File size: 8,545 Bytes
0985519 |
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 |
import numpy as np
"""
Utilities for bounding box manipulation and GIoU.
"""
import torch
from torchvision.ops.boxes import box_area
from loguru import logger
def write_results(filename, results):
save_format = '{frame},{id},{x1},{y1},{w},{h},{s},-1,-1,-1\n'
with open(filename, 'w') as f:
for frame_id, tlwhs, track_ids, scores in results:
for tlwh, track_id, score in zip(tlwhs, track_ids, scores):
if track_id < 0:
continue
x1, y1, w, h = tlwh
line = save_format.format(frame=frame_id, id=track_id, x1=round(x1, 1), y1=round(y1, 1), w=round(w, 1), h=round(h, 1), s=round(score, 2))
f.write(line)
logger.info('save results to {}'.format(filename))
def write_results_no_score(filename, results):
save_format = '{frame},{id},{x1},{y1},{w},{h},-1,-1,-1,-1\n'
with open(filename, 'w') as f:
for frame_id, tlwhs, track_ids in results:
for tlwh, track_id in zip(tlwhs, track_ids):
if track_id < 0:
continue
x1, y1, w, h = tlwh
line = save_format.format(frame=frame_id, id=track_id, x1=round(x1, 1), y1=round(y1, 1), w=round(w, 1), h=round(h, 1))
f.write(line)
logger.info('save results to {}'.format(filename))
def get_iou(bb1, bb2):
"""
Calculate the Intersection over Union (IoU) of two bounding boxes.
Parameters
----------
bb1 : dict
Keys: {'x1', 'x2', 'y1', 'y2'}
The (x1, y1) position is at the top left corner,
the (x2, y2) position is at the bottom right corner
bb2 : dict
Keys: {'x1', 'x2', 'y1', 'y2'}
The (x, y) position is at the top left corner,
the (x2, y2) position is at the bottom right corner
Returns
-------
float
in [0, 1]
"""
assert bb1['x1'] < bb1['x2']
assert bb1['y1'] < bb1['y2']
assert bb2['x1'] < bb2['x2']
assert bb2['y1'] < bb2['y2']
# determine the coordinates of the intersection rectangle
x_left = max(bb1['x1'], bb2['x1'])
y_top = max(bb1['y1'], bb2['y1'])
x_right = min(bb1['x2'], bb2['x2'])
y_bottom = min(bb1['y2'], bb2['y2'])
if x_right < x_left or y_bottom < y_top:
return 0.0
# The intersection of two axis-aligned bounding boxes is always an
# axis-aligned bounding box
intersection_area = (x_right - x_left) * (y_bottom - y_top)
# compute the area of both AABBs
bb1_area = (bb1['x2'] - bb1['x1']) * (bb1['y2'] - bb1['y1'])
bb2_area = (bb2['x2'] - bb2['x1']) * (bb2['y2'] - bb2['y1'])
# compute the intersection over union by taking the intersection
# area and dividing it by the sum of prediction + ground-truth
# areas - the interesection area
iou = intersection_area / float(bb1_area + bb2_area - intersection_area)
assert iou >= 0.0
assert iou <= 1.0
return iou
def vectorized_iou(boxes1, boxes2):
'''
this is not a standard implementation, but to incorporate with the main function
'''
x11, y11, x12, y12 = boxes1
x21, y21, x22, y22 = boxes2
xA = np.maximum(x11, np.transpose(x21))
yA = np.maximum(y11, np.transpose(y21))
xB = np.maximum(x12, np.transpose(x22))
yB = np.maximum(y12, np.transpose(y22))
interArea = np.maximum((xB-xA+1), 0) * np.maximum((yB-yA+1), 0)
boxAArea = (x12-x11+1) * (y12-y11+1)
boxBArea = (x22-x21+1) * (y22-y21+1)
iou = interArea / (boxAArea + np.transpose(boxBArea) - interArea)
return iou
def batch_iou(a, b, epsilon=1e-5):
""" Given two arrays `a` and `b` where each row contains a bounding
box defined as a list of four numbers:
[x1,y1,x2,y2]
where:
x1,y1 represent the upper left corner
x2,y2 represent the lower right corner
It returns the Intersect of Union scores for each corresponding
pair of boxes.
Args:
a: (numpy array) each row containing [x1,y1,x2,y2] coordinates
b: (numpy array) each row containing [x1,y1,x2,y2] coordinates
epsilon: (float) Small value to prevent division by zero
Returns:
(numpy array) The Intersect of Union scores for each pair of bounding
boxes.
"""
# COORDINATES OF THE INTERSECTION BOXES
x1 = np.array([a[:, 0], b[:, 0]]).max(axis=0)
y1 = np.array([a[:, 1], b[:, 1]]).max(axis=0)
x2 = np.array([a[:, 2], b[:, 2]]).min(axis=0)
y2 = np.array([a[:, 3], b[:, 3]]).min(axis=0)
# AREAS OF OVERLAP - Area where the boxes intersect
width = (x2 - x1)
height = (y2 - y1)
# handle case where there is NO overlap
width[width < 0] = 0
height[height < 0] = 0
area_overlap = width * height
# COMBINED AREAS
area_a = (a[:, 2] - a[:, 0]) * (a[:, 3] - a[:, 1])
area_b = (b[:, 2] - b[:, 0]) * (b[:, 3] - b[:, 1])
area_combined = area_a + area_b - area_overlap
# RATIO OF AREA OF OVERLAP OVER COMBINED AREA
iou = area_overlap / (area_combined + epsilon)
return iou
def clip_iou(boxes1,boxes2):
area1 = box_area(boxes1)
area2 = box_area(boxes2)
lt = torch.max(boxes1[:, :2], boxes2[:, :2])
rb = torch.min(boxes1[:, 2:], boxes2[:, 2:])
wh = (rb-lt).clamp(min=0)
inter = wh[:,0]*wh[:,1]
union = area1 + area2 - inter
iou = (inter+1e-6) / (union+1e-6)
# generalized version
# iou=iou-(inter-union)/inter
return iou
def multi_iou(boxes1, boxes2):
lt = torch.max(boxes1[...,:2], boxes2[...,:2])
rb = torch.min(boxes1[...,2:], boxes2[...,2:])
wh = (rb-lt).clamp(min=0)
wh_1 = boxes1[...,2:] - boxes1[...,:2]
wh_2 = boxes2[...,2:] - boxes2[...,:2]
inter = wh[...,0] * wh[...,1]
union = wh_1[...,0] * wh_1[...,1] + wh_2[...,0] * wh_2[...,1] - inter
iou = (inter+1e-6) / (union+1e-6)
return iou
def box_cxcywh_to_xyxy(x):
x_c, y_c, w, h = x.unbind(-1)
b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
(x_c + 0.5 * w), (y_c + 0.5 * h)]
return torch.stack(b, dim=-1)
def box_xyxy_to_cxcywