cv2.meanShift(probImage, window, criteria)

import cv2 as cv
# 創(chuàng)建讀取視頻的對(duì)象
cap = cv.VideoCapture("E:\Python-Code/videodataset/enn.mp4")
# 獲取第一幀位置，并指定目標(biāo)位置
ret, frame = cap.read()
c, r, h, w = 530, 160, 300, 320
track_window = (c, r, h, w)
# 指定感興趣區(qū)域
roi = frame[r:r + h, c:c + w]
# 計(jì)算直方圖
# 轉(zhuǎn)換色彩空間
hsv_roi = cv.cvtColor(roi, cv.COLOR_BGR2HSV)
# 計(jì)算直方圖
roi_hist = cv.calcHist([hsv_roi], [0], None, [180], [0, 180])
# 歸一化
cv.normalize(roi_hist, roi_hist, 0, 255, cv.NORM_MINMAX)
# 目標(biāo)追蹤
# 設(shè)置窗口搜索終止條件：最大迭代次數(shù)，窗口中心漂移最小值
term_crit = (cv.TermCriteria_EPS | cv.TERM_CRITERIA_COUNT, 10, 1)
while True:
    ret, frame = cap.read()
    if ret:
        # 計(jì)算直方圖的反向投影
        hsv = cv.cvtColor(frame, cv.COLOR_BGR2HSV)
        dst = cv.calcBackProject([hsv], [0], roi_hist, [0, 180], 1)
        # 進(jìn)行meanshift追蹤
        ret, track_window = cv.meanShift(dst, track_window, term_crit)
        # 將追蹤的位置繪制在視頻上，并進(jìn)行顯示
        x, y, w, h = track_window
        img = cv.rectangle(frame, (x, y), (x + w, y + h), 255, 2)
        cv.imshow("frame", img)
        if cv.waitKey(20) & 0xFF == ord('q'):
            break
    else:
        break
# 資源釋放
cap.release()
cv.destroyAllWindows()

track_window=cv2.selectROI('frameName', frame)

import cv2
import numpy as np
# 讀取視頻
cap=cv2.VideoCapture('E:\Python-Code/videodataset/enn.mp4')
# 獲取第一幀位置，參數(shù)ret 為True 或者False,代表有沒(méi)有讀取到圖片 第二個(gè)參數(shù)frame表示截取到一幀的圖片
ret,frame=cap.read()
#我這里畫面太大了所以縮小點(diǎn)——但是縮小后我的就會(huì)報(bào)錯(cuò)
# frame=cv2.resize(frame,None,None,fx=1/2,fy=1/2,interpolation=cv2.INTER_CUBIC)
#跟蹤框
track_window=cv2.selectROI('img', frame)
#獲得綠色的直方圖
# 轉(zhuǎn)換色彩空間
hsv=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
mask=cv2.inRange(hsv,np.array((35,43,46)),np.array((77,255,255)))
# 計(jì)算直方圖
hist=cv2.calcHist([hsv],[0],mask,[181],[0,180])
# hist=cv2.calcHist([hsv],[0],[None],[180],[0,180])
# 歸一化
cv2.normalize(hist,hist,0,255,cv2.NORM_MINMAX)
# 目標(biāo)追蹤
# 設(shè)置窗口搜索終止條件：最大迭代次數(shù)，窗口中心漂移最小值
term_crit=(cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT,10,1)
while True:
    ret,frame=cap.read()
    # frame = cv2.resize(frame, None, None, fx=1 / 2, fy=1 / 2, interpolation=cv2.INTER_CUBIC)
    if ret== True:
        # 計(jì)算直方圖的反向投影
        hsv=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
        dst=cv2.calcBackProject([hsv],[0],hist,[0,180],1)
        # 進(jìn)行meanshift追蹤
        ret,track_window=cv2.meanShift(dst,track_window,term_crit)
        # 將追蹤的位置繪制在視頻上，并進(jìn)行顯示
        x,y,w,h = track_window
        img = cv2.rectangle(frame,(x,y),(x+w,y+h),(0,255,0),2)
        (x,y)=img.shape[:2]
        cv2.imshow('img',img)
        if cv2.waitKey(1)==ord('q'):
            break
    else:
        break
# 資源釋放
cap.release()
cv2.destroyAllWindows()

