def handDetect()

in src/controlnet_aux/open_pose/util.py [0:0]

• 53 lines of code
• 14 McCabe index (conditional complexity)

def handDetect(body: BodyResult, oriImg) -> List[Tuple[int, int, int, bool]]:
    """
    Detect hands in the input body pose keypoints and calculate the bounding box for each hand.

    Args:
        body (BodyResult): A BodyResult object containing the detected body pose keypoints.
        oriImg (numpy.ndarray): A 3D numpy array representing the original input image.

    Returns:
        List[Tuple[int, int, int, bool]]: A list of tuples, each containing the coordinates (x, y) of the top-left
                                          corner of the bounding box, the width (height) of the bounding box, and
                                          a boolean flag indicating whether the hand is a left hand (True) or a
                                          right hand (False).

    Notes:
        - The width and height of the bounding boxes are equal since the network requires squared input.
        - The minimum bounding box size is 20 pixels.
    """
    ratioWristElbow = 0.33
    detect_result = []
    image_height, image_width = oriImg.shape[0:2]
    
    keypoints = body.keypoints
    # right hand: wrist 4, elbow 3, shoulder 2
    # left hand: wrist 7, elbow 6, shoulder 5
    left_shoulder = keypoints[5]
    left_elbow = keypoints[6]
    left_wrist = keypoints[7]
    right_shoulder = keypoints[2]
    right_elbow = keypoints[3]
    right_wrist = keypoints[4]

    # if any of three not detected
    has_left = all(keypoint is not None for keypoint in (left_shoulder, left_elbow, left_wrist))
    has_right = all(keypoint is not None for keypoint in (right_shoulder, right_elbow, right_wrist))
    if not (has_left or has_right):
        return []
    
    hands = []
    #left hand
    if has_left:
        hands.append([
            left_shoulder.x, left_shoulder.y,
            left_elbow.x, left_elbow.y,
            left_wrist.x, left_wrist.y,
            True
        ])
    # right hand
    if has_right:
        hands.append([
            right_shoulder.x, right_shoulder.y,
            right_elbow.x, right_elbow.y,
            right_wrist.x, right_wrist.y,
            False
        ])

    for x1, y1, x2, y2, x3, y3, is_left in hands:
        # pos_hand = pos_wrist + ratio * (pos_wrist - pos_elbox) = (1 + ratio) * pos_wrist - ratio * pos_elbox
        # handRectangle.x = posePtr[wrist*3] + ratioWristElbow * (posePtr[wrist*3] - posePtr[elbow*3]);
        # handRectangle.y = posePtr[wrist*3+1] + ratioWristElbow * (posePtr[wrist*3+1] - posePtr[elbow*3+1]);
        # const auto distanceWristElbow = getDistance(poseKeypoints, person, wrist, elbow);
        # const auto distanceElbowShoulder = getDistance(poseKeypoints, person, elbow, shoulder);
        # handRectangle.width = 1.5f * fastMax(distanceWristElbow, 0.9f * distanceElbowShoulder);
        x = x3 + ratioWristElbow * (x3 - x2)
        y = y3 + ratioWristElbow * (y3 - y2)
        distanceWristElbow = math.sqrt((x3 - x2) ** 2 + (y3 - y2) ** 2)
        distanceElbowShoulder = math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2)
        width = 1.5 * max(distanceWristElbow, 0.9 * distanceElbowShoulder)
        # x-y refers to the center --> offset to topLeft point
        # handRectangle.x -= handRectangle.width / 2.f;
        # handRectangle.y -= handRectangle.height / 2.f;
        x -= width / 2
        y -= width / 2  # width = height
        # overflow the image
        if x < 0: x = 0
        if y < 0: y = 0
        width1 = width
        width2 = width
        if x + width > image_width: width1 = image_width - x
        if y + width > image_height: width2 = image_height - y
        width = min(width1, width2)
        # the max hand box value is 20 pixels
        if width >= 20:
            detect_result.append((int(x), int(y), int(width), is_left))

    '''
    return value: [[x, y, w, True if left hand else False]].
    width=height since the network require squared input.
    x, y is the coordinate of top left 
    '''
    return detect_result