python+pygame+opencv+gpt实现虚拟数字人

# -*- coding: utf-8 -*- # @Author : yangyongzhen # @Email : [email protected] # @File : mqttclienttool.py # @Project : study import pygame #from moviepy.editor import VideoFileClip import numpy as np import time from PIL import Image from rembg import remove import cv2 import os #import pyttsx3 # 常量 屏幕大小 WIDTH, HEIGHT = 500, 900 print(cv2.__version__) # 初始化操作 pygame.init() pygame.mixer.init() #engine = pyttsx3.init() # 创建窗口 screen = pygame.display.set_mode((WIDTH, HEIGHT)) # 设置窗口标题 pygame.display.set_caption('虚拟数字人--关注作者：blog.csdn.net/qq8864') # 添加背景音乐 pygame.mixer.music.load('./sound/bgLoop.wav') pygame.mixer.music.set_volume(0.5) # 音量 #pygame.mixer.music.play(-1, 0) # 添加系统时钟 FPS = 30 clock = pygame.time.Clock() # 创建用户自定义事件，每隔1000毫秒触发一次事件 USER_EVENT = pygame.USEREVENT pygame.time.set_timer(USER_EVENT, 1000) # 加载字体文件 font_path = "./font/SIMYOU.ttf" # 替换为你的字体文件路径 font_size = 24 font = pygame.font.Font(font_path, font_size) # ========虚拟数字人主角========== # class Hero(pygame.sprite.Sprite) # class BackGround(pygame.sprite.Sprite) # 虚拟人主角 (静默状态保持微笑和3秒眨一次眼睛) class VirtualMan(pygame.sprite.Sprite): def __init__(self, speed): super().__init__() self.image = pygame.image.load('./image/man.png') self.image_index = 0 self.readt_to_change = 0 self.rect = self.image.get_rect() self.rect.width *= 0.5 self.rect.height *= 0.5 self.image = pygame.transform.scale(self.image, (self.rect.width, self.rect.height)) self.rect.x, self.rect.y = 0, 100 self.speed = speed self.frames = None self.current_frame = 0 self.state = "idle" def update(self, *args): #这里用上下左右、空格几个按键来测试虚拟数字人的不同动作 keys = pygame.key.get_pressed() if keys[pygame.K_UP]: #加油动作手势 self.comeOn() if keys[pygame.K_DOWN]: #欢迎动作手势 self.welcome() if keys[pygame.K_LEFT]: #说话动作和表情 self.say() if keys[pygame.K_RIGHT]: #停下来 self.stop() if keys[pygame.K_SPACE]: #欢迎动作手势 self.goodbye() if keys[pygame.K_0]: print("getImgFromVideo") self.getImgFromVideo(2) if keys[pygame.K_1]: print("speek:") self.speek() if self.state != "idle": self.current_frame = (self.current_frame + 1) % len(self.frames) self.image = pygame.transform.scale(self.frames[self.current_frame], (self.rect.width, self.rect.height)) #print("current_frame:"+str(self.current_frame)) if self.current_frame == 0: self.frames.clear() self.state = "idle" print("idle") self.end = time.time() print("time:"+str(self.end - self.start)) img = pygame.image.load('./image/man.png') self.image = pygame.transform.scale(img, (self.rect.width, self.rect.height)) pass # 加油动作手势 def comeOn(self): # 加载mp4视频并提取图像帧 #video = VideoFileClip("./mp4/1.mp4") frames = [] ''' video = cv2.VideoCapture("./mp4/1.mp4") # 设置帧计数器 frame_count = 0 while True: # 读取视频的每一帧 ret, frame = video.read() # 如果没有读到帧，说明视频已经结束 if not ret: break # 保存帧图片 #cv2.imwrite(f'output/frame_{frame_count}.png', frame) #OpenCV转换成PIL.Image格式 pil_image = Image.fromarray(cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)) image = remove(pil_image) image.save(f"framet_{frame_count}.png") # Convert PIL Image to pygame surface pygame_image = pygame.image.fromstring(image.tobytes(), image.size, image.mode).convert_alpha() frames.append(pygame_image) # 帧计数器自增 frame_count += 1 # 释放视频对象 video.release() ''' for i in range(0,75): img = pygame.image.load(f"./motion/2/framet_{i}.png") frames.append(img) self.frames = frames print("frames count:"+str(len(self.frames))) self.current_frame = 0 self.image = self.frames[self.current_frame] self.state = "comeOn" self.start = time.time() #再见动作手势 def goodbye(self): frames = [] dir_path = './motion/2' # 当前文件夹路径 # 筛选出以txt为后缀名的文件 files = [f for f in os.listdir(dir_path) if f.endswith('.png')] file_num = len(files) # 计算文件数量 print(file_num) # 输出文件数量 for i in range(0,file_num): img = pygame.image.load(f"./motion/2/framet_{i}.png") frames.append(img) self.frames = frames print("frames count:"+str(len(self.frames))) self.current_frame = 0 self.image = self.frames[self.current_frame] self.state = "goodbye" self.start = time.time() #欢迎动作手势 def welcome(self): pass #停止所有动作 def stop(self): pass #开始说话 def say(self): print("say:") #engine.say("Hello World!") ''' rate = engine.getProperty("rate") #获取engine的属性参数方法，有rate，volume,voice,voices,使用setProperty("",value)可以进行设置 engine.setProperty("rate",150) #设置rate语音速率为150 engine.setProperty("volue",1.0) #设置语音音量为1.0，范围为0-1 engine.say("但这里我用的似乎最近简单的pyttsx3，执行效率快，但也有缺点，那就是音色太少，只有单纯的机械音，这里我们就好好介绍下，在python上可用的各类文字转语音库。") engine.runAndWait() voices = engine.getProperty('voices') for voice in voices: print(voice, voice.id) engine.setProperty('voice', voice.id) engine.say("黄河之水天上来，奔流到海不复回。") engine.runAndWait() #engine.stop() engine.stop() ''' #sound = pygame.mixer.Sound('./sound/nihao.wav') #sound.play() # 加油动作手势 def speek(self): frames = [] for i in range(0,246): img = pygame.image.load(f"./motion/speek/framet_{i}.png") frames.append(img) self.frames = frames print("frames count:"+str(len(self.frames))) self.current_frame = 0 self.image = self.frames[self.current_frame] self.state = "speek" self.start = time.time() def getImgFromVideo(self,index): video = cv2.VideoCapture(f"./mp4/{index}.mp4") if not os.path.exists(f"./motion/{index}"): os.makedirs(f"./motion/{index}") # 设置帧计数器 frame_count = 0 while True: # 读取视频的每一帧 ret, frame = video.read() # 如果没有读到帧，说明视频已经结束 if not ret: break # 保存帧图片 #cv2.imwrite(f'output/frame_{frame_count}.png', frame) #OpenCV转换成PIL.Image格式 pil_image = Image.fromarray(cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)) image = remove(pil_image) image.save(f"./mo