bboxes = []
colors = [] 
while 1:
    bbox = cv2.selectROI('MultiTracker', frame)
    bboxes.append(bbox)
    colors.append((randint(0, 255), randint(0, 255), randint(0, 255)))
    print("按下q鍵退出，按下其他鍵繼續(xù)畫下一個(gè)框")
    if cv2.waitKey(0) & 0xFF==ord('q'):
        break
print('選取的邊框?yàn)閧}'.format(bboxes))

import math
import numpy as np
import cv2
def get_tr(img):
    # 定義需要返回的參數(shù)
    mouse_params = {'x': None, 'width': None, 'height': None,
                    'y': None, 'temp': None}
    cv2.namedWindow('image')
    # 鼠標(biāo)框選操作函數(shù)
    cv2.setMouseCallback('image', on_mouse, mouse_params)
    cv2.imshow('image', img)
    cv2.waitKey(0)
    return [mouse_params['x'], mouse_params['y'], mouse_params['width'],
            mouse_params['height']], mouse_params['temp']
def on_mouse(event, x, y, flags, param):
    global img, point1
    img2 = img.copy()
    if event == cv2.EVENT_LBUTTONDOWN:  # 左鍵點(diǎn)擊
        point1 = (x, y)
        cv2.circle(img2, point1, 10, (0, 255, 0), 5)
        cv2.imshow('image', img2)
    elif event == cv2.EVENT_MOUSEMOVE and (flags & cv2.EVENT_FLAG_LBUTTON):  # 按住左鍵拖曳
        cv2.rectangle(img2, point1, (x, y), (255, 0, 0), 5)
        cv2.imshow('image', img2)
    elif event == cv2.EVENT_LBUTTONUP:  # 左鍵釋放
        point2 = (x, y)
        cv2.rectangle(img2, point1, point2, (0, 0, 255), 5)
        cv2.imshow('image', img2)
        # 返回框選矩形左上角點(diǎn)的坐標(biāo)、矩形寬度、高度以及矩形包含的圖像
        param['x'] = min(point1[0], point2[0])
        param['y'] = min(point1[1], point2[1])
        param['width'] = abs(point1[0] - point2[0])
        param['height'] = abs(point1[1] - point2[1])
        param['temp'] = img[param['y']:param['y'] + param['height'],
                        param['x']:param['x'] + param['width']]
def main():
    global img
    cap = cv2.VideoCapture("E:\Python-Code/videodataset/enn.mp4")
    # 獲取視頻第一幀
    ret, frame = cap.read()
    img = frame
    # 框選目標(biāo)并返回相應(yīng)信息：rect為四個(gè)信息，temp為框選出來(lái)的圖像
    rect, temp = get_tr(img)
    print(temp)
    (a, b, c) = temp.shape
    y = [a / 2, b / 2]
    # 計(jì)算目標(biāo)圖像的權(quán)值矩陣
    m_wei = np.zeros((a, b))
    for i in range(a):
        for j in range(b):
            z = (i - y[0]) ** 2 + (j - y[1]) ** 2
            m_wei[i, j] = 1 - z / (y[0] ** 2 + y[1] ** 2)
    # 計(jì)算目標(biāo)權(quán)值直方圖
    C = 1 / sum(sum(m_wei))
    hist1 = np.zeros(16 ** 3)
    for i in range(a):
        for j in range(b):
            q_b = math.floor(float(temp[i, j, 0]) / 16)
            q_g = math.floor(float(temp[i, j, 1]) / 16)
            q_r = math.floor(float(temp[i, j, 2]) / 16)
            q_temp1 = q_r * 256 + q_g * 16 + q_b
            hist1[int(q_temp1)] = hist1[int(q_temp1)] + m_wei[i, j]
    hist1 = hist1 * C
    # 接著讀取視頻并進(jìn)行目標(biāo)跟蹤
    while (1):
        ret, frame = cap.read()
        if ret == True:
            Img = frame
            num = 0
            Y = [1, 1]
            # mean shift迭代
            while (np.sqrt(Y[0] ** 2 + Y[1] ** 2) > 0.5) & (num < 20):
                num = num + 1
                # 計(jì)算候選區(qū)域直方圖
                temp2 = Img[int(rect[1]):int(rect[1] + rect[3]), int(rect[0]):int(rect[0] + rect[2])]
                hist2 = np.zeros(16 ** 3)
                q_temp2 = np.zeros((a, b))
                for i in range(a):
                    for j in range(b):
                        q_b = math.floor(float(temp2[i, j, 0]) / 16)
                        q_g = math.floor(float(temp2[i, j, 1]) / 16)
                        q_r = math.floor(float(temp2[i, j, 2]) / 16)
                        q_temp2[i, j] = q_r * 256 + q_g * 16 + q_b
                        hist2[int(q_temp2[i, j])] = hist2[int(q_temp2[i, j])] + m_wei[i, j]
                hist2 = hist2 * C
                w = np.zeros(16 ** 3)
                for i in range(16 ** 3):
                    if hist2[i] != 0:
                        w[i] = math.sqrt(hist1[i] / hist2[i])
                    else:
                        w[i] = 0
                sum_w = 0
                sum_xw = [0, 0]
                for i in range(a):
                    for j in range(b):
                        sum_w = sum_w + w[int(q_temp2[i, j])]
                        sum_xw = sum_xw + w[int(q_temp2[i, j])] * np.array([i - y[0], j - y[1]])
                Y = sum_xw / sum_w
                # 位置更新
                rect[0] = rect[0] + Y[1]
                rect[1] = rect[1] + Y[0]
            v0 = int(rect[0])
            v1 = int(rect[1])
            v2 = int(rect[2])
            v3 = int(rect[3])
            pt1 = (v0, v1)
            pt2 = (v0 + v2, v1 + v3)
            # 畫矩形
            IMG = cv2.rectangle(Img, pt1, pt2, (0, 0, 255), 2)
            cv2.imshow('IMG', IMG)
            k = cv2.waitKey(60) & 0xff
            if k == 27:
                break
        else:
            break
if __name__ == '__main__':
    main()

