Jetson Xavier NX下读取RTSP视频流

现有一个网络摄像机，需要在Jetson Xavier NX平台上读取它的视频流进行图像处理，最基本的使用Opencv读取RTSP视频流代码如下：

import cv2
cap = cv2.VideoCapture("rtsp://192.168.1.1:554/")
while True:
	ret , frame = cap.read()
	cv2.imshow("Test" , frame)
	if chr(cv2.waitkey(1)&255)=='q'
		break

这样简单粗暴的读取视频流会产生较大的延时，或者是图像帧会累加，导致画面不同步，找到了如下解决办法，使用GSTREAMER去硬解码视频流：
https://gist.github.com/jkjung-avt/86b60a7723b97da19f7bfa3cb7d2690e

import sys
import argparse
import subprocess

import cv2


WINDOW_NAME = 'CameraDemo'


def parse_args():
    # Parse input arguments
    desc = 'Capture and display live camera video on Jetson TX2/TX1'
    parser = argparse.ArgumentParser(description=desc)
    parser.add_argument('--rtsp', dest='use_rtsp',
                        help='use IP CAM (remember to also set --uri)',
                        action='store_true')
    parser.add_argument('--uri', dest='rtsp_uri',
                        help='RTSP URI, e.g. rtsp://192.168.1.64:554',
                        default=None, type=str)
    parser.add_argument('--latency', dest='rtsp_latency',
                        help='latency in ms for RTSP [200]',
                        default=200, type=int)
    parser.add_argument('--usb', dest='use_usb',
                        help='use USB webcam (remember to also set --vid)',
                        action='store_true')
    parser.add_argument('--vid', dest='video_dev',
                        help='device # of USB webcam (/dev/video?) [1]',
                        default=1, type=int)
    parser.add_argument('--width', dest='image_width',
                        help='image width [1920]',
                        default=1920, type=int)
    parser.add_argument('--height', dest='image_height',
                        help='image height [1080]',
                        default=1080, type=int)
    args = parser.parse_args()
    return args


def open_cam_rtsp(uri, width, height, latency):
    gst_str = ('rtspsrc location={} latency={} ! '
               'rtph264depay ! h264parse ! omxh264dec ! '
               'nvvidconv ! '
               'video/x-raw, width=(int){}, height=(int){}, '
               'format=(string)BGRx ! '
               'videoconvert ! appsink').format(uri, latency, width, height)
    return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)


def open_cam_usb(dev, width, height):
    # We want to set width and height here, otherwise we could just do:
    #     return cv2.VideoCapture(dev)
    gst_str = ('v4l2src device=/dev/video{} ! '
               'video/x-raw, width=(int){}, height=(int){} ! '
               'videoconvert ! appsink').format(dev, width, height)
    return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)


def open_cam_onboard(width, height):
    gst_elements = str(subprocess.check_output('gst-inspect-1.0'))
    if 'nvcamerasrc' in gst_elements:
        # On versions of L4T prior to 28.1, add 'flip-method=2' into gst_str
        gst_str = ('nvcamerasrc ! '
                   'video/x-raw(memory:NVMM), '
                   'width=(int)2592, height=(int)1458, '
                   'format=(string)I420, framerate=(fraction)30/1 ! '
                   'nvvidconv ! '
                   'video/x-raw, width=(int){}, height=(int){}, '
                   'format=(string)BGRx ! '
                   'videoconvert ! appsink').format(width, height)
    elif 'nvarguscamerasrc' in gst_elements:
        gst_str = ('nvarguscamerasrc ! '
                   'video/x-raw(memory:NVMM), '
                   'width=(int)1920, height=(int)1080, '
                   'format=(string)NV12, framerate=(fraction)30/1 ! '
                   'nvvidconv flip-method=2 ! '
                   'video/x-raw, width=(int){}, height=(int){}, '
                   'format=(string)BGRx ! '
                   'videoconvert ! appsink').format(width, height)
    else:
        raise RuntimeError('onboard camera source not found!')
    return cv2.VideoCapture(gst_str, cv2.CAP_GSTREAMER)


def open_window(width, height):
    cv2.namedWindow(WINDOW_NAME, cv2.WINDOW_NORMAL)
    cv2.resizeWindow(WINDOW_NAME, width, height)
    cv2.moveWindow(WINDOW_NAME, 0, 0)
    cv2.setWindowTitle(WINDOW_NAME, 'Camera Demo for Jetson TX2/TX1')


def read_cam(cap):
    show_help = True
    full_scrn = False
    help_text = '"Esc" to Quit, "H" for Help, "F" to Toggle Fullscreen'
    font = cv2.FONT_HERSHEY_PLAIN
    while True:
        if cv2.getWindowProperty(WINDOW_NAME, 0) < 0:
            # Check to see if the user has closed the window
            # If yes, terminate the program
            break
        _, img = cap.read() # grab the next image frame from camera
        if show_help:
            cv2.putText(img, help_text, (11, 20), font,
                        1.0, (32, 32, 32), 4, cv2.LINE_AA)
            cv2.putText(img, help_text, (10, 20), font,
                        1.0, (240, 240, 240), 1, cv2.LINE_AA)
        cv2.imshow(WINDOW_NAME, img)
        key = cv2.waitKey(10)
        if key == 27: # ESC key: quit program
            break
        elif key == ord('H') or key == ord('h'): # toggle help message
            show_help = not show_help
        elif key == ord('F') or key == ord('f'): # toggle fullscreen
            full_scrn = not full_scrn
            if full_scrn:
                cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,
                                      cv2.WINDOW_FULLSCREEN)
            else:
                cv2.setWindowProperty(WINDOW_NAME, cv2.WND_PROP_FULLSCREEN,
                                      cv2.WINDOW_NORMAL)


def main():
    args = parse_args()
    print('Called with args:')
    print(args)
    print('OpenCV version: {}'.format(cv2.__version__))

    if args.use_rtsp:
        cap = open_cam_rtsp(args.rtsp_uri,
                            args.image_width,
                            args.image_height,
                            args.rtsp_latency)
    elif args.use_usb:
        cap = open_cam_usb(args.video_dev,
                           args.image_width,
                           args.image_height)
    else: # by default, use the Jetson onboard camera
        cap = open_cam_onboard(args.image_width,
                               args.image_height)

    if not cap.isOpened():
        sys.exit('Failed to open camera!')

    open_window(args.image_width, args.image_height)
    read_cam(cap)

    cap.release()
    cv2.destroyAllWindows()


if __name__ == '__main__':
    main()

运行Demo后打开jtop查看Jetson Xavier NX上的资源使用情况，发现确实启用了硬解码功能，但依然出现如下问题：
1、只能用python2运行Demo，python3运行失败
解决办法：
下载jetson的opencv并重新编译，在cmake编译选项里需要打开
-DBUILD_opencv_python3=ON
-DWITH_GSTREAMER=ON
2、依然会出现卡顿的情况
3、延时还是很大
4、硬件资源占用跟软解码没什么区别
目前我也没有搞清楚问题的原因所在，很有可能是哪里的设置有问题，代码需要优化。

我决定自己尝试：
运行如下代码，查看opencv的环境：

import cv2
print(cv2.getBuildInformation())

我看到打印的除了GSTREAMER外还有FFMPEG，于是将代码改为：

import cv2
cap = cv2.VideoCapture("rtsp://192.168.1.1:554/" ， cv2.CAP_FFMPEG)
while True:
	ret , frame = cap.read()
	cv2.imshow("Test" , frame)
	if chr(cv2.waitkey(1)&255)=='q'
		break

视频画面竟然神奇的正常了，原理我也不清楚，写出来权当记录