• Get frames from Oak 1 Max

jakaskerl
Hey, I can send one later.

In the meantime, can you refer me on how to decode/save JPEGS from a VideoEncoder bitstream in H265 or MJPEG format?

    Hi JaimilDalwadi
    Assuming you have .h265 or .mjpeg files in some folder, you can use ffmpeg library to decode and save the file as the desired file type. (docs)

    Thanks,
    Jaka

      jakaskerl
      Is there no way to do it in realtime as the frames are getting written?

      ` with open(rawFile, 'wb') as videoFile:
      print("Press Ctrl+C to stop encoding...")
      try:
      while True:
      h265Packet = q.get() # Blocking call, will wait until a new data has arrived
      h265Packet.getData().tofile(videoFile) # Appends the packet data to the opened file

      do something here with the packet data to save as jpegs?

      `

      jakaskerl
      Here's an MRE of just saving images directly:

      
      import cv2
      import numpy as np
      import depthai as dai
      import time
      
      #TODO: Figure out how to ensure the fps for the OAK camera has been changed to 60
      def save_frames(output_folder):
      
          pipeline = dai.Pipeline()
      
          oakCam = pipeline.create(dai.node.ColorCamera)
          print(str(oakCam.getFps()))
          oakCam.setFps(60)
          manip = pipeline.create(dai.node.ImageManip)
          controlIn = pipeline.create(dai.node.XLinkIn)
          manipOut = pipeline.create(dai.node.XLinkOut)
          controlIn.setStreamName('control')
          manipOut.setStreamName("preview")
      
      
          topLeft = dai.Point2f(0.2, 0.2)
          bottomRight = dai.Point2f(0.8, 0.8)
      
          # to save the video using opencv
          # cap = cv2.VideoCapture(0)
      
          oakCam.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
          manip.setMaxOutputFrameSize(12441600)
      
          oakCam.video.link(manip.inputImage)
          manip.out.link(manipOut.input)
          controlIn.out.link(oakCam.inputControl)
      
          with dai.Device(pipeline) as device:
              controlQueue = device.getInputQueue(controlIn.getStreamName(),maxSize=30, blocking=False)
              qPreview = device.getOutputQueue("preview", maxSize=30, blocking=False)
      
              temp = dict()
              fc = 0
              while True:
      
                  img = qPreview.get()
                  fc += 1
                  frame_name = f"frame_{time.time()}.jpg"
                  output_path = f"{output_folder}/{frame_name}"
                  temp[frame_name] = img
                  
                  if cv2.waitKey(1) == ord('q'):
                      break
              
          print(fc)
          for filename, f in temp.items():
              frame = f.getCvFrame()
              output_path = f"{output_folder}/{filename}"
              cv2.imwrite(output_path,frame)
          cv2.destroyAllWindows()
      
      # Example usage
      output_folder = f"./testPhotos" # change as needed
      
      save_frames(output_folder)

      Here's another MRE of a script to save videos and convert using ffmpeg and trying to save the frames as JPEGS:

      
      
      ##
      #!/usr/bin/env python3
      
      # Script to save videos in .h265 format from oak camera
      
      import depthai as dai
      import time
      import os
      import cv2
      # Create pipeline
      pipeline = dai.Pipeline()
      
      # Define sources and output
      camRgb = pipeline.create(dai.node.ColorCamera)
      ctrl = dai.CameraControl()
      videoEnc = pipeline.create(dai.node.VideoEncoder)
      xout = pipeline.create(dai.node.XLinkOut)
      stillEnc = pipeline.create(dai.node.VideoEncoder)
      
      xout.setStreamName('h265')
      
      # Properties
      camRgb.setBoardSocket(dai.CameraBoardSocket.CAM_A)
      fps = 30
      camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_4_K)
      videoEnc.setDefaultProfilePreset(fps, dai.VideoEncoderProperties.Profile.H265_MAIN)
      camRgb.setSensorCrop(0.2, 0.1) # By default 0.25, 0.25 for center crop
      
      
      
      
      # Linking
      camRgb.video.link(videoEnc.input)
      videoEnc.bitstream.link(xout.input)
      
      with dai.Device(pipeline) as device:
       
          # Output queue will be used to get the encoded data from the output defined above
          q = device.getOutputQueue(name="h265", maxSize=30, blocking=True)
      
