课设项目-基于python实现的人体动作捕捉与三维重建源码+操作说明.zip

""" Copyright 2016 Max Planck Society, Federica Bogo, Angjoo Kanazawa. All rights reserved. This software is provided for research purposes only. By using this software you agree to the terms of the SMPLify license here: http://smplify.is.tue.mpg.de/license About this Script: ============ This is a demo version of the algorithm implemented in the paper, which fits the SMPL body model to the image given the joint detections. The code is organized to be run on the LSP dataset. See README to see how to download images and the detected joints. """ from os.path import join, exists, abspath, dirname from os import makedirs import logging import pickle # import cPickle as pickle from time import time from glob import glob import argparse import cv2 import numpy as np import chumpy as ch from opendr.camera import ProjectPoints from lib.robustifiers import GMOf from smpl_webuser.serialization import load_model from smpl_webuser.lbs import global_rigid_transformation from smpl_webuser.verts import verts_decorated from lib.sphere_collisions import SphereCollisions from lib.max_mixture_prior import MaxMixtureCompletePrior from render_model import render_model _LOGGER = logging.getLogger(__name__) # Mapping from LSP joints to SMPL joints. # 0 Right ankle 8 # 1 Right knee 5 # 2 Right hip 2 # 3 Left hip 1 # 4 Left knee 4 # 5 Left ankle 7 # 6 Right wrist 21 # 7 Right elbow 19 # 8 Right shoulder 17 # 9 Left shoulder 16 # 10 Left elbow 18 # 11 Left wrist 20 # 12 Neck - # 13 Head top added # --------------------Camera estimation -------------------- def guess_init(model, focal_length, j2d, init_pose): """Initialize the camera translation via triangle similarity, by using the torso joints . :param model: SMPL model :param focal_length: camera focal length (kept fixed) :param j2d: 14x2 array of CNN joints :param init_pose: 72D vector of pose parameters used for initialization (kept fixed) :returns: 3D vector corresponding to the estimated camera translation """ cids = np.arange(0, 12) # map from LSP to SMPL joints j2d_here = j2d[cids] smpl_ids = [8, 5, 2, 1, 4, 7, 21, 19, 17, 16, 18, 20] opt_pose = ch.array(init_pose) (_, A_global) = global_rigid_transformation( opt_pose, model.J, model.kintree_table, xp=ch) Jtr = ch.vstack([g[:3, 3] for g in A_global]) Jtr = Jtr[smpl_ids].r # 9 is L shoulder, 3 is L hip # 8 is R shoulder, 2 is R hip diff3d = np.array([Jtr[9] - Jtr[3], Jtr[8] - Jtr[2]]) mean_height3d = np.mean(np.sqrt(np.sum(diff3d**2, axis=1))) diff2d = np.array([j2d_here[9] - j2d_here[3], j2d_here[8] - j2d_here[2]]) mean_height2d = np.mean(np.sqrt(np.sum(diff2d**2, axis=1))) est_d = focal_length * (mean_height3d / mean_height2d) # just set the z value init_t = np.array([0., 0., est_d]) return init_t def initialize_camera(model, j2d, img, init_pose, flength=5000., pix_thsh=25., viz=False): """Initialize camera translation and body orientation :param model: SMPL model :param j2d: 14x2 array of CNN joints :param img: h x w x 3 image :param init_pose: 72D vector of pose parameters used for initialization :param flength: camera focal length (kept fixed) :param pix_thsh: threshold (in pixel), if the distance between shoulder joints in 2D is lower than pix_thsh, the body orientation as ambiguous (so a fit is run on both the estimated one and its flip) :param viz: boolean, if True enables visualization during optimization :returns: a tuple containing the estimated camera, a boolean deciding if both the optimized body orientation and its flip should be considered, 3D vector for the body orientation """ # optimize camera translation and body orientation based on torso joints # LSP torso ids: # 2=right hip, 3=left hip, 8=right shoulder, 9=left shoulder torso_cids = [2, 3, 8, 9] # corresponding SMPL torso ids torso_smpl_ids = [2, 1, 17, 16] center = np.array([img.shape[1] / 2, img.shape[0] / 2]) # initialize camera rotation rt = ch.zeros(3) # initialize camera translation _LOGGER.info('initializing translation via similar triangles') init_t = guess_init(model, flength, j2d, init_pose) t = ch.array(init_t) # check how close the shoulder joints are try_both_orient = np.linalg.norm(j2d[8] - j2d[9]) < pix_thsh opt_pose = ch.array(init_pose) (_, A_global) = global_rigid_transformation( opt_pose, model.J, model.kintree_table, xp=ch) Jtr = ch.vstack([g[:3, 3] for g in A_global]) # initialize the camera cam = ProjectPoints( f=np.array([flength, flength]), rt=rt, t=t, k=np.zeros(5), c=center) # we are going to project the SMPL joints cam.v = Jtr if viz: viz_img = img.copy() # draw the target (CNN) joints for coord in np.around(j2d).astype(int): if (coord[0] < img.shape[1] and coord[0] >= 0 and coord[1] < img.shape[0] and coord[1] >= 0): cv2.circle(viz_img, tuple(coord), 3, [0, 255, 0]) import matplotlib.pyplot as plt plt.ion() # draw optimized joints at each iteration def on_step(_): """Draw a visualization.""" plt.figure(1, figsize=(5, 5)) plt.subplot(1, 1, 1) viz_img = img.copy() for coord in np.around(cam.r[torso_smpl_ids]).astype(int): if (coord[0] < viz_img.shape[1] and coord[0] >= 0 and coord[1] < viz_img.shape[0] and coord[1] >= 0): cv2.circle(viz_img, tuple(coord), 3, [0, 0, 255]) plt.imshow(viz_img[:, :, ::-1]) plt.draw() plt.show() plt.pause(1e-3) else: on_step = None # optimize for camera translation and body orientation free_variables = [cam.t, opt_pose[:3]] ch.minimize( # data term defined over torso joints... {'cam': j2d[torso_cids] - cam[torso_smpl_ids], # ...plus a regularizer for the camera translation 'cam_t': 1e2 * (cam.t[2] - init_t[2])}, x0=free_variables, method='dogleg', callback=on_step, options={'maxiter': 100, 'e_3': .0001, # disp set to 1 enables verbose output from the optimizer 'disp': 0}) if viz: plt.ioff() return (cam, try_both_orient, opt_pose[:3].r) # --------------------Core optimization -------------------- def optimize_on_joints(j2d, model, cam, img, prior, try_both_orient, body_orient, n_betas=10, regs=None, conf=None, viz=False): """Fit the model to the given set of joints, given the estimated camera :param j2d: 14x2 array of CNN joints :param model: SMPL model :param cam: estimated camera :param img: h x w x 3 image :param prior: mixture of gaussians pose prior :param try_both_orient: boolean, if True both body_orient and its flip are considered for the fit :param body_orient: 3D vector, initialization for the body orientation :param n_betas: number of shape coefficients considered during optimization :param regs: regressors for capsules' axis and radius, if not None enables the interpenetration error term :param conf: 14D vector storing the confidence values from the CNN :param viz: boolean, if True enables visualization during optimization :returns: a tuple containing the optimized model, its joints projected on image space,