv2.imshow(window_name, img)
cv2.waitKey(1)
frames = frames + 1
cv2.destroyAllWindows()
print(
f"Captured {frames} in {seconds_to_measure} seconds. FPS: {frames/seconds_to_measure}"
)
if __name__ == "__main__":
main()
Captured 121 in 10 seconds. FPS: 12.1
多线程，opencv gui：
import logging
import time
from queue import Full, Queue
from threading import Thread, Event
import cv2
logger = logging.getLogger("VideoStream")
def setup_webcam_stream(src=0):
cap = cv2.VideoCapture(src)
width, height = (
cap.get(cv2.CAP_PROP_FRAME_WIDTH),
cap.get(cv2.CAP_PROP_FRAME_HEIGHT),
)
logger.info(f"Camera dimensions: {width, height}")
logger.info(f"Camera FPS: {cap.get(cv2.CAP_PROP_FPS)}")
grabbed, frame = cap.read() # Read once to init
if not grabbed:
raise IOError("Cannot read video stream.")
return cap
def video_stream_loop(video_stream: cv2.VideoCapture, queue: Queue, stop_event: Event):
while not stop_event.is_set():
try:
success, img = video_stream.read()
# We need a timeout here to not get stuck when no images are retrieved from the queue
queue.put(img, timeout=1)
except Full:
pass # try again with a newer frame
def processing_loop(input_queue: Queue, output_queue: Queue, stop_event: Event):
while not stop_event.is_set():
try:
img = input_queue.get()
img = img[:, ::-1] # mirror
time.sleep(0.01) # simulate some processing time
# We need a timeout here to not get stuck when no images are retrieved from the queue
output_queue.put(img, timeout=1)
except Full:
pass # try again with a newer frame
def main():
stream = setup_webcam_stream(0)
webcam_queue = Queue()
processed_queue = Queue()
stop_event = Event()
window_name = "FPS Multi Threading"
cv2.namedWindow(window_name, cv2.WINDOW_NORMAL)
start_time = time.time()
frames = 0
seconds_to_measure = 10
try:
Thread(
target=video_stream_loop, args=[stream, webcam_queue, stop_event]
).start()
Thread(
target=processing_loop, args=[webcam_queue, processed_queue, stop_event]
).start()
while start_time + seconds_to_measure > time.time():
img = processed_queue.get()
cv2.imshow(window_name, img)
cv2.waitKey(1)
frames = frames + 1
finally:
stop_event.set()
cv2.destroyAllWindows()
print(
f"Captured {frames} frames in {seconds_to_measure} seconds. FPS: {frames/seconds_to_measure}"
)
print(f"Webcam queue: {webcam_queue.qsize()}")
print(f"Processed queue: {processed_queue.qsize()}")
if __name__ == "__main__":
logging.basicConfig(level=logging.DEBUG)
main()
INFO:VideoStream:Camera dimensions: (1280.0, 720.0)
INFO:VideoStream:Camera FPS: 29.000049
Captured 209 frames in 10 seconds. FPS: 20.9
Webcam queue: 0
Processed queue: 82
在这里，您可以看到在第二个队列中剩余的图像被提取以显示它们。
当我取消注释这两行时：
cv2.imshow(window_name, img)
cv2.waitKey(1)
那么输出是：
INFO:VideoStream:Camera dimensions: (1280.0, 720.0)
INFO:VideoStream:Camera FPS: 29.000049
Captured 291 frames in 10 seconds. FPS: 29.1
Webcam queue: 0
Processed queue: 0
因此它能够以网络摄像头的速度处理所有帧，而无需 GUI 显示它们。
多线程，Tkinter gui：
import logging
import time
import tkinter
from queue import Full, Queue, Empty
from threading import Thread, Event
import PIL
from PIL import ImageTk
import cv2
logger = logging.getLogger("VideoStream")
def setup_webcam_stream(src=0):
cap = cv2.VideoCapture(src)
width, height = cap.get(cv2.CAP_PROP_FRAME_WIDTH), cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
logger.info(f"Camera dimensions: {width, height}")
logger.info(f"Camera FPS: {cap.get(cv2.CAP_PROP_FPS)}")
grabbed, frame = cap.read() # Read once to init
if not grabbed:
raise IOError("Cannot read video stream.")
