Python implements ultra-simple video object extraction function

This article mainly introduces the ultra-simple video object extraction function implemented in python, which has certain reference value. Now I share it with everyone. Friends in need can refer to it

Video object extraction

# is not so much video object extraction as video color extraction, because its essence still uses OpenCV’s HSV color object detection. Not much to say below, let’s take a look at the detailed introduction.

HSV introduction

HSV stands for hue (H: hue), saturation (S: saturation), brightness ( V: value), a color space created by A. R. Smith in 1978, also called the Hexcone Model;

Hue (H: hue): measured in angle, with a value range of 0°～360°, starting from red and counting in counterclockwise direction, red is 0°, green is 120°, and blue is 240°. Their complementary colors are: yellow is 60°, cyan is 180°, and magenta is 300°; (the value range of H in OpenCV is 0~180, when 8bit is stored);

Saturation (S: saturation): The value range is 0~255. The larger the value, the more saturated the color;

Brightness (V: value): The value range is 0 (black) ~ 255 (white);

Effect display

#Implementation ideas

As shown in the rendering above, all we have to do is to identify the green Peppa Pig in the video. The following are the identification steps:

• The HSB value of the Peppa Pig color obtained using PS is equivalent to the HSV of OpenCV, but the HSV (HSB) value of PS is: 0~360, 0~1, 0~1, while the HSV of OpenCV is: 0 ~180, 0~255, 0~255, so the hsv of ps needs to be processed, H/2, SV*255;

• Use OpenCV bit "AND operation" to extract the HSV Color part of the picture;

• Use Gaussian blur to optimize the picture;

• Picture display;

PS The HSB on the right side of the toolbar displays:

Full code

#coding=utf-8 #HSV转换（颜色提取） import cv2 import numpy as np cap = cv2.VideoCapture(0) while (1): _, frame = cap.read() hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV) #在PS里用取色器的HSV psHSV = [112, 89, 52] diff = 40 #上下浮动值 #因为PS的HSV（HSB）取值是：0~360、0~1、0~1，而OpenCV的HSV是：0~180、0~255、0~255，所以要对ps的hsv进行处理，H/2、SV*255 lowerHSV = [(psHSV[0] - diff) / 2, (psHSV[1] - diff) * 255 / 100, (psHSV[2] - diff) * 255 / 100] upperHSV = [(psHSV[0] + diff) / 2, (psHSV[1] + diff) * 255 / 100, (psHSV[2] + diff) * 255 / 100] mask = cv2.inRange(hsv, np.array(lowerHSV), np.array(upperHSV)) #使用位“与运算”提取颜色部分 res = cv2.bitwise_and(frame, frame, mask=mask) #使用高斯模式优化图片 res = cv2.GaussianBlur(res, (5, 5), 1) cv2.imshow('frame', frame) # cv2.imshow('mask', mask) cv2.imshow('res', res) if cv2.waitKey(1) & 0xFF == ord('q'): break cv2.destroyAllWindows()

Related recommendations:

Using Python to implement video download function example code

##

The above is the detailed content of Python implements ultra-simple video object extraction function. For more information, please follow other related articles on the PHP Chinese website!