【DBnet】MakeBorderMap 的功能与作用

2023-05-16

在这里插入图片描述

MakeBorderMap的输入是polygon,输出是“threshold_map”和对应的“threshold_mask”。
threshold_map 是由polygon进行内外延展而来,shrink_ratio设置得越大,延展得越小。
threshold_map 越靠近polygon的数值越高,threshold_map 中数值最小为thresh_min,数值最大为thresh_max。
threshold_mask 是覆盖polygon外延展后的mask区域。

下图的threshold_map 0.4 ,是当shrink_ratio 设置为0.4 出来的图,此时内外延展是比设置为0.9要大的。
在这里插入图片描述

下面是测试的代码:

import cv2
import numpy as np
import pyclipper
from shapely.geometry import Polygon


class MakeBorderMap(object):
    def __init__(self,
                 shrink_ratio=0.4,
                 thresh_min=0.3,
                 thresh_max=0.7,
                 **kwargs):
        self.shrink_ratio = shrink_ratio
        self.thresh_min = thresh_min
        self.thresh_max = thresh_max

    def __call__(self, polygon):
        data = {}
        canvas = np.zeros((640, 640), dtype=np.float32)
        mask = np.zeros((640, 640), dtype=np.float32)
        self.draw_border_map(polygon, canvas, mask=mask)
        canvas = canvas * (self.thresh_max - self.thresh_min) + self.thresh_min
        data['threshold_map'] = canvas
        data['threshold_mask'] = mask
        return data

    def draw_border_map(self, polygon, canvas, mask):
        polygon = np.array(polygon)
        assert polygon.ndim == 2
        assert polygon.shape[1] == 2

        polygon_shape = Polygon(polygon)
        if polygon_shape.area <= 0:
            return

        # 计算出distance,这是一个独特的公式,distance=area*(1-shrink_ratio^2)/length
        distance = polygon_shape.area * (
                1 - np.power(self.shrink_ratio, 2)) / polygon_shape.length

        # 用pyclipper对polygon进行padding
        # 将polygon中的点坐标列表转换为由tuple组成的列表,tuple表示一个点坐标
        subject = [tuple(l) for l in polygon]
        # 创建一个PyclipperOffset对象,用于多边形的内外延操作
        padding = pyclipper.PyclipperOffset()
        # 将subject中的多边形路径添加到padding对象中,JT_ROUND表示joins类型为圆滑join,ET_CLOSEDPOLYGON表示这是一个闭合的多边形
        padding.AddPath(subject, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
        # 执行padding对象中多边形的内延操作,距离为distance,获得内延后的多边形坐标padded_polygon
        padded_polygon = np.array(padding.Execute(distance)[0])
        # 在mask图像上填充内延后的多边形padded_polygon,值设置为1.0
        cv2.fillPoly(mask, [padded_polygon.astype(np.int32)], 1.0)

        xmin = padded_polygon[:, 0].min()
        xmax = padded_polygon[:, 0].max()
        ymin = padded_polygon[:, 1].min()
        ymax = padded_polygon[:, 1].max()
        width = xmax - xmin + 1
        height = ymax - ymin + 1

        polygon[:, 0] = polygon[:, 0] - xmin
        polygon[:, 1] = polygon[:, 1] - ymin

        xs = np.broadcast_to(np.linspace(0, width - 1, num=width).reshape(1, width), (height, width))
        ys = np.broadcast_to(np.linspace(0, height - 1, num=height).reshape(height, 1), (height, width))

        distance_map = np.zeros((polygon.shape[0], height, width), dtype=np.float32)
        for i in range(polygon.shape[0]):
            j = (i + 1) % polygon.shape[0]
            absolute_distance = self._distance(xs, ys, polygon[i], polygon[j])
            distance_map[i] = np.clip(absolute_distance / distance, 0, 1)
        distance_map = distance_map.min(axis=0)