return cap, width, height
def video_stream_loop(video_stream: cv2.VideoCapture, queue: Queue, stop_event: Event):
while not stop_event.is_set():
try:
success, img = video_stream.read()
# We need a timeout here to not get stuck when no images are retrieved from the queue
queue.put(img, timeout=1)
except Full:
pass # try again with a newer frame
def processing_loop(input_queue: Queue, output_queue: Queue, stop_event: Event):
while not stop_event.is_set():
try:
img = input_queue.get()
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img[:, ::-1] # mirror
time.sleep(0.01) # simulate some processing time
# We need a timeout here to not get stuck when no images are retrieved from the queue
output_queue.put(img, timeout=1)
except Full:
pass # try again with a newer frame
class App:
def __init__(self, window, window_title, image_queue: Queue, image_dimensions: tuple):
self.window = window
self.window.title(window_title)
self.image_queue = image_queue
# Create a canvas that can fit the above video source size
self.canvas = tkinter.Canvas(window, width=image_dimensions[0], height=image_dimensions[1])
self.canvas.pack()
# After it is called once, the update method will be automatically called every delay milliseconds
self.delay = 1
self.update()
self.window.mainloop()
def update(self):
try:
frame = self.image_queue.get(timeout=0.1) # Timeout to not block this method forever
self.photo = ImageTk.PhotoImage(image=PIL.Image.fromarray(frame))
self.canvas.create_image(0, 0, image=self.photo, anchor=tkinter.NW)
self.window.after(self.delay, self.update)
except Empty:
pass # try again next time
def main():
stream, width, height = setup_webcam_stream(0)
webcam_queue = Queue()
processed_queue = Queue()
stop_event = Event()
window_name = "FPS Multi Threading"
try:
Thread(target=video_stream_loop, args=[stream, webcam_queue, stop_event]).start()
Thread(target=processing_loop, args=[webcam_queue, processed_queue, stop_event]).start()
App(tkinter.Tk(), window_name, processed_queue, (width, height))
finally:
stop_event.set()
print(f"Webcam queue: {webcam_queue.qsize()}")
print(f"Processed queue: {processed_queue.qsize()}")
if __name__ == "__main__":
logging.basicConfig(level=logging.DEBUG)
main()
INFO:VideoStream:Camera dimensions: (1280.0, 720.0)
INFO:VideoStream:Camera FPS: 29.000049
Webcam queue: 0
Processed queue: 968
【问题讨论】：
-
您是否知道在 python 中“多线程”并不意味着“同时执行”，因为全局解释器锁？
-
是的，我知道这一点。我试图研究多处理，但偶然发现了更多问题。其中之一是，GUI 事件应该发生在主线程中。我也无法在单独的过程中读取相机。如果有使用多处理或不使用多线程的解决方案，那么我很高兴听到它。
-
我也不认为多处理是要走的路，通信我太复杂了（我怀疑它是否仍然足够高性能）。你需要找出你的脚本的哪一部分是慢的，然后看看你能做些什么。由于它在没有可视化的情况下以 30FPS 运行，我怀疑这可能是瓶颈。您可以尝试一下 Qt（通过它的一个 python 绑定），因为这既可以帮助您加快速度，又可以提供真正的多线程。我认为带有 GUI 的纯 python 解决方案对于 30FPS 来说不够快
-
也许将 OpenCV 与 Gstreamer 相结合是前进的方向，但它需要您重写几乎所有内容。
-
Kivy + gstreamer 怎么样？
kivy.core.camera.camera_gi可以使用与!链接的 gst 元素进行初始化...
标签： python python-3.x multithreading opencv tkinter