File size: 5,997 Bytes
625a17f |
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 |
import argparse
import json
import tqdm
import cv2
import os
import numpy as np
from pycocotools import mask as mask_utils
import random
from PIL import Image
from natsort import natsorted
EVALMODE = "test"
# MAX_OBJ_NUM = 2 # debug
def blend_mask(input_img, binary_mask, alpha=0.5, color="g"):
if input_img.ndim == 2:
return input_img
mask_image = np.zeros(input_img.shape, np.uint8)
if color == "r":
mask_image[:, :, 0] = 255
if color == "g":
mask_image[:, :, 1] = 255
if color == "b":
mask_image[:, :, 2] = 255
if color == "o":
mask_image[:, :, 0] = 255
mask_image[:, :, 1] = 165
mask_image[:, :, 2] = 0
if color == "c":
mask_image[:, :, 0] = 0
mask_image[:, :, 1] = 255
mask_image[:, :, 2] = 255
if color == "p":
mask_image[:, :, 0] = 128
mask_image[:, :, 1] = 0
mask_image[:, :, 2] = 128
mask_image = mask_image * np.repeat(binary_mask[:, :, np.newaxis], 3, axis=2)
blend_image = input_img[:, :, :].copy()
pos_idx = binary_mask > 0
for ind in range(input_img.ndim):
ch_img1 = input_img[:, :, ind]
ch_img2 = mask_image[:, :, ind]
ch_img3 = blend_image[:, :, ind]
ch_img3[pos_idx] = alpha * ch_img1[pos_idx] + (1 - alpha) * ch_img2[pos_idx]
blend_image[:, :, ind] = ch_img3
return blend_image
def upsample_mask(mask, frame):
H, W = frame.shape[:2]
mH, mW = mask.shape[:2]
if W > H:
ratio = mW / W
h = H * ratio
diff = int((mH - h) // 2)
if diff == 0:
mask = mask
else:
mask = mask[diff:-diff]
else:
ratio = mH / H
w = W * ratio
diff = int((mW - w) // 2)
if diff == 0:
mask = mask
else:
mask = mask[:, diff:-diff]
mask = cv2.resize(mask, (W, H))
return mask
def downsample(mask, frame):
H, W = frame.shape[:2]
mH, mW = mask.shape[:2]
mask = cv2.resize(mask, (W, H))
return mask
#datapath /datasegswap
#inference_path /inference_xmem_ego_last/coco
#output /vis_piano
#--show_gt要加上
if __name__ == "__main__":
color = ['g', 'r', 'b', 'o', 'c', 'p']
data_path = "/scratch/yuqian_fu/data_imgs/b511dfed-58f4-4c91-bf0a-f8ce9d47aea9/cam01"
output_path = "/scratch/yuqian_fu/iccv_vis_imgs/sam2/exo"
# output_path = "/scratch/yuqian_fu/iccv_vis_imgs/ego2exo"
mask_path = "/scratch/yuqian_fu/iccv_results_memory/sam2/exo"
# mask_path = "/scratch/yuqian_fu/iccv_results_memory/ego2exo"
takes_ids = ["b511dfed-58f4-4c91-bf0a-f8ce9d47aea9"]
for take_id in tqdm.tqdm(takes_ids):
prediction_path = os.path.join(mask_path, take_id)
file_names = natsorted(os.listdir(prediction_path))
idxs = [f.split(".")[0] for f in file_names]
INSTANCE_ALL = []
# 先统计该take下所有的物体个数及对应id
for id in idxs:
frame_idx = id
frame = cv2.imread(
f"{data_path}/{frame_idx}.jpg"
)
mask = Image.open(f"{prediction_path}/{frame_idx}.png")
mask = np.array(mask)
unique_instances = np.unique(mask)
unique_instances = unique_instances[unique_instances != 0]
if len(unique_instances) > 0:
for instance_value in unique_instances:
if instance_value not in INSTANCE_ALL:
INSTANCE_ALL.append(instance_value)
print("INSTANCE_ALL:", INSTANCE_ALL) # debug
# 开始上色
for id in idxs:
frame_idx = id
frame = cv2.imread(
f"{data_path}/{frame_idx}.jpg"
)
mask = Image.open(f"{prediction_path}/{frame_idx}.png")
mask = np.array(mask)
unique_instances = np.unique(mask)
unique_instances = unique_instances[unique_instances != 0]
# print("unique_instances:", unique_instances) # debug
if len(unique_instances) == len(INSTANCE_ALL):
for i,instance_value in enumerate(unique_instances):
binary_mask = (mask == instance_value).astype(np.uint8)
binary_mask = cv2.resize(binary_mask, (frame.shape[1], frame.shape[0]))
binary_mask = upsample_mask(binary_mask, frame)
out = blend_mask(frame, binary_mask, color=color[0])
os.makedirs(
f"{output_path}/{take_id}/obj_{instance_value}", #debug
exist_ok=True,
)
cv2.imwrite(
f"{output_path}/{take_id}/obj_{instance_value}/{frame_idx}.jpg",
out,
)
elif len(unique_instances) < len(INSTANCE_ALL):
for i, instance_value in enumerate(INSTANCE_ALL):
if instance_value in unique_instances:
binary_mask = (mask == instance_value).astype(np.uint8)
binary_mask = cv2.resize(binary_mask, (frame.shape[1], frame.shape[0]))
binary_mask = upsample_mask(binary_mask, frame)
out = blend_mask(frame, binary_mask, color=color[0])
else:
zero_mask = np.zeros((frame.shape[0], frame.shape[1]), dtype=np.uint8)
out = blend_mask(frame, zero_mask, color=color[0])
os.makedirs(
f"{output_path}/{take_id}/obj_{instance_value}", #debug
exist_ok=True,
)
cv2.imwrite(
f"{output_path}/{take_id}/obj_{instance_value}/{frame_idx}.jpg",
out,
)
|