        xmin_valid = min(max(0, xmin), canvas.shape[1] - 1)
        xmax_valid = min(max(0, xmax), canvas.shape[1] - 1)
        ymin_valid = min(max(0, ymin), canvas.shape[0] - 1)
        ymax_valid = min(max(0, ymax), canvas.shape[0] - 1)
        canvas[ymin_valid:ymax_valid + 1, xmin_valid:xmax_valid + 1] = np.fmax(
            1 - distance_map[ymin_valid - ymin:ymax_valid - ymax + height,
                xmin_valid - xmin:xmax_valid - xmax + width],
            canvas[ymin_valid:ymax_valid + 1, xmin_valid:xmax_valid + 1])

    def _distance(self, xs, ys, point_1, point_2):
        '''
        compute the distance from point to a line
        ys: coordinates in the first axis
        xs: coordinates in the second axis
        point_1, point_2: (x, y), the end of the line
        '''
        height, width = xs.shape[:2]
        square_distance_1 = np.square(xs - point_1[0]) + np.square(ys - point_1[
            1])
        square_distance_2 = np.square(xs - point_2[0]) + np.square(ys - point_2[
            1])
        square_distance = np.square(point_1[0] - point_2[0]) + np.square(
            point_1[1] - point_2[1])

        cosin = (square_distance - square_distance_1 - square_distance_2) / (
                2 * np.sqrt(square_distance_1 * square_distance_2))
        square_sin = 1 - np.square(cosin)
        square_sin = np.nan_to_num(square_sin)
        result = np.sqrt(square_distance_1 * square_distance_2 * square_sin /
                         square_distance)

        result[cosin <
               0] = np.sqrt(np.fmin(square_distance_1, square_distance_2))[cosin
                                                                           < 0]
        # self.extend_line(point_1, point_2, result)
        return result

    def extend_line(self, point_1, point_2, result, shrink_ratio):
        ex_point_1 = (int(
            round(point_1[0] + (point_1[0] - point_2[0]) * (1 + shrink_ratio))),
                      int(
                          round(point_1[1] + (point_1[1] - point_2[1]) * (
                                  1 + shrink_ratio))))
        cv2.line(
            result,
            tuple(ex_point_1),
            tuple(point_1),
            4096.0,
            1,
            lineType=cv2.LINE_AA,
            shift=0)
        ex_point_2 = (int(
            round(point_2[0] + (point_2[0] - point_1[0]) * (1 + shrink_ratio))),
                      int(
                          round(point_2[1] + (point_2[1] - point_1[1]) * (
                                  1 + shrink_ratio))))
        cv2.line(
            result,
            tuple(ex_point_2),
            tuple(point_2),
            4096.0,
            1,
            lineType=cv2.LINE_AA,
            shift=0)
        return ex_point_1, ex_point_2


if __name__ == '__main__':
    # 测试
    polygon = [[151.24755859, 187.33417013],
               [69.91391389, 183.99514903],
               [67.82457435, 205.93434209],
               [149.14115574, 210.08720066]]
    shrink_ratio = 0.4
    thresh_min = 0.3
    thresh_max = 0.7
    MakeBorderMapI = MakeBorderMap(shrink_ratio, thresh_min, thresh_max)
    data = MakeBorderMapI(polygon)
    canvas = data['threshold_map']
    mask = data['threshold_mask']
    # 为了更高清,只保留左上部分
    canvas1 = canvas[175:225, 50:200]
    mask1 = mask[175:225, 50:200]

    shrink_ratio = 0.9
    MakeBorderMapI = MakeBorderMap(shrink_ratio, thresh_min, thresh_max)
    data = MakeBorderMapI(polygon)
    canvas = data['threshold_map']
    mask = data['threshold_mask']
    # 为了更高清,只保留左上部分
    canvas2 = canvas[175:225, 50:200]
    mask2 = mask[175:225, 50:200]

    # 绘制
    import matplotlib.pyplot as plt

    plt.subplot(221)
    plt.title('threshold_map 0.4')
    plt.imshow(canvas1)

    plt.subplot(222)
    plt.title('threshold_mask 0.4')
    plt.imshow(mask1)

    plt.subplot(223)
    plt.title('threshold_map 0.9')
    plt.imshow(canvas2)

    plt.subplot(224)
    plt.title('threshold_mask 0.9')
    plt.imshow(mask2)

    plt.show()

本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系:hwhale#tublm.com(使用前将#替换为@)

【DBnet】MakeBorderMap 的功能与作用 的相关文章

随机推荐