Revision history [back]

I am trying to get axis-aligned bounding box by commenting out some lines in the original project(https://github.com/foolwood/SiamMask). These lines are -- pbox = cv2.boundingRect(polygon) # Min Max Rectangle box_in_img = pbox. But getting the following error: tuple object doesnot have flatten. but flatten() previously worked with rotated bounding boxes. If I remove flatten to execute the code, the error is gone but I am getting wrong bounding boxes like this--

I have matched results in every steps of axis aligned to rotated bounding box version, they match completely, just the flatten() does not work. Please give some ideas to solve this issue.

I am trying to get axis-aligned bounding box by commenting out some lines in the original project(https://github.com/foolwood/SiamMask). project. These lines are -- pbox = cv2.boundingRect(polygon) # Min Max Rectangle box_in_img = pbox. But getting the following error: tuple object doesnot have flatten. but flatten() previously worked with rotated bounding boxes. If I remove flatten to execute the code, the error is gone but I am getting wrong bounding boxes like this--

I have matched results in every steps of axis aligned to rotated bounding box version, they match completely, just the flatten() does not work. Please give some ideas to solve this issue.

I am trying to get axis-aligned bounding box by commenting out some lines in the original project. These lines are -- --

pbox = cv2.boundingRect(polygon) # Min Max Rectangle
box_in_img = pbox.

But getting the following error: tuple object doesnot have flatten. but flatten() previously worked with rotated bounding boxes. If I remove flatten to execute the code, the error is gone but I am getting wrong bounding boxes like this--

I have matched results in every steps of axis aligned to rotated bounding box version, they match completely, just the flatten() does not work. Please give some ideas to solve this issue.

I am trying to get axis-aligned bounding box by commenting out some lines in where the original project. These algorithm used rotated bounding boxes. corresponding lines are --

if len(contours) != 0 and np.max(cnt_area) > 100:
contour = contours[np.argmax(cnt_area)] # use max area polygon
polygon = contour.reshape(-1, 2)
pbox = cv2.boundingRect(polygon)  # Min Max Rectangle
 #pbox = cv2.boxPoints(cv2.minAreaRect(polygon))
box_in_img = pbox.

But getting the following error: tuple object doesnot have flatten. but flatten() previously worked with rotated bounding boxes. If I remove flatten to execute the code, the error is gone but I am getting wrong bounding boxes like this--

I have matched results in every steps of axis aligned to rotated bounding box version, they match completely, just the flatten() does not work. Please give some ideas to solve this issue.

I am trying to get axis-aligned bounding box where the original algorithm used rotated bounding boxes. corresponding lines are --

if len(contours) != 0 and np.max(cnt_area) > 100:
  contour = contours[np.argmax(cnt_area)] # use max area polygon
 polygon = contour.reshape(-1, 2)
  pbox = cv2.boundingRect(polygon) # Min Max Rectangle
 #pbox = cv2.boxPoints(cv2.minAreaRect(polygon))
  box_in_img = pbox
 state['ploygon'] = rbox_in_img if mask_enable else []
[]
  
location = state['ploygon'].flatten()state['ploygon'].flatten()