          # The .h265 file is a raw stream file (not playable yet)
          curr = int(round(time.time()))
          rawFile = rf'.\rawStreams\{curr}.h265'
          convertedFile = rf'.\convertedStreams\{curr}.mp4'
          temp = dict()
          fc = 0
          with open(rawFile, 'wb') as videoFile:
              print("Press Ctrl+C to stop encoding...")
              try:
                  while True:
                      h265Packet = q.get()  # Blocking call, will wait until a new data has arrived
                      h265Packet.getData().tofile(videoFile)  # Appends the packet data to the opened file
                      fc += 1
                      frame_name = f"frame_{int(time.time()*1000)}.jpeg"
                      temp[frame_name] = h265Packet
      
      
              except KeyboardInterrupt:
                  # Keyboard interrupt (Ctrl + C) detected
                  pass
          print(fc)
          output_folder = rf".\testPhotos"
          for filename, f in temp.items():
              with open(filename, "wb") as fi:
                  fi.write(f.getData())
                  print('Image saved to', filename)
      
          print("To view the encoded data, convert the stream file (.h265) into a video file (.mp4) using a command below:")
          # print("ffmpeg -framerate 30 -i video.h265 -c copy video.mp4")
          command = f"ffmpeg -framerate {fps} -i {rawFile} -c copy {convertedFile}"
          os.system(command)

      `

      If anyone can help,

      I managed to save frames at 30 FPS but I think it's capping there because of this warning:

      [184430108104DB0E00] [1.1] [0.801] [ColorCamera(0)] [warning] LCM48 supported resolutions: 4_K / 4000X3000 / 5312X6000. Defaulting to 4_K

      I have it set to:

      camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)

      camRgb.setVideoSize(1920, 1080)

      But I'm guessing it defaults to 4k. Can anyone help? This is on the Oak1 Max

        Hi JaimilDalwadi
        The lowest sensor resolution for Max is indeed 4K. You can try downscaling it using ISP.
        This capping you are referring to, does is come from camera being unable to process images fast enough or the ffmpeg?

        Thanks,
        Jaka

          jakaskerl

          This time I'm not using ffmpeg, I'm simply saving them to a dictionary and then saving them to files at the end like in the below script, so I'm not sure if it's being capped anywhere:

          #!/usr/bin/env python3
          
          # Script to save videos in .h265 format from oak camera
          
          import depthai as dai
          import time
          import os
          import cv2
          # Create pipeline
          pipeline = dai.Pipeline()
          
          # Define sources and output
          camRgb = pipeline.create(dai.node.ColorCamera)
          ctrl = dai.CameraControl()
          xout = pipeline.create(dai.node.XLinkOut)
          xoutStill = pipeline.create(dai.node.XLinkOut)
          
          
          xout.setStreamName('h265')
          xoutStill.setStreamName('preview')
          
          # Properties
          camRgb.setBoardSocket(dai.CameraBoardSocket.RGB)
          fps = 60
          camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
          camRgb.setPreviewSize(360,360)
          # camRgb.setIspScale(1,2)
          
          # camRgb.setVideoSize(1920, 1080)
          stillEnc.setDefaultProfilePreset(fps, dai.VideoEncoderProperties.Profile.H265_MAIN)
          
          
          
          
          # Linking
          
          camRgb.preview.link(xoutStill.input)
          
          with dai.Device(pipeline) as device:
              device.setLogLevel(dai.LogLevel.DEBUG)
              device.setLogOutputLevel(dai.LogLevel.DEBUG)
              # Output queue will be used to get the encoded data from the output defined above
              qPreview = device.getOutputQueue(name="preview", maxSize=60,blocking=False)
              curr = int(round(time.time()))
              rawFile = rf'.\rawStreams\{curr}.h265'
              convertedFile = rf'.\convertedStreams\{curr}.mp4'
              temp = dict()
              fc = 0
              starttime = time.time()
              totaltime = 0
              with open(rawFile, 'wb') as videoFile:
                  print("Press Ctrl+C to stop encoding...")
                  
                  try:
                      while True:
                          fc += 1
                          frame = qPreview.get()
                          frame_name = f"frame_{int(time.time()*1000)}.jpeg"
                          temp[frame_name] = frame
                          # cv2.imshow("rgb",frame)
          
          
                  except KeyboardInterrupt:
                      # Keyboard interrupt (Ctrl + C) detected
                      totaltime = time.time() - starttime
                      pass
              print(f"Total frame count: {fc}")
              print(f"Total time run: {totaltime}")
              print(f"FPS: {fc/totaltime}")
              output_folder = rf".\testPhotos"
              for filename, f in temp.items():
                  pathout = f"../testPhotos/{filename}"
                  f = f.getCvFrame()
                  cv2.imwrite(pathout,f)

          `

            Hi JaimilDalwadi
            And the number of frames you are getting?
            Since you have set the queue size to 60, when ending the stream with ctrl+c, I think there might still be some frames left in that queue that haven't yet been read, so you get lower number of frames than you should be getting.

