本篇博文分享一篇寻找图像中灯光亮点(图像中最亮点)的教程,例如,检测图像中五个灯光的亮点并标记,项目效果如下所示:
第1步:导入并打开原图像,实现代码如下所示:
# import the necessary<i style="color:transparent">本文来源gaodai$ma#com搞$$代**码网$</i> packages from imutils import contours from skimage import measure import numpy as np import argparse import imutils import cv2 # construct the argument parse and parse the arguments ap = argparse.ArgumentParser() ap.add_argument("-i", "--image", required=True, help="path to the image file") args = vars(ap.parse_args())
第2步:开始检测图像中最亮的区域,首先需要从磁盘加载图像,然后将其转换为灰度图并进行平滑滤波,以减少高频噪声,实现代码如下所示:
#load the image, convert it to grayscale, and blur it image = cv2.imread(args["image"]) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) blurred = cv2.GaussianBlur(gray, (11, 11), 0)
导入亮灯图像,过滤后效果如下所示:
第3步:阈值化处理,为了显示模糊图像中最亮的区域,将像素值p >= 200,设置为255(白色),像素值< 200,设置为0(黑色),实现代码如下所示:
# threshold the image to reveal light regions in the # blurred image thresh = cv2.threshold(blurred, 200, 255, cv2.THRESH_BINARY)[1]
效果如下所示:
第4步:此时可看到图像中存在噪声(小斑点),所以需要通过腐蚀和膨胀操作来清除,实现代码如下所示:
# perform a series of erosions and dilations to remove # any small blobs of noise from the thresholded image thresh = cv2.erode(thresh, None, iterations=2) thresh = cv2.dilate(thresh, None, iterations=4)
此时“干净”的图像如下所示:
第5步:本项目的关键步骤是对上图中的每个区域进行标记,即使在应用了腐蚀和膨胀后,仍然想要过滤掉剩余的小块儿区域。一个很好的方法是执行连接组件分析,实现代码如下所示:
# perform a connected component analysis on the thresholded # image, then initialize a mask to store only the "large" # components labels = measure.label(thresh, neighbors=8, background=0) mask = np.zeros(thresh.shape, dtype="uint8") # loop over the unique components for label in np.unique(labels): # if this is the background label, ignore it if label == 0: continue # otherwise, construct the label mask and count the # number of pixels labelMask = np.zeros(thresh.shape, dtype="uint8") labelMask[labels == label] = 255 numPixels = cv2.countNonZero(labelMask) # if the number of pixels in the component is sufficiently # large, then add it to our mask of "large blobs" if numPixels > 300: mask = cv2.add(mask, labelMask)
上述代码中,第4行使用scikit-image库执行实际的连接组件分析。measure.lable返回的label和阈值图像有相同的大小,唯一的区别就是label存储的为阈值图像每一斑点对应的正整数。