Tag: cloud

pip install opencv-python
pip install pygame

(imgH, imgW) = frame.shape[:2]
(srcH, srcW) = source.shape[:2]

# Detect Aruco markers in the input frame
(corners, ids, rejected) = cv2.aruco.detectMarkers(frame, arucoDict, parameters=arucoParams)

# Loop over the IDs of the ArUco markers in Top-Left, Top-Right,
# Bottom-Right, and Bottom-Left order
for i in cornerIDs:
  # Grab the index of the corner with the current ID
  j = np.squeeze(np.where(ids == i))

  # If we receive an empty list instead of an integer index,
  # then we could not find the marker with the current ID
  if j.size == 0:
    continue

  # Otherwise, append the corner (x, y)-coordinates to our list
  # of reference points
  corner = np.squeeze(corners[j])
  refPts.append(corner)

# Check to see if we failed to find the four ArUco markers
if len(refPts) != 4:
  # If we are allowed to use cached reference points, fall
  # back on them
  if useCache and CACHED_REF_PTS is not None:
    refPts = CACHED_REF_PTS

  # Otherwise, we cannot use the cache and/or there are no
  # previous cached reference points, so return early
  else:
    return None

# If we are allowed to use cached reference points, then update
# the cache with the current set
if useCache:
  CACHED_REF_PTS = refPts

# Unpack our Aruco reference points and use the reference points
# to define the Destination transform matrix, making sure the
# points are specified in Top-Left, Top-Right, Bottom-Right, and
# Bottom-Left order
(refPtTL, refPtTR, refPtBR, refPtBL) = refPts
dstMat = [refPtTL[0], refPtTR[1], refPtBR[2], refPtBL[3]]
dstMat = np.array(dstMat)

# For zoom option recalculating all the 4 points
refPtTL1_L_X = refPtTL[0][0]-TOP_LEFT_X
refPtTL1_L_Y = refPtTL[0][1]-TOP_LEFT_Y

refPtTL1.append((refPtTL1_L_X,refPtTL1_L_Y))

refPtTL1_R_X = refPtTL[1][0]+TOP_RIGHT_X
refPtTL1_R_Y = refPtTL[1][1]+TOP_RIGHT_Y

refPtTL1.append((refPtTL1_R_X,refPtTL1_R_Y))

refPtTD1_L_X = refPtTL[2][0]+BOTTOM_RIGHT_X
refPtTD1_L_Y = refPtTL[2][1]+BOTTOM_RIGHT_Y

refPtTL1.append((refPtTD1_L_X,refPtTD1_L_Y))

refPtTD1_R_X = refPtTL[3][0]-BOTTOM_LEFT_X
refPtTD1_R_Y = refPtTL[3][1]+BOTTOM_LEFT_Y

refPtTL1.append((refPtTD1_R_X,refPtTD1_R_Y))

dstMatMod = [refPtTL1[0], refPtTL1[1], refPtTL1[2], refPtTL1[3]]
dstMatMod = np.array(dstMatMod)

# Define the transform matrix for the *source* image in Top-Left,
# Top-Right, Bottom-Right, and Bottom-Left order
srcMat = np.array([[0, 0], [srcW, 0], [srcW, srcH], [0, srcH]])

# Compute the homography matrix and then warp the source image to
# the destination based on the homography depending upon the
# zoom flag
if zoomFlag == 1:
  (H, _) = cv2.findHomography(srcMat, dstMat)
else:
  (H, _) = cv2.findHomography(srcMat, dstMatMod)

warped = cv2.warpPerspective(source, H, (imgW, imgH))

# Construct a mask for the source image now that the perspective
# warp has taken place (we'll need this mask to copy the source
# image into the destination)
mask = np.zeros((imgH, imgW), dtype="uint8")
if zoomFlag == 1:
  cv2.fillConvexPoly(mask, dstMat.astype("int32"), (255, 255, 255), cv2.LINE_AA)
else:
  cv2.fillConvexPoly(mask, dstMatMod.astype("int32"), (255, 255, 255), cv2.LINE_AA)

# This optional step will give the source image a black
# border surrounding it when applied to the source image, you
# can apply a dilation operation
rect = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
mask = cv2.dilate(mask, rect, iterations=2)

