Python OpenCV实现图像标注局部放大功能详解
发布时间：2026-10-14| 6人浏览过
本文介绍如何使用Python和OpenCV开发图像标注工具中的局部放大功能。通过同步主窗口与放大窗口的鼠标操作，实现矩形框标注的精准微调。详细解析了鼠标在不同窗口下的行为逻辑、坐标映射机制及代码实现细节，帮助开发者提升标注效率。
该功能旨在优化基于OpenCV的图像标注工具的使用体验。
为何需要局部放大视图？
在图像数据标注过程中，一次性实现精准标注往往难度较大，通常需要多次微调才能达到理想效果。当标注目标尺寸较小时，即便经过微调也难以保证精度，因此引入局部放大窗口显得尤为必要，它允许用户对特定标注区域进行放大查看，从而辅助精细调整。
程序运行逻辑
本文以矩形框作为标注信息的示例，因为矩形框是图像标注中最基础且常用的形态。其他复杂标注形态的设计思路与此类似。
程序的核心逻辑在于实现两个窗口间鼠标操作的同步映射。控制主要依据两个维度：一是当前鼠标位于主窗口还是放大窗口；二是具体的鼠标操作行为。其中，主窗口负责显示完整的原始大图，而放大窗口则专门用于展示局部放大的细节区域。
- 鼠标位于主窗口时的行为
- 鼠标移动事件：以当前鼠标位置（current_pt）为中心，截取并显示一块放大区域，其显示范围由参数default_zoom_image_size决定。为确保以current_pt为中心向四周均能获取到default_zoom_image_size一半大小的图像数据，current_pt的有效活动范围被限制在大图内部，需减去相当于default_zoom_image_size一半宽度的边缘区域。在此有效范围内，current_pt直接对应鼠标当前坐标；若鼠标进入边缘区域，current_pt则被修正为距离鼠标当前位置最近的边界点。
- 鼠标绘制矩形框：在主窗口中，按下左键并拖动即可绘制矩形框，且绘制的矩形框严格限制在大图边界之内。
- 删除矩形框：存在两种触发删除的情况：一是左键绘制出的矩形框面积为零（即未形成有效区域）；二是点击鼠标右键。
- 鼠标位于放大窗口时的行为
- 鼠标移动事件：在放大窗口中，此操作不执行任何动作。
- 鼠标绘制矩形框：在放大窗口中，按下左键并拖动可绘制矩形框。此时矩形框允许超出放大窗口的显示边界，但依然受到大图实际边界的约束，不会超出大图范围。
- 删除矩形框：在放大窗口中，删除矩形框的条件与主窗口一致，即上述两种情况。
- 鼠标点击事件：无论是左键还是右键点击，在放大窗口中均可用于选中当前的current_pt中心点。
总体而言，在主窗口中的操作可以较为随意，因为除了矩形框的绘制外，原始图像本身保持不变。而在放大窗口中的操作则需相对谨慎，否则界面会因频繁刷新而变得混乱，导致无法有效操作。因此，当在主窗口绘制矩形框时，放大窗口会随之动态更新以显示对应区域；而在放大窗口内绘制矩形框时，放大窗口保持静止（避免视觉干扰）。
程序代码示例
理解上述逻辑后，阅读下方代码将变得相对容易。此处省略细枝末节，仅强调一个关键设计点：我们需要分别为两个窗口编写独立的鼠标回调函数。
在深入理解本程序细节之前，先回顾一下单纯绘制矩形框的基础代码，这有助于理解后续实现：OpenCV-Python中绘制矩形框的方法cv2.rectangle()。
# -*- coding: utf-8 -*-
import cv2
class Rect(object):
def __init__(self, pt1=(0, 0), pt2=(0, 0)):
self.tl = pt1
self.br = pt2
self.regularize()
def regularize(self):
"""
make sure tl = TopLeft point, br = BottomRight point
"""
tl = (min(self.tl[0], self.br[0]), min(self.tl[1], self.br[1]))
br = (max(self.tl[0], self.br[0]), max(self.tl[1], self.br[1]))
self.tl = tl
self.br = br
def get_center(self):
"""
get center point of Rect
"""
center_x = (self.tl[0] + self.br[0]) // 2
center_y = (self.tl[1] + self.br[1]) // 2
return center_x, center_y
def get_width(self):
"""
get width of Rect
"""
return abs(self.br[0] - self.tl[0])
def get_height(self):
"""
get height of Rect
"""
return abs(self.br[1] - self.tl[1])
def height_over_width(self):
"""
ratio of height over width
"""
return self.get_height() / self.get_width()
def get_area(self):
"""
get area of Rect
"""
return self.get_width() * self.get_height()
class DrawZoom(object):
def __init__(self, image, color,
current_pt=(0, 0),
default_zoom_image_size=(256, 256)):
self.original_image = image
self.color = color
self.thickness = 2
self.current_pt = current_pt
self.default_zoom_image_size = default_zoom_image_size
self.rect_in_big_image = Rect()
self.rect_in_zoom_image = Rect()
self.zoom_offset = (0, 0)
self.is_drawing_big = False
self.is_drawing_zoom = False
