python+mediapipe人体分割替换背景

python+mediapipe人体分割替换背景

目录

前言

mediapipe官网:随时随地进行机器学习
MediaPipe为直播和流媒体提供跨平台、可定制的 ML 解决方案。

一、mediapipe是什么?

mediapipe官网随时随地进行机器学习
MediaPipe为直播和流媒体提供跨平台、可定制的 ML 解决方案。

二、使用方法&注意事项

1.引入库

安装mediapipe

pip install mediapipe

2.上代码

import cv2
import mediapipe as mp
import numpy as np
mp_drawing = mp.solutions.drawing_utils
mp_selfie_segmentation = mp.solutions.selfie_segmentation

IMAGE_FILES = []
BG_COLOR = (192, 192, 192)
MASK_COLOR = (255, 255, 255)
with mp_selfie_segmentation.SelfieSegmentation(model_selection=0) as selfie_segmentation:
    for idx, file in enumerate(IMAGE_FILES):
        image = cv2.imread(file)
        image_height, image_width, _ = image.shape

        results = selfie_segmentation.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))

        condition = np.stack((results.segmentation_mask,) * 3, axis=-1) > 0.1

        fg_image = np.zeros(image.shape, dtype=np.uint8)
        fg_image[:] = MASK_COLOR
        bg_image = np.zeros(image.shape, dtype=np.uint8)
        bg_image[:] = BG_COLOR
        output_image = np.where(condition, fg_image, bg_image)
        cv2.imwrite('/tmp/selfie_segmentation_output' + str(idx) + '.png', output_image)

BG_COLOR = (192, 192, 192)
cap = cv2.VideoCapture(0)
with mp_selfie_segmentation.SelfieSegmentation(
        model_selection=1) as selfie_segmentation:
    bg_image = None
    while cap.isOpened():
        success, image = cap.read()
        if not success:
            print("摄像头被占用")

            continue

        image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)

        image.flags.writeable = False
        results = selfie_segmentation.process(image)
        image.flags.writeable = True
        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)

        condition = np.stack(
            (results.segmentation_mask,) * 3, axis=-1) > 0.5

        if bg_image is None:
            bg_image = np.zeros(image.shape, dtype=np.uint8)
            bg_image[:] = BG_COLOR

        bg_image = cv2.imread('001.png')
        output_image = np.where(condition, image, bg_image)

        cv2.imshow('MediaPipe Selfie Segmentation', output_image)
        if cv2.waitKey(5) & 0xFF == 27:
            break
cap.release()

3.注意事项

        bg_image = cv2.GaussianBlur(image,(55,55),0)
        bg_image = cv2.imread('001.png')

成品

python+mediapipe人体分割替换背景

Original: https://blog.csdn.net/qq_44291652/article/details/122885590
Author: 我是小杰啊
Title: python+mediapipe人体分割替换背景

原创文章受到原创版权保护。转载请注明出处:https://www.johngo689.com/762519/

转载文章受原作者版权保护。转载请注明原作者出处!

(0)

大家都在看

亲爱的 Coder【最近整理,可免费获取】👉 最新必读书单  | 👏 面试题下载  | 🌎 免费的AI知识星球