将Detectron2实例分割转换为opencv Mat数组

Question

我正在尝试从使用 Detectron2 执行的实例分割输出中获取二值图像。根据 the official documentation 掩码的输出格式如下：

“pred_masks”: a Tensor of shape (N, H, W), masks for each detected instance.

所以我尝试将其转换为 numpy： mask = outputs["instances"].get("pred_masks").numpy() 输出如下：

[[[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]

 [[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  ...
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]

 [[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  ...
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]

 ...

 [[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  ...
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]

 [[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  ...
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]

 [[False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]
  ...
  [False False False ... False False False]
  [False False False ... False False False]
  [False False False ... False False False]]]

但是数据类型是布尔值，所以我添加了以下行以更接近 opencv 格式： array = (mask > 126) * 255

[[[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]

 [[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]

 [[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]

 ...

 [[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]

 [[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]

 [[0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  ...
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]
  [0 0 0 ... 0 0 0]]]

我到此为止。我希望能够将每个蒙版单独可视化为 opencv 图像： cv2.imshow("Mask", mask) , 而无需保存图像。

What I would like to achieve

提前致谢。

Answer 1

我希望这能为您提供解决方案

mask_array = outputs['instances'].pred_masks.numpy()
num_instances = mask_array.shape[0]
mask_array = np.moveaxis(mask_array, 0, -1)
mask_array_instance = []
output = np.zeros_like(im) #black
#print('output',output)
for i in range(num_instances):
    mask_array_instance.append(mask_array[:, :, i:(i+1)])
    output = np.where(mask_array_instance[i] == True, 255, output)
cv2.imwrite(mask_path+'/'+item+'.jpg',output)#mask

Answer 2

mask_array = outputs['instances'].pred_masks.to("cpu").numpy()
num_instances = mask_array.shape[0]
scores = outputs['instances'].scores.to("cpu").numpy()
labels = outputs['instances'].pred_classes .to("cpu").numpy()
bbox   = outputs['instances'].pred_boxes.to("cpu").tensor.numpy()

mask_array = np.moveaxis(mask_array, 0, -1)

mask_array_instance = []
#img = np.zeros_like(im) #black
h = im.shape[0]
w = im.shape[1]
img_mask = np.zeros([h, w, 3], np.uint8)
color = (200, 100, 255)
for i in range(num_instances):
    img = np.zeros_like(im)
    mask_array_instance.append(mask_array[:, :, i:(i+1)])
    img = np.where(mask_array_instance[i] == True, 255, img)
    array_img = np.asarray(img)
    img_mask[np.where((array_img==[255,255,255]).all(axis=2))]=color
    
img_mask = np.asarray(img_mask)
output = cv2.addWeighted(im, 0.7, img_mask, 0.3, 0)

将Detectron2实例分割转换为opencv Mat数组

Converting Detectron2 instance segmentation to opencv Mat array

python

opencv

numpy

data-conversion

detectron