self.exist_rect = False
self.big_image = image.copy()
self.zoom_image = None
self.zoom_image_backup = None
self.get_zoom_image()
def get_image_height(self):
"""
get height of big image
"""
return self.original_image.shape[0]
def get_image_width(self):
"""
get width of big image
"""
return self.original_image.shape[1]
def get_margin_height(self):
"""
get height of margin. in the margin area of big image, coordinate of
current_pt does NOT change
"""
return self.default_zoom_image_size[0] // 2
def get_margin_width(self):
"""
get width of margin
"""
return self.default_zoom_image_size[1] // 2
def get_zoom_image(self, height_ratio_expand=0.2, width_ratio_expand=0.2):
"""
get zoom image for two cases: the rect exists or not.
height_ratio_expand and width_ratio_expand are used for expanding some
area of rect
"""
if not self.exist_rect:
self.get_zoom_image_for_current_pt()
elif self.rect_in_big_image.get_area() > 0:
self.get_zoom_image_for_rect(height_ratio_expand,
width_ratio_expand)
def get_zoom_image_for_current_pt(self):
"""
get zoom image for current mouse point (when rect does not exist)
"""
# (x, y) is center coordinate
x = max(self.current_pt[0], self.get_margin_width())
x = min(x, self.get_image_width() - self.get_margin_width())
y = max(self.current_pt[1], self.get_margin_height())
y = min(y, self.get_image_height() - self.get_margin_height())
tl_x = x - self.get_margin_width()
tl_y = y - self.get_margin_height()
br_x = x + self.get_margin_width()
br_y = y + self.get_margin_height()
tl_x, tl_y, br_x, br_y = self.shrink_rect(tl_x, tl_y, br_x, br_y)
self.zoom_image = self.big_image[tl_y:br_y, tl_x:br_x]
self.zoom_image_backup = self.original_image[tl_y:br_y, tl_x:br_x]
self.zoom_offset = (tl_x, tl_y)
def get_zoom_image_for_rect(self, height_ratio_expand, width_ratio_expand):
"""
get zoom image when rect exists
"""
if self.rect_in_big_image.get_area() == 0:
return None
height_over_width_for_win_zoom = \
self.default_zoom_image_size[1] / self.default_zoom_image_size[0]
center = self.rect_in_big_image.get_center()
if self.rect_in_big_image.height_over_width() > \
height_over_width_for_win_zoom:
half_height = int(0.5 * (1 + height_ratio_expand) *
self.rect_in_big_image.get_height())
half_width = int(half_height / height_over_width_for_win_zoom)
else:
half_width = int(0.5 * (1 + width_ratio_expand) *
self.rect_in_big_image.get_width())
half_height = int(half_width * height_over_width_for_win_zoom)
tl_x = center[0] - half_width
tl_y = center[1] - half_height
br_x = center[0] + half_width
br_y = center[1] + half_height
tl_x, tl_y, br_x, br_y = self.shrink_rect(tl_x, tl_y, br_x, br_y)
self.zoom_image = self.big_image[tl_y:br_y, tl_x:br_x]
