File size: 14,576 Bytes
8503a3c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
#!/usr/bin/env python3
# This code from https://github.com/lllyasviel/ControlNet
import os
import argparse
import cv2
import numpy as np
import math
import glob
from scipy.ndimage import gaussian_filter
import matplotlib.pyplot as plt
import torch
import urllib
import openpose.util as util
from openpose.model import bodypose_model
import json
class Body(object):
def __init__(self, the_model_path):
self.model = bodypose_model()
if torch.cuda.is_available():
self.model = self.model.cuda()
model_dict = util.transfer(self.model, torch.load(the_model_path))
self.model.load_state_dict(model_dict)
self.model.eval()
def __call__(self, ori_img):
# scale_search = [0.5, 1.0, 1.5, 2.0]
scale_search = [0.5]
boxsize = 368
stride = 8
padValue = 128
threshold1 = 0.1
threshold2 = 0.05
multiplier = [x * boxsize / ori_img.shape[0] for x in scale_search]
heatmap_avg = np.zeros((ori_img.shape[0], ori_img.shape[1], 19))
paf_avg = np.zeros((ori_img.shape[0], ori_img.shape[1], 38))
for m in range(len(multiplier)):
scale = multiplier[m]
imageToTest = cv2.resize(ori_img, (0, 0), fx=scale, fy=scale, interpolation=cv2.INTER_CUBIC)
imageToTest_padded, pad = util.padRightDownCorner(imageToTest, stride, padValue)
im = np.transpose(np.float32(imageToTest_padded[:, :, :, np.newaxis]), (3, 2, 0, 1)) / 256 - 0.5
im = np.ascontiguousarray(im)
data = torch.from_numpy(im).float()
if torch.cuda.is_available():
data = data.cuda()
# data = data.permute([2, 0, 1]).unsqueeze(0).float()
with torch.no_grad():
Mconv7_stage6_L1, Mconv7_stage6_L2 = self.model(data)
Mconv7_stage6_L1 = Mconv7_stage6_L1.cpu().numpy()
Mconv7_stage6_L2 = Mconv7_stage6_L2.cpu().numpy()
# extract outputs, resize, and remove padding
# output 1 is heatmaps
# heatmap = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[1]].data), (1, 2, 0))
heatmap = np.transpose(np.squeeze(Mconv7_stage6_L2), (1, 2, 0))
heatmap = cv2.resize(heatmap, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
heatmap = heatmap[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
heatmap = cv2.resize(heatmap, (ori_img.shape[1], ori_img.shape[0]), interpolation=cv2.INTER_CUBIC)
# paf = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[0]].data), (1, 2, 0)) # output 0 is PAFs
paf = np.transpose(np.squeeze(Mconv7_stage6_L1), (1, 2, 0)) # output 0 is PAFs
paf = cv2.resize(paf, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
paf = paf[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
paf = cv2.resize(paf, (ori_img.shape[1], ori_img.shape[0]), interpolation=cv2.INTER_CUBIC)
heatmap_avg += heatmap_avg + heatmap / len(multiplier)
paf_avg += + paf / len(multiplier)
all_peaks = []
peak_counter = 0
for part in range(18):
map_ori = heatmap_avg[:, :, part]
one_heatmap = gaussian_filter(map_ori, sigma=3)
map_left = np.zeros(one_heatmap.shape)
map_left[1:, :] = one_heatmap[:-1, :]
map_right = np.zeros(one_heatmap.shape)
map_right[:-1, :] = one_heatmap[1:, :]
map_up = np.zeros(one_heatmap.shape)
map_up[:, 1:] = one_heatmap[:, :-1]
map_down = np.zeros(one_heatmap.shape)
map_down[:, :-1] = one_heatmap[:, 1:]
peaks_binary = np.logical_and.reduce(
(one_heatmap >= map_left, one_heatmap >= map_right, one_heatmap >= map_up,
one_heatmap >= map_down, one_heatmap > threshold1))
peaks = list(zip(np.nonzero(peaks_binary)[1], np.nonzero(peaks_binary)[0])) # note reverse
peaks_with_score = [x + (map_ori[x[1], x[0]],) for x in peaks]
peak_id = range(peak_counter, peak_counter + len(peaks))
peaks_with_score_and_id = [peaks_with_score[i] + (peak_id[i],) for i in range(len(peak_id))]
all_peaks.append(peaks_with_score_and_id)
peak_counter += len(peaks)
