Letterbox操作(保持原图的长宽比的等比例缩放,防止resize时发生形变)
对图像进行resize时,保持原图的长宽比的等比例缩放,当长边 resize 到需要的长度时,短边未匹配部分采用灰色填充。
在CNN卷积模块中,由于卷积核为基本为方形,所以模型输入图片的尺寸也需要为方形。然而大多数数据集的图片基本上为 矩形,直接将图片 resize 到正方形,会导致图片失真,比如细长图片中的物体会变畸形。
letterbox操作:对图像进行resize时,保持原图的长宽比的等比例缩放,当长边 resize 到需要的长度时,短边未匹配部分采用灰色填充。
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
# Resize and pad image while meeting stride-multiple constraints
shape = im.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better val mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return im, ratio, (dw, dh)