# Create a three channel version of the mask by stacking it
# depth-wise, such that we can copy the warped source image
# into the input image
maskScaled = mask.copy() / 255.0
maskScaled = np.dstack([maskScaled] * 3)

# Copy the warped source image into the input image by
# (1) Multiplying the warped image and masked together,
# (2) Then multiplying the original input image with the
#     mask (giving more weight to the input where there
#     are not masked pixels), and
# (3) Adding the resulting multiplications together
warpedMultiplied = cv2.multiply(warped.astype("float"), maskScaled)
imageMultiplied = cv2.multiply(frame.astype(float), 1.0 - maskScaled)
output = cv2.add(warpedMultiplied, imageMultiplied)
output = output.astype("uint8")

def playAudio(self, audioFile, audioLen, freq, stopFlag=False):
  try:
    pygame.mixer.init()
    pygame.init()
    pygame.mixer.music.load(audioFile)

    pygame.mixer.music.set_volume(10)

    val = int(audioLen)
    i = 0

    while i < val:
      pygame.mixer.music.play(loops=0, start=float(i))
      time.sleep(freq)

      i = i + 1

      if (i >= val):
        raise BreakLoop

      if (stopFlag==True):
        raise BreakLoop

    return 0
  except BreakLoop as s:
    return 0
  except Exception as e:
    x = str(e)
    print(x)

    return 1

def extractAudio(self, video_file, output_ext="mp3"):
    try:
        """Converts video to audio directly using `ffmpeg` command
        with the help of subprocess module"""
        filename, ext = os.path.splitext(video_file)
        subprocess.call(["ffmpeg", "-y", "-i", video_file, f"{filename}.{output_ext}"],
                        stdout=subprocess.DEVNULL,
                        stderr=subprocess.STDOUT)

        return 0
    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

# Initialize the video file stream
print("[INFO] accessing video stream...")
vf = cv2.VideoCapture(videoFile)

x = self.extractAudio(videoFile)

if x == 0:
    print('Successfully Audio extracted from the source file!')
else:
    print('Failed to extract the source audio!')

# Initialize a queue to maintain the next frame from the video stream
Q = deque(maxlen=128)

# We need to have a frame in our queue to start our augmented reality
# pipeline, so read the next frame from our video file source and add
# it to our queue
(grabbed, source) = vf.read()
Q.appendleft(source)

# Initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()

time.sleep(2.0)
flg = 0

t = threading.Thread(target=self.playAudio, args=(audioFile, audioLen, audioFreq, stopFlag,))
t.daemon = True

while len(Q) > 0:
  try:
    # Grab the frame from our video stream and resize it
    frame = vs.read()
    frame = imutils.resize(frame, width=1020)

    # Attempt to find the ArUCo markers in the frame, and provided
    # they are found, take the current source image and warp it onto
    # input frame using our augmented reality technique
    warped = x1.getWarpImages(
      frame, source,
      cornerIDs=(923, 1001, 241, 1007),
      arucoDict=arucoDict,
      arucoParams=arucoParams,
      zoomFlag=zFlag,
      useCache=CacheL > 0)

    # If the warped frame is not None, then we know (1) we found the
    # four ArUCo markers and (2) the perspective warp was successfully
    # applied
    if warped is not None:
      # Set the frame to the output augment reality frame and then
      # grab the next video file frame from our queue
      frame = warped
      source = Q.popleft()

      if flg == 0:

        t.start()
        flg = flg + 1

    # For speed/efficiency, we can use a queue to keep the next video
    # frame queue ready for us -- the trick is to ensure the queue is
    # always (or nearly full)
    if len(Q) != Q.maxlen:
      # Read the next frame from the video file stream
      (grabbed, nextFrame) = vf.read()

      # If the frame was read (meaning we are not at the end of the
      # video file stream), add the frame to our queue
      if grabbed:
        Q.append(nextFrame)

    # Show the output frame
    cv2.imshow(title, frame)
    time.sleep(videoFrame)

    # If the `q` key was pressed, break from the loop
    if cv2.waitKey(2) & 0xFF == ord('q'):
      stopFlag = True
      break

  except BreakLoop:
    raise BreakLoop
  except Exception as e:
    pass

  if (len(Q) == Q.maxlen):
    time.sleep(2)
    break

# Performing cleanup at the end
cv2.destroyAllWindows()
vs.stop()