            Thoughts?
            Jaka

              jakaskerl

              I was getting around 29 fps. I'm not sure if its the queue size, I tested with the ISP downscaling to (1,2) but it still only gives about the same. Do you think it could be a camera issue? Or something with the configuration such that it keeps using 4k resolution or limits it to 30 fps instead for some reason?

                Hi JaimilDalwadi
                I don't know for sure. You can try running your script with DEPTHAI_LEVEL=TRACE python3 <file> to see how much time each frame acquisition took.

                Thanks,
                Jaka

                  jakaskerl

                  Thank you for all the help! I was able to save frames for x number of seconds on command.

                  I am facing issues though as it starts to not get any frames. I basically wait on the keyboard press for "c" and set some flags and run the following code:
                  `

                  if getImgs and time.time()-starttime <= 1:

                  frame = qPreview.tryGet()

                  if frame is not None:

                  fc += 1

                  frame_name = f"frame_{int(time.time()*1000)}.jpeg"

                  temp[frame_name] = frame

                  `
                  When I press c the first time, it works and gets around 40 fps, but when I press c the second time after everything has saved, it only gets around 10, and then anytime I press c again, it just doesn't get anything. Could it be anything to do with the video pipeline? Is it possible the queue gets empty for some reason or the camera doesn't get any more frames for some reason?

                  These are the pipelines:

                  xoutPrev = pipeline.create(dai.node.XLinkOut)

                  xoutPrev.setStreamName('preview')

                  camRgb.video.link(xoutPrev.input)
                  qPreview = device.getOutputQueue(name="preview", maxSize=10,blocking=False)

                    jakaskerl

                    I somehow got it to work with the MRE, maybe there were some issues in my original script. Are there any improvements I can make to this MRE code:

                    #!/usr/bin/env python3
                    import depthai as dai
                    import time
                    import os
                    import cv2
                    import keyboard
                    # Create pipeline
                    pipeline = dai.Pipeline()
                    
                    # Define sources and output
                    camRgb = pipeline.create(dai.node.ColorCamera)
                    
                    xoutPrev = pipeline.create(dai.node.XLinkOut)
                    xoutPrev.setStreamName('preview')
                    
                    camRgb.setBoardSocket(dai.CameraBoardSocket.RGB)
                    fps = 30
                    camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
                    
                    
                    camRgb.video.link(xoutPrev.input)
                    
                    with dai.Device(pipeline) as device:
                    
                        qPreview = device.getOutputQueue(name="preview", maxSize=10,blocking=False)
                        # The .h265 file is a raw stream file (not playable yet)
                        temp = dict()
                        fc = 0
                        starttime = time.time()
                        totaltime = 0
                        getImgs = False
                        try:
                            while True:
                                if getImgs and time.time()-starttime <= 1:
                                    frame = qPreview.tryGet()
                                    if frame is not None:
                                        fc += 1
                                        frame_name = f"{int(time.time()*1000)}.jpeg"
                                        temp[frame_name] = frame
                                elif getImgs:
                                    totaltime = time.time() - starttime
                                    print(f"Total frame count: {fc}")
                                    print(f"Total time run: {totaltime}")
                                    print(f"FPS: {fc/totaltime}")
                                    output_folder = rf".\testPhotos"
                                    for filename, f in temp.items():
                                        pathout = f"../testPhotos/{filename}"
                                        f = f.getCvFrame()
                                        cv2.imwrite(pathout,f)
                                    getImgs = False
                                    temp.clear()
                                    fc = 0
                                    totaltime = 0
                                
                                if not getImgs:
                                    keyboard.wait("c")
                                    getImgs = True
                                    starttime = time.time()
                    
                    
                        except KeyboardInterrupt:
                            pass

                      Hi JaimilDalwadi
                      Great! So I assume the code works as expected? The point of a MRE is to find the minimal amount of code you need to reproduce the issue you are facing. Very often the issue goes away on it's own when shrinking down the code. I am not sure what the cause for the above error is, but since the script is now working I feel there is no need to dig into what is possibly just a coding mistake.

                      Thanks,
                      Jaka