Spaces:
Running
Running
File size: 3,894 Bytes
95f8bbc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
# Copyright (c) 2018-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
#
import copy
import numpy as np
from common.mocap_dataset import MocapDataset
from common.skeleton import Skeleton
humaneva_skeleton = Skeleton(parents=[-1, 0, 1, 2, 3, 1, 5, 6, 0, 8, 9, 0, 11, 12, 1],
joints_left=[2, 3, 4, 8, 9, 10],
joints_right=[5, 6, 7, 11, 12, 13])
humaneva_cameras_intrinsic_params = [
{
'id': 'C1',
'res_w': 640,
'res_h': 480,
'azimuth': 0, # Only used for visualization
},
{
'id': 'C2',
'res_w': 640,
'res_h': 480,
'azimuth': -90, # Only used for visualization
},
{
'id': 'C3',
'res_w': 640,
'res_h': 480,
'azimuth': 90, # Only used for visualization
},
]
humaneva_cameras_extrinsic_params = {
'S1': [
{
'orientation': [0.424207, -0.4983646, -0.5802981, 0.4847012],
'translation': [4062.227, 663.2477, 1528.397],
},
{
'orientation': [0.6503354, -0.7481602, -0.0919284, 0.0941766],
'translation': [844.8131, -3805.2092, 1504.9929],
},
{
'orientation': [0.0664734, -0.0690535, 0.7416416, -0.6639132],
'translation': [-797.67377, 3916.3174, 1433.6602],
},
],
'S2': [
{
'orientation': [0.4214752, -0.4961493, -0.5838273, 0.4851187],
'translation': [4112.9121, 626.4929, 1545.2988],
},
{
'orientation': [0.6501393, -0.7476588, -0.0954617, 0.0959808],
'translation': [923.5740, -3877.9243, 1504.5518],
},
{
'orientation': [0.0699353, -0.0712403, 0.7421637, -0.662742],
'translation': [-781.4915, 3838.8853, 1444.9929],
},
],
'S3': [
{
'orientation': [0.424207, -0.4983646, -0.5802981, 0.4847012],
'translation': [4062.2271, 663.2477, 1528.3970],
},
{
'orientation': [0.6503354, -0.7481602, -0.0919284, 0.0941766],
'translation': [844.8131, -3805.2092, 1504.9929],
},
{
'orientation': [0.0664734, -0.0690535, 0.7416416, -0.6639132],
'translation': [-797.6738, 3916.3174, 1433.6602],
},
],
'S4': [
{},
{},
{},
],
}
class HumanEvaDataset(MocapDataset):
def __init__(self, path):
super().__init__(fps=60, skeleton=humaneva_skeleton)
self._cameras = copy.deepcopy(humaneva_cameras_extrinsic_params)
for cameras in self._cameras.values():
for i, cam in enumerate(cameras):
cam.update(humaneva_cameras_intrinsic_params[i])
for k, v in cam.items():
if k not in ['id', 'res_w', 'res_h']:
cam[k] = np.array(v, dtype='float32')
if 'translation' in cam:
cam['translation'] = cam['translation'] / 1000 # mm to meters
for subject in list(self._cameras.keys()):
data = self._cameras[subject]
del self._cameras[subject]
for prefix in ['Train/', 'Validate/', 'Unlabeled/Train/', 'Unlabeled/Validate/', 'Unlabeled/']:
self._cameras[prefix + subject] = data
# Load serialized dataset
data = np.load(path)['positions_3d'].item()
self._data = {}
for subject, actions in data.items():
self._data[subject] = {}
for action_name, positions in actions.items():
self._data[subject][action_name] = {
'positions': positions,
'cameras': self._cameras[subject],
}
|