使用 OpenCV 的隐形斗篷 |Python项目
你见过哈利波特的隐形斗篷吗?很棒吗?你有没有想过穿那件斗篷?如是!!那么在这篇文章中,我们将建造哈利波特用来隐形的斗篷。是的,我们并没有以真正的方式构建它,但它完全是关于图形技巧。
在这篇文章中,我们将学习如何在OpenCV中使用简单的计算机视觉技术创建我们自己的“隐形斗篷”。在这里,我们用Python编写了这段代码,因为它提供了详尽且足够的库来构建这个程序。
在这里,我们将使用一种称为颜色检测和分割的图像处理技术来创造这种神奇的体验。为了运行此代码,您需要一个名为“ video.mp4
”的 mp4 视频。您必须有一块相同颜色的布,并且该布中不应有其他颜色可见。我们正在拿红布。如果您使用其他布料,代码将保持不变,但会稍作更改。
为什么是红色?绿色是我的最爱?
当然,我们可以使用绿色,不是魔术师的颜色吗?撇开玩笑不谈,像绿色或蓝色这样的颜色也可以通过对代码进行一些更改来正常工作。
这种技术与绿色筛选相反。在绿色筛选中,我们删除了背景,但在这里我们将删除前景框。所以让我们开始我们的代码。
算法:
1. Capture and store the background frame [ This will be done for some seconds ]
2. Detect the red colored cloth using color detection and segmentation algorithm.
3. Segment out the red colored cloth by generating a mask. [ used in code ]
4. Generate the final augmented output to create a magical effect. [ video.mp4 ]
以下是代码:
import cv2
import numpy as np
import time
# replace the red pixels ( or undesired area ) with
# background pixels to generate the invisibility feature.
## 1. Hue: This channel encodes color information. Hue can be
# thought of an angle where 0 degree corresponds to the red color,
# 120 degrees corresponds to the green color, and 240 degrees
# corresponds to the blue color.
## 2. Saturation: This channel encodes the intensity/purity of color.
# For example, pink is less saturated than red.
## 3. Value: This channel encodes the brightness of color.
# Shading and gloss components of an image appear in this
# channel reading the videocapture video
# in order to check the cv2 version
print(cv2.__version__)
# taking video.mp4 as input.
# Make your path according to your needs
capture_video = cv2.VideoCapture("video.mp4")
# give the camera to warm up
time.sleep(1)
count = 0
background = 0
# capturing the background in range of 60
# you should have video that have some seconds
# dedicated to background frame so that it
# could easily save the background image
for i in range(60):
return_val, background = capture_video.read()
if return_val == False :
continue
background = np.flip(background, axis = 1) # flipping of the frame
# we are reading from video
while (capture_video.isOpened()):
return_val, img = capture_video.read()
if not return_val :
break
count = count + 1
img = np.flip(img, axis = 1)
# convert the image - BGR to HSV
# as we focused on detection of red color
# converting BGR to HSV for better
# detection or you can convert it to gray
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
#-------------------------------------BLOCK----------------------------#
# ranges should be carefully chosen
# setting the lower and upper range for mask1
lower_red = np.array([100, 40, 40])
upper_red = np.array([100, 255, 255])
mask1 = cv2.inRange(hsv, lower_red, upper_red)
# setting the lower and upper range for mask2
lower_red = np.array([155, 40, 40])
upper_red = np.array([180, 255, 255])
mask2 = cv2.inRange(hsv, lower_red, upper_red)
#----------------------------------------------------------------------#
# the above block of code could be replaced with
# some other code depending upon the color of your cloth
mask1 = mask1 + mask2
# Refining the mask corresponding to the detected red color
mask1 = cv2.morphologyEx(mask1, cv2.MORPH_OPEN, np.ones((3, 3),
np.uint8), iterations = 2)
mask1 = cv2.dilate(mask1, np.ones((3, 3), np.uint8), iterations = 1)
mask2 = cv2.bitwise_not(mask1)
# Generating the final output
res1 = cv2.bitwise_and(background, background, mask = mask1)
res2 = cv2.bitwise_and(img, img, mask = mask2)
final_output = cv2.addWeighted(res1, 1, res2, 1, 0)
cv2.imshow("INVISIBLE MAN", final_output)
k = cv2.waitKey(10)
if k == 27:
break
输出:
您可以在项目 github 存储库中查看源代码,以获取输入视频和更多详细信息 – 此处参考: http://datascienctherapy.com/?p=71