self.zoom_image_backup = self.original_image[tl_y:br_y, tl_x:br_x]
self.zoom_offset = (tl_x, tl_y)
@staticmethod
def clip(value, low, high):
"""
clip value between low and high
"""
output = max(value, low)
output = min(output, high)
return output
def shrink_point(self, x, y):
"""
shrink point (x, y) to inside big image
"""
x_shrink = self.clip(x, 0, self.get_image_width())
y_shrink = self.clip(y, 0, self.get_image_height())
return x_shrink, y_shrink
def shrink_rect(self, pt1_x, pt1_y, pt2_x, pt2_y):
"""
shrink rect to inside big image
"""
pt1_x = self.clip(pt1_x, 0, self.get_image_width())
pt1_y = self.clip(pt1_y, 0, self.get_image_height())
pt2_x = self.clip(pt2_x, 0, self.get_image_width())
pt2_y = self.clip(pt2_y, 0, self.get_image_height())
rect = Rect((pt1_x, pt1_y), (pt2_x, pt2_y))
rect.regularize()
tl_x, tl_y = rect.tl
br_x, br_y = rect.br
return tl_x, tl_y, br_x, br_y
def reset_big_image(self):
"""
reset big_image (for show) using original image
"""
self.big_image = self.original_image.copy()
def reset_zoom_image(self):
"""
reset zoom_image (for show) using the zoom image backup
"""
self.zoom_image = self.zoom_image_backup.copy()
def draw_rect_in_big_image(self):
"""
draw rect in big image
"""
cv2.rectangle(self.big_image,
self.rect_in_big_image.tl, self.rect_in_big_image.br,
color=self.color, thickness=self.thickness)
def draw_rect_in_zoom_image(self):
"""
draw rect in zoom image
"""
cv2.rectangle(self.zoom_image,
self.rect_in_zoom_image.tl, self.rect_in_zoom_image.br,
color=self.color, thickness=self.thickness)
def update_drawing_big(self):
"""
update drawing big image, and map the corresponding area to zoom image
"""
if self.exist_rect:
self.draw_rect_in_big_image()
self.get_zoom_image()
def update_drawing_zoom(self):
"""
update drawing big and zoom image when drawing rect in zoom image
"""
if self.exist_rect:
self.draw_rect_in_big_image()
self.draw_rect_in_zoom_image()
def onmouse_big_image(event, x, y, flags, draw_zoom):
if event == cv2.EVENT_LBUTTONDOWN:
# pick first point of rect
draw_zoom.is_drawing_big = True
draw_zoom.rect_in_big_image.tl = (x, y)
draw_zoom.exist_rect = True
elif draw_zoom.is_drawing_big and event == cv2.EVENT_MOUSEMOVE:
# pick second point of rect and draw current rect
draw_zoom.rect_in_big_image.br = draw_zoom.shrink_point(x, y)
draw_zoom.reset_big_image()
draw_zoom.update_drawing_big()
elif event == cv2.EVENT_LBUTTONUP:
# finish drawing current rect
draw_zoom.is_drawing_big = False
draw_zoom.rect_in_big_image.br = draw_zoom.shrink_point(x, y)
draw_zoom.rect_in_big_image.regularize()
if draw_zoom.rect_in_big_image.get_area() == 0:
draw_zoom.reset_big_image()
draw_zoom.rect_in_big_image = Rect()
draw_zoom.exist_rect = False
draw_zoom.update_drawing_big()
