如何使用 Python 和 PyObjC 从 Apple iSight 捕获帧？

Question

我正在尝试使用 Python（2.7 或 2.6 版）和 PyObjC（2.2 版）从 Macbook Pro 内置的 Apple iSight 摄像头捕获单帧。

作为起点，我使用了this old StackOverflow 问题。为了验证它是否有意义，我交叉引用了它似乎基于的 Apple's MyRecorder 示例。不幸的是，我的脚本不起作用。

我的主要问题是：

• 我是否正确初始化了相机？
• 我是否正确启动了事件循环？
• 还有其他我应该做的设置吗？

在下面粘贴的示例脚本中，预期的操作是在调用 startImageCapture() 之后，我应该开始打印来自 CaptureDelegate 的“Got a frame...”消息。但是，相机的灯永远不会打开，并且代理的回调永远不会执行。

另外，startImageCapture() 过程中没有失败，所有函数都声称成功，并且成功找到了 iSight 设备。分析 pdb 中的 session 对象表明它有有效的输入和输出对象，输出分配了一个委托，设备没有被其他进程使用，并且在调用 startRunning() 后会话被标记为正在运行。

代码如下：

#!/usr/bin/env python2.7

import sys
import os
import time
import objc
import QTKit
import AppKit
from Foundation import NSObject
from Foundation import NSTimer
from PyObjCTools import AppHelper
objc.setVerbose(True)

class CaptureDelegate(NSObject):
    def captureOutput_didOutputVideoFrame_withSampleBuffer_fromConnection_(self, captureOutput, 
                                                                           videoFrame, sampleBuffer, 
                                                                           connection):
        # This should get called for every captured frame
        print "Got a frame: %s" % videoFrame

class QuitClass(NSObject):
    def quitMainLoop_(self, aTimer):
        # Just stop the main loop.
        print "Quitting main loop."
        AppHelper.stopEventLoop()


def startImageCapture():
    error = None

    # Create a QT Capture session
    session = QTKit.QTCaptureSession.alloc().init()

    # Find iSight device and open it
    dev = QTKit.QTCaptureDevice.defaultInputDeviceWithMediaType_(QTKit.QTMediaTypeVideo)
    print "Device: %s" % dev
    if not dev.open_(error):
        print "Couldn't open capture device."
        return

    # Create an input instance with the device we found and add to session
    input = QTKit.QTCaptureDeviceInput.alloc().initWithDevice_(dev)
    if not session.addInput_error_(input, error):
        print "Couldn't add input device."
        return

    # Create an output instance with a delegate for callbacks and add to session
    output = QTKit.QTCaptureDecompressedVideoOutput.alloc().init()
    delegate = CaptureDelegate.alloc().init()
    output.setDelegate_(delegate)
    if not session.addOutput_error_(output, error):
        print "Failed to add output delegate."
        return

    # Start the capture
    print "Initiating capture..."
    session.startRunning()


def main():
    # Open camera and start capturing frames
    startImageCapture()

    # Setup a timer to quit in 10 seconds (hack for now)
    quitInst = QuitClass.alloc().init()
    NSTimer.scheduledTimerWithTimeInterval_target_selector_userInfo_repeats_(10.0, 
                                                                             quitInst, 
                                                                             'quitMainLoop:', 
                                                                             None, 
                                                                             False)
    # Start Cocoa's main event loop
    AppHelper.runConsoleEventLoop(installInterrupt=True)

    print "After event loop"


if __name__ == "__main__":
    main()

感谢您提供的任何帮助！

Answer 1

好的，我花了一天时间深入研究 PyObjC 并让它工作。

为了将来记录，问题中的代码不起作用的原因：变量范围和垃圾收集。 session 变量在超出范围时被删除，这发生在事件处理器运行之前。必须做一些事情来保留它，以便在它有时间运行之前不会被释放。

将所有内容移动到一个类中并使 session 成为一个类变量使回调开始工作。此外，下面的代码演示了将帧的像素数据转换为位图格式并通过 Cocoa 调用保存，以及如何将其作为缓冲区或字符串复制回 Python 的世界视图。