hist=cv2.calcHist(images, channels, mask, histSize, ranges) 
images:輸入的圖像
channels:選擇圖像的通道，如果是三通道的話就可以是[0],[1],[2]
mask:掩膜，是一個(gè)大小和image一樣的np數(shù)組，其中把需要處理的部分指定為1，不需要處理的部分指定為0，一般設(shè)置為None，如果有mask，會(huì)先對(duì)輸入圖像進(jìn)行掩膜操作
histSize:使用多少個(gè)bin(柱子)，一般為256,但如果是H值就是181
ranges:像素值的范圍，一般為[0,255]表示0~255,對(duì)于H通道而言就是[0,180]

hist=cv2.calcHist([img],[0],mask,[181],[0,180]) 

cv2.normalize(src,dst, alpha,beta, norm_type）
·src-輸入數(shù)組。
·dst-與SRC大小相同的輸出數(shù)組。
·α-范數(shù)值在范圍歸一化的情況下歸一化到較低的范圍邊界。
·β-上限范圍在范圍歸一化的情況下；它不用于范數(shù)歸一化。
·范式-規(guī)范化類型（見(jiàn)下面詳細(xì)介紹）。

NORM_MINMAX：數(shù)組的數(shù)值被平移或縮放到一個(gè)指定的范圍，線性歸一化。
NORM_INF：歸一化數(shù)組的（切比雪夫距離）L∞范數(shù)(絕對(duì)值的最大值)
NORM_L1： 歸一化數(shù)組的（曼哈頓距離）L1-范數(shù)(絕對(duì)值的和)
NORM_L2： 歸一化數(shù)組的（歐幾里德距離）L2-范數(shù)

dst=cv2.calcBackProject(image,channel,hist,range,scale)
image：輸入圖像
channel：用來(lái)計(jì)算反向投影的通道數(shù)，與產(chǎn)生直方圖對(duì)應(yīng)的通道應(yīng)一致
hist：作為輸入的直方圖
range：直方圖的取值范圍
scale：輸出圖像的縮放比，一般為1，保持與輸入圖像一樣的大小
dst：輸出圖像
注意：除了hist和scale外，其他的參數(shù)都要加上[]

dst=cv2.calcBackProject([hsv],[0],hist,[0,180],1)