任務(wù)目標(biāo)：攝像頭采集圖像（例如：480640），并對視頻流每一幀（灰度圖）特定矩形區(qū)域（48030）像素值進(jìn)行行求和，得到一個(gè)480*1的數(shù)組，用這480個(gè)數(shù)據(jù)繪制條形圖，即在逐幀采集視頻流并處理后“實(shí)時(shí)”顯示采集到的視頻，并“實(shí)時(shí)”更新條形圖。工作流程如下圖：

這里寫圖片描述

源碼：

# -*- coding:utf-8 -*-
import cv2
import numpy as np
camera = cv2.VideoCapture(0) # 參數(shù)0表示第一個(gè)攝像頭
# camera = cv2.VideoCapture("test.avi") # 從文件讀取視頻
# 判斷視頻是否打開
if (camera.isOpened()):
    print 'Open'
else:
    print 'Fail to open!'

# # 測試用,查看視頻size
# size = (int(camera.get(cv2.CAP_PROP_FRAME_WIDTH)),
#        int(camera.get(cv2.CAP_PROP_FRAME_HEIGHT)))
# print 'size:'+repr(size)
rectangleCols = 30
while True:
    grabbed, frame_lwpCV = camera.read() # 逐幀采集視頻流
    if not grabbed:
        break
    gray_lwpCV = cv2.cvtColor(frame_lwpCV, cv2.COLOR_BGR2GRAY) # 轉(zhuǎn)灰度圖
    frame_data = np.array(gray_lwpCV)  # 每一幀循環(huán)存入數(shù)組
    box_data = frame_data[:, 400:400+rectangleCols] # 取矩形目標(biāo)區(qū)域
    pixel_sum = np.sum(box_data, axis=1) # 行求和q
    length = len(gray_lwpCV)
    x = range(length)
    emptyImage = np.zeros((rectangleCols*10, length*2, 3), np.uint8)
    for i in x:
        cv2.rectangle(emptyImage, (i*2, (rectangleCols-pixel_sum[i]/255)*10), ((i+1)*2, rectangleCols*10), (255, 0, 0), 1)
    emptyImage = cv2.resize(emptyImage, (320, 240))

    # 畫目標(biāo)區(qū)域
    lwpCV_box = cv2.rectangle(frame_lwpCV, (400, 0), (430, length), (0, 255, 0), 2)
    cv2.imshow('lwpCVWindow', frame_lwpCV) # 顯示采集到的視頻流
    cv2.imshow('sum', emptyImage)  # 顯示畫出的條形圖
    key = cv2.waitKey(1) & 0xFF
    if key == ord('q'):
        break
camera.release()
cv2.destroyAllWindows()

以上就是python環(huán)境下OPenCV處理視頻流局部區(qū)域像素值的詳細(xì)內(nèi)容，更多關(guān)于OPenCV視頻流局部區(qū)域像素處理的資料請關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: