# -*- coding:utf-8 -*-
import cv2
import os
import sys
import numpy as np

# 制作模板的图像路径
ORI_IMAGE_PATH = r'mm12.jpg'
# 待检测图像的路径
DETECT_IMAGE_PATH = r'mm11.jpg'


def rotate_bound(image, angle):
    # grab the dimensions of the image and then determine the
    # center
    (h, w) = image.shape[:2]
    (cX, cY) = (w // 2, h // 2)
    # grab the rotation matrix (applying the negative of the
    # angle to rotate clockwise), then grab the sine and cosine
    # (i.e., the rotation components of the matrix)
    M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
    cos = np.abs(M[0, 0])
    sin = np.abs(M[0, 1])
    # compute the new bounding dimensions of the image
    nW = int((h * sin) + (w * cos))
    nH = int((h * cos) + (w * sin))
    # adjust the rotation matrix to take into account translation
    M[0, 2] += (nW / 2) - cX
    M[1, 2] += (nH / 2) - cY
    # perform the actual rotation and return the image
    return cv2.warpAffine(image, M, (nW, nH))


def main():

    # 读取制作模板和待检测的原图
    img_ori = cv2.imread(ORI_IMAGE_PATH)
    img_detect = cv2.imread(DETECT_IMAGE_PATH)
    # 灰度化并保存
    gray_img_ori = cv2.cvtColor(img_ori, cv2.COLOR_BGR2GRAY)
    gray_img_detect = cv2.cvtColor(img_detect, cv2.COLOR_BGR2GRAY)
    cv2.imwrite('mm_gray_mm11.png', gray_img_detect)
    cv2.imwrite('mm_gray_mm12.png', gray_img_ori)
    # 制作模板：
    # 先检测出待检测的目标，阈值-寻找轮廓-寻找最小正包围框的WH
    # 待检测模板可以用最小旋转包围框来确定旋转角度
    # 在按同样的步骤制作模板，只是最后一步采用最小旋转包围框，并
    ret, det_thresh_img = cv2.threshold(
        gray_img_detect, 40, 255, cv2.THRESH_BINARY)#二值化
    det_image, hierarchy = cv2.findContours(
         det_thresh_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)#找方框
    # x, y, w, h = cv2.boundingRect(det_image[1])  
    # cv2.rectangle(gray_img_detect, (x,y), (x+w,y+h), (0,0,255), 5)
    # cv2.imshow("1111",gray_img_detect)
    # cv2.waitKey()
    # 画轮廓
    # det_img_new = cv2.drawContours(img_detect, det_image, -1, (0, 0, 255), 3)
    # 计算最小旋转矩形包围框
    contour_len_det = [len(x) for x in det_image] #方框个数
    print(contour_len_det)
    max_contor_det = det_image[np.argmax(contour_len_det)]
    x, y, w, h = cv2.boundingRect(max_contor_det)
    
    # det_img_new = cv2.drawContours(img_detect, max_contor, -1, (0, 0, 255), 3)
    det_rect = cv2.minAreaRect(max_contor_det)
    # 目标旋转角度 53.1°
    rotation_angel = det_rect[-1]
    # # calculate coordinates of the minimum area rectangle
    # det_box = cv2.boxPoints(det_rect)
    # # normalize coordinates to integers
    # det_box = np.int0(det_box)
    # bounding = cv2.rectangle(img_detect, (x, y), (x+w, y+h), (255, 0, 255), 2)
    # det_img = cv2.polylines(img_detect, [det_box], True, (255, 0, 255), 3)

    # 制作模板的步骤
    ret, thresh_img = cv2.threshold(gray_img_ori, 50, 255, cv2.THRESH_BINARY)
    contour_ori, hierarchy = cv2.findContours(
        thresh_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    contour_len = [len(x) for x in contour_ori]
    max_contor = contour_ori[np.argmax(contour_len)]
    # img_new = cv2.drawContours(img_ori, max_contor, -1, (0, 0, 255), 3)
    rect = cv2.minAreaRect(max_contor)
    # calculate coordinates of the minimum area rectangle
    box = cv2.boxPoints(rect)
    # normalize coordinates to integers
    box = np.int0(box)
    # tuple(box[0])
    # new_roi = cv2.rectangle(img_ori, tuple(box[1]), tuple(box[-1]), (0, 255, 0), 2)
    # roi_img = img_ori[box[1, 1]:box[0, 1], box[1, 0]:box[2, 0]]
    # 裁剪ROI区域
    # gray_roi_img = gray_img_ori[min(box[:, 1]):max(
        # box[:, 1]), min(box[:, 1]):max(box[:, 1])]
    print('box:')
    print(box)
    # cv2.imshow("1", gray_img_ori)
    # cv2.waitKey()
    x_min = min(box[:,1])
    x_max = max(box[:,1])
    y_min = min(box[:,0])
    y_max = max(box[:,0])
    #gray_roi_img = gray_img_ori[box[1, 1]:box[2, 1], box[0, 0]:box[1, 0]]
    gray_roi_img = gray_img_ori[x_min:x_max, y_min:y_max]
    cv2.imwrite('mm_gray_roi_img.png', gray_roi_img)
    
    # ret, thresh_img =  cv2.threshold(gray_img_ori,50, 255, cv2.THRESH_BINARY)
    # cv2.rectangle()
    # gray_roi = cv2.imread(r'mm_gray_roi_img.png')
    # temple_img = cv2.imread(r'mm_gray_mm11.png')
    # 旋转模板，和目标角度一致
    temple = rotate_bound(gray_roi_img, rotation_angel)
    # 不resize结果不准确，resize后也不太准确，自己取舍
    temple = cv2.resize(temple, (w, h))
    th, tw = temple.shape[:2]
    # temple_img = cv2.imread(r'mm_gray_mm11.png')
    # 模板匹配
    result = cv2.matchTemplate(gray_img_detect, temple, cv2.TM_CCOEFF_NORMED)
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
    tl = max_loc
    br = (tl[0]+tw, tl[1]+th)
    # 画框框
    _ = cv2.rectangle(gray_img_detect, tl, br, (0, 0, 255), 2)
    templed_img_gary = gray_img_detect[tl[-1]:br[-1], tl[0]:br[0]]
    cv2.imwrite('mm_templed_gray.png', templed_img_gary)
    # cv2.namedWindow('img', 1)
    # try:
    #     cv2.imshow('templed_img', templed_img_gary)
    #     cv2.imshow('temple_img', temple)
    #     cv2.imshow('gray_roi_img', gray_roi_img)
    # except Exception as e:
    #     print('Error: !', e)
    # cv2.waitKey(0)
    # cv2.destroyAllWindows()


if __name__ == '__main__':
    # main()中主要做了模板匹配的操作，模板相减得到污染物位置没有做
    main()