下面的脚本将捕获单个帧

#!/usr/bin/env python2.7
#
# camera.py -- by Trevor Bentley (02/04/2011)
# 
# This work is licensed under a Creative Commons Attribution 3.0 Unported License.
#
# Run from the command line on an Apple laptop running OS X 10.6, this script will
# take a single frame capture using the built-in iSight camera and save it to disk
# using three methods.
#

import sys
import os
import time
import objc
import QTKit
from AppKit import *
from Foundation import NSObject
from Foundation import NSTimer
from PyObjCTools import AppHelper

class NSImageTest(NSObject):
    def init(self):
        self = super(NSImageTest, self).init()
        if self is None:
            return None

        self.session = None
        self.running = True

        return self

    def captureOutput_didOutputVideoFrame_withSampleBuffer_fromConnection_(self, captureOutput, 
                                                                           videoFrame, sampleBuffer, 
                                                                           connection):
        self.session.stopRunning() # I just want one frame

        # Get a bitmap representation of the frame using CoreImage and Cocoa calls
        ciimage = CIImage.imageWithCVImageBuffer_(videoFrame)
        rep = NSCIImageRep.imageRepWithCIImage_(ciimage)
        bitrep = NSBitmapImageRep.alloc().initWithCIImage_(ciimage)
        bitdata = bitrep.representationUsingType_properties_(NSBMPFileType, objc.NULL)

        # Save image to disk using Cocoa
        t0 = time.time()
        bitdata.writeToFile_atomically_("grab.bmp", False)
        t1 = time.time()
        print "Cocoa saved in %.5f seconds" % (t1-t0)

        # Save a read-only buffer of image to disk using Python
        t0 = time.time()
        bitbuf = bitdata.bytes()
        f = open("python.bmp", "w")
        f.write(bitbuf)
        f.close()
        t1 = time.time()
        print "Python saved buffer in %.5f seconds" % (t1-t0)

        # Save a string-copy of the buffer to disk using Python
        t0 = time.time()
        bitbufstr = str(bitbuf)
        f = open("python2.bmp", "w")
        f.write(bitbufstr)
        f.close()
        t1 = time.time()
        print "Python saved string in %.5f seconds" % (t1-t0)

        # Will exit on next execution of quitMainLoop_()
        self.running = False

    def quitMainLoop_(self, aTimer):
        # Stop the main loop after one frame is captured.  Call rapidly from timer.
        if not self.running:
            AppHelper.stopEventLoop()

    def startImageCapture(self, aTimer):
        error = None
        print "Finding camera"

        # Create a QT Capture session
        self.session = QTKit.QTCaptureSession.alloc().init()

        # Find iSight device and open it
        dev = QTKit.QTCaptureDevice.defaultInputDeviceWithMediaType_(QTKit.QTMediaTypeVideo)
        print "Device: %s" % dev
        if not dev.open_(error):
            print "Couldn't open capture device."
            return

        # Create an input instance with the device we found and add to session
        input = QTKit.QTCaptureDeviceInput.alloc().initWithDevice_(dev)
        if not self.session.addInput_error_(input, error):
            print "Couldn't add input device."
            return

        # Create an output instance with a delegate for callbacks and add to session
        output = QTKit.QTCaptureDecompressedVideoOutput.alloc().init()
        output.setDelegate_(self)
        if not self.session.addOutput_error_(output, error):
            print "Failed to add output delegate."
            return

        # Start the capture
        print "Initiating capture..."
        self.session.startRunning()


    def main(self):
        # Callback that quits after a frame is captured
        NSTimer.scheduledTimerWithTimeInterval_target_selector_userInfo_repeats_(0.1, 
                                                                                 self, 
                                                                                 'quitMainLoop:', 
                                                                                 None, 
                                                                                 True)

        # Turn on the camera and start the capture
        self.startImageCapture(None)

        # Start Cocoa's main event loop
        AppHelper.runConsoleEventLoop(installInterrupt=True)

        print "Frame capture completed."

if __name__ == "__main__":
    test = NSImageTest.alloc().init()
    test.main()

Answer 2

QTKit 已弃用，PyObjC 是一个很大的依赖项（如果你想在 HomeBrew 中构建它似乎很棘手）。加上PyObjC 没有大部分AVFoundation，所以我创建了a simple camera extension for Python，它使用AVFoundation 来录制视频或拍照，它不需要依赖（Cython 中间文件被提交以避免需要 Cython大多数用户）。

应该可以这样构建：

pip install -e git+https://github.com/dashesy/pyavfcam.git

那我们就可以用它来take a picture:

import pyavfcam

# Open the default video source
cam = pyavfcam.AVFCam(sinks='image')
frame = cam.snap_picture('test.jpg')  # frame is a memory buffer np.asarray(frame) can retrieve

与本题无关，但如果AVFCam类被子类化，会调用被覆盖的方法，并带有结果。