openpose算法整合face_recongnition + 深度摄像头的Python实现

最新推荐文章于 2024-01-18 19:53:03 发布

weixin_44576543

最新推荐文章于 2024-01-18 19:53:03 发布

阅读量2.3k

点赞数 2

分类专栏： python 姿态估计人脸识别深度摄像头

本文链接：https://blog.csdn.net/weixin_44576543/article/details/96182335

版权

本文介绍了如何使用OpenPose算法与face_recognition库，结合深度摄像头进行人脸识别和姿态估计的Python实现。提供了参考代码链接、人脸识别资源以及代码结构概述，最后展示了测试效果并邀请读者交流讨论。

摘要由CSDN通过智能技术生成

1、openpose 参考代码

code link:https://github.com/YangZeyu95/unofficial-implement-of-openpose
inference : https://www.aiuai.cn/aifarm292.html

2、人脸识别（可参考上一篇文章）

参考 https://github.com/ageitgey/face_recognition

3、代码结构如下

4、主要代码附上

rgb_face_pose.py

import argparse
import tensorflow as tf
import sys
import time
import logging
import cv2
import numpy as np
from tensorflow.contrib import slim
import vgg
from cpm import PafNet
import common
from tensblur.smoother import Smoother
from estimator import PoseEstimator, TfPoseEstimator
import face_recognition
from read_data import read_name_list
from read_data import read_file


all_encoding, lable_list, counter = read_file('./dataset')
name_list = read_name_list('./dataset')
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True

logger = logging.getLogger('run')
logger.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
formatter = logging.Formatter('[%(asctime)s] [%(name)s] [%(levelname)s] %(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Training codes for Openpose using Tensorflow')
    parser.add_argument('--checkpoint_path', type=str, default='checkpoints/train/2018-12-13-16-56-49/')
    parser.add_argument('--backbone_net_ckpt_path', type=str, default='checkpoints/vgg/vgg_19.ckpt')
    parser.add_argument('--image', type=str, default=None)
    # parser.add_argument('--run_model', type=str, default='img')
    parser.add_argument('--video', type=str, default=None)
    parser.add_argument('--train_vgg', type=bool, default=True)
    parser.add_argument('--use_bn', type=bool, default=False)
    parser.add_argument('--save_video', type=str, default='result/our.mp4')

    args = parser.parse_args()

    checkpoint_path = args.checkpoint_path
    logger.info('checkpoint_path: ' + checkpoint_path)

    with tf.name_scope('inputs'):
        raw_img = tf.placeholder(tf.float32, shape=[None, None, None, 3])
        img_size = tf.placeholder(dtype=tf.int32, shape=(2,), name='original_image_size')

    img_normalized = raw_img / 255 - 0.5

    # define vgg19
    with slim.arg_scope(vgg.vgg_arg_scope()):
        vgg_outputs, end_points = vgg.vgg_19(img_normalized)

    # get net graph
    logger.info('initializing model...')
    net = PafNet(inputs_x=vgg_outputs, use_bn=args.use_bn)
    hm_pre, cpm_pre, added_layers_out = net.gen_net()

    hm_up = tf.image.resize_area(hm_pre[5], img_size)
    cpm_up = tf.image.resize_area(cpm_pre[5], img_size)
    # hm_up = hm_pre[5]
    # cpm_up = cpm_pre[5]
    smoother = Smoother({'data': hm_up}, 25, 3.0)
    gaussian_heatMat = smoother.get_output()

    max_pooled_in_tensor = tf.nn.pool(gaussian_heatMat, window_shape=(3, 3), pooling_type='MAX', padding='SAME')
    tensor_peaks = tf.where(tf.equal(gaussian_heatMat, max_pooled_in_tensor), gaussian_heatMat,
                                 tf.zeros_like(gaussian_heatMat))

    logger.info('initialize saver...')
    # trainable_var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='openpose_layers')
    # trainable_var_list = []
    trainable_var_list = tf.get_colle