# find connection in the specified sequence, center 29 is in the position 15
limbSeq = [[2, 3], [2, 6], [3, 4], [4, 5], [6, 7], [7, 8], [2, 9], [9, 10],
[10, 11], [2, 12], [12, 13], [13, 14], [2, 1], [1, 15], [15, 17],
[1, 16], [16, 18], [3, 17], [6, 18]]
# the middle joints heatmap correspondence
mapIdx = [[31, 32], [39, 40], [33, 34], [35, 36], [41, 42], [43, 44], [19, 20], [21, 22],
[23, 24], [25, 26], [27, 28], [29, 30], [47, 48], [49, 50], [53, 54], [51, 52],
[55, 56], [37, 38], [45, 46]]
connection_all = []
special_k = []
mid_num = 10
for k in range(len(mapIdx)):
score_mid = paf_avg[:, :, [x - 19 for x in mapIdx[k]]]
candA = all_peaks[limbSeq[k][0] - 1]
candB = all_peaks[limbSeq[k][1] - 1]
nA = len(candA)
nB = len(candB)
# indexA, indexB = limbSeq[k]
if nA != 0 and nB != 0:
connection_candidate = []
for i in range(nA):
for j in range(nB):
vec = np.subtract(candB[j][:2], candA[i][:2])
norm = math.sqrt(vec[0] * vec[0] + vec[1] * vec[1])
norm = max(0.001, norm)
vec = np.divide(vec, norm)
startend = list(zip(np.linspace(candA[i][0], candB[j][0], num=mid_num),
np.linspace(candA[i][1], candB[j][1], num=mid_num)))
vec_x = np.array([score_mid[int(round(startend[index][1])), int(round(startend[index][0])), 0]
for index in range(len(startend))])
vec_y = np.array([score_mid[int(round(startend[index][1])), int(round(startend[index][0])), 1]
for index in range(len(startend))])
score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1])
score_with_dist_prior = sum(score_midpts) / len(score_midpts) + min(
0.5 * ori_img.shape[0] / norm - 1, 0)
criterion1 = len(np.nonzero(score_midpts > threshold2)[0]) > 0.8 * len(score_midpts)
criterion2 = score_with_dist_prior > 0
if criterion1 and criterion2:
connection_candidate.append(
[i, j, score_with_dist_prior, score_with_dist_prior + candA[i][2] + candB[j][2]])
connection_candidate = sorted(connection_candidate, key=lambda x: x[2], reverse=True)
connection = np.zeros((0, 5))
for c in range(len(connection_candidate)):
i, j, s = connection_candidate[c][0:3]
if i not in connection[:, 3] and j not in connection[:, 4]:
connection = np.vstack([connection, [candA[i][3], candB[j][3], s, i, j]])
if len(connection) >= min(nA, nB):
break
connection_all.append(connection)
else:
special_k.append(k)
connection_all.append([])
# last number in each row is the total parts number of that person
# the second last number in each row is the score of the overall configuration
subset = -1 * np.ones((0, 20))
candidate = np.array([item for sublist in all_peaks for item in sublist])
for k in range(len(mapIdx)):
if k not in special_k:
partAs = connection_all[k][:, 0]
partBs = connection_all[k][:, 1]
indexA, indexB = np.array(limbSeq[k]) - 1
for i in range(len(connection_all[k])): # = 1:size(temp,1)
found = 0
subset_idx = [-1, -1]
for j in range(len(subset)): # 1:size(subset,1):
if subset[j][indexA] == partAs[i] or subset[j][indexB] == partBs[i]:
subset_idx[found] = j
found += 1
if found == 1:
j = subset_idx[0]
if subset[j][indexB] != partBs[i]:
subset[j][indexB] = partBs[i]
subset[j][-1] += 1
subset[j][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
elif found == 2: # if found 2 and disjoint, merge them
j1, j2 = subset_idx
membership = ((subset[j1] >= 0).astype(int) + (subset[j2] >= 0).astype(int))[:-2]
if len(np.nonzero(membership == 2)[0]) == 0: # merge
subset[j1][:-2] += (subset[j2][:-2] + 1)
subset[j1][-2:] += subset[j2][-2:]
subset[j1][-2] += connection_all[k][i][2]
subset = np.delete(subset, j2, 0)
else: # as like found == 1
subset[j1][indexB] = partBs[i]
subset[j1][-1] += 1
subset[j1][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
# if no partA is found in the subset, create a new subset
elif not found and k < 17:
row = -1 * np.ones(20)
row[indexA] = partAs[i]