elif (not draw_zoom.is_drawing_big) and event == cv2.EVENT_RBUTTONDOWN:
# right button down to erase current rect
draw_zoom.rect_in_big_image = Rect()
draw_zoom.exist_rect = False
draw_zoom.reset_big_image()
draw_zoom.update_drawing_big()
else:
# default case: mouse move without rect
draw_zoom.current_pt = (x, y)
draw_zoom.update_drawing_big()
def onmouse_zoom_image(event, x, y, flags, draw_zoom):
if event == cv2.EVENT_LBUTTONDOWN:
# pick first point of rect
draw_zoom.is_drawing_zoom = True
draw_zoom.rect_in_zoom_image.tl = (x, y)
draw_zoom.rect_in_big_image.tl = (x + draw_zoom.zoom_offset[0],
y + draw_zoom.zoom_offset[1])
draw_zoom.exist_rect = True
elif draw_zoom.is_drawing_zoom and event == cv2.EVENT_MOUSEMOVE:
# pick second point of rect and draw current rect
draw_zoom.rect_in_zoom_image.br = (x, y)
draw_zoom.rect_in_big_image.br = draw_zoom.shrink_point(
x + draw_zoom.zoom_offset[0], y + draw_zoom.zoom_offset[1])
draw_zoom.reset_zoom_image()
draw_zoom.reset_big_image()
draw_zoom.update_drawing_zoom()
elif event == cv2.EVENT_LBUTTONUP:
# finish drawing current rect
draw_zoom.is_drawing_zoom = False
draw_zoom.rect_in_big_image.br = draw_zoom.shrink_point(
x + draw_zoom.zoom_offset[0], y + draw_zoom.zoom_offset[1])
draw_zoom.rect_in_big_image.regularize()
if draw_zoom.rect_in_big_image.get_area() == 0:
draw_zoom.reset_big_image()
draw_zoom.rect_in_big_image = Rect()
draw_zoom.rect_in_zoom_image = Rect()
draw_zoom.exist_rect = False
draw_zoom.current_pt = draw_zoom.shrink_point(
x + draw_zoom.zoom_offset[0], y + draw_zoom.zoom_offset[1])
draw_zoom.update_drawing_big()
elif (not draw_zoom.is_drawing_big) and event == cv2.EVENT_RBUTTONDOWN:
# right button down to erase current rect
draw_zoom.rect_in_big_image = Rect()
draw_zoom.rect_in_zoom_image = Rect()
draw_zoom.exist_rect = False
draw_zoom.reset_big_image()
draw_zoom.current_pt = draw_zoom.shrink_point(
x + draw_zoom.zoom_offset[0], y + draw_zoom.zoom_offset[1])
draw_zoom.update_drawing_big()
else:
# mousemove in zoom image will not change the content of image
pass
if __name__ == '__main__':
WIN_NAME_BIG = 'big_image'
WIN_NAME_ZOOM = 'zoom_image'
image = cv2.imread('1.jpg')
draw_zoom = DrawZoom(image, (0, 255, 0))
cv2.namedWindow(WIN_NAME_BIG, 0)
cv2.namedWindow(WIN_NAME_ZOOM, 0)
cv2.setMouseCallback(WIN_NAME_BIG, onmouse_big_image, draw_zoom)
cv2.setMouseCallback(WIN_NAME_ZOOM, onmouse_zoom_image, draw_zoom)
while True:
cv2.imshow(WIN_NAME_BIG, draw_zoom.big_image)
cv2.imshow(WIN_NAME_ZOOM, draw_zoom.zoom_image)
key = cv2.waitKey(30)
if key == 27: # ESC
break
cv2.destroyAllWindows()
运行结果展示：
总结
至此，关于Python OpenCV实现图像局部放大功能的介绍已完成。如需了解更多相关OpenCV局部放大技巧，欢迎查阅本站往期文章或继续浏览后续内容。感谢大家的支持！
免责声明：本文内容仅供参考，不代表本站观点。转载或引用请注明出处。