row[indexB] = partBs[i]
row[-1] = 2
row[-2] = sum(candidate[connection_all[k][i, :2].astype(int), 2]) + connection_all[k][i][2]
subset = np.vstack([subset, row])
# delete some rows of subset which has few parts occur
deleteIdx = []
for i in range(len(subset)):
if subset[i][-1] < 4 or subset[i][-2] / subset[i][-1] < 0.4:
deleteIdx.append(i)
subset = np.delete(subset, deleteIdx, axis=0)
# subset: n*20 array, 0-17 is the index in candidate, 18 is the total score, 19 is the total parts
# candidate: x, y, score, id
return candidate, subset
def get_pose_json(ori_img):
height, width, channels = ori_img.shape
candidate, subset = body_estimation(ori_img)
if len(candidate) == 0 or len(subset) == 0:
print("No poses found in the input image.")
return None
candidate_int = candidate.astype(int)
candidate_list = candidate_int[:, :2].tolist()
data = {
"width": width,
"height": height,
"keypoints": candidate_list
}
candidate_json = json.dumps(data)
return candidate_json
def process_image(this_input_image, the_body_estimation, these_args):
output_filename = '.'.join(this_input_image.split('.')[:-1]) + '.openpose.png'
if os.path.isfile(output_filename) and not args.force:
print(f"Output file {output_filename} already exists, skipping {this_input_image}")
return
ori_img = cv2.imread(this_input_image) # B,G,R order
# height, width, channels = ori_img.shape
try:
candidate, subset = the_body_estimation(ori_img)
except Exception as e:
print(f"Error processing image {input_image}: {e}")
return
if len(candidate) == 0 or len(subset) == 0:
print(f"No poses found in the input image {input_image}.")
return
if these_args.json_output:
candidate_json = get_pose_json(ori_img)
output_filename = '.'.join(input_image.split('.')[:-1]) + '.openpose.json'
with open(output_filename, 'w') as f:
f.write(candidate_json)
canvas = np.zeros_like(ori_img)
canvas.fill(0)
canvas = util.draw_bodypose(canvas, candidate, subset)
cv2.imwrite(output_filename, canvas)
if these_args.show_image:
plt.imshow(canvas[:, :, [2, 1, 0]])
plt.show()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Body Pose Estimation using OpenPose', add_help=True)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument("-i", "--input_image", help="Path to the input image", type=str)
group.add_argument("-d", "--directory", help="Directory to search for images", type=str)
parser.add_argument("-p", "--patterns", help="Pattern to match for images in directory", type=str)
parser.add_argument("-r", "--recursive", help="Search for files in subdirectories recursively",
action="store_true")
parser.add_argument("-s", "--show_image", help="Display the output image", action="store_true")
parser.add_argument("-j", "--json_output", help="Save JSON output to file", action="store_true")
parser.add_argument("-f", "--force", help="Force processing of images even if output file already exists",
action="store_true")
args = parser.parse_args()
script_path = os.path.abspath(__file__)
script_dir = os.path.dirname(script_path)
model_dir = os.path.join(script_dir, "model")
os.makedirs(model_dir, exist_ok=True)
model_path = os.path.join(model_dir, "body_pose_model.pth")
if not os.path.isfile(model_path):
body_model_path = \
"https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/body_pose_model.pth"
urllib.request.urlretrieve(body_model_path, model_path)
body_estimation = Body(model_path)
if args.input_image:
images = [args.input_image]
else:
patterns = args.patterns.split(',')
for pattern in patterns:
for input_image in glob.iglob(os.path.join(args.directory, '**', pattern)
if args.recursive else os.path.join(args.directory, pattern),
recursive=args.recursive):
print(f"Processing {input_image}")
process_image(input_image, body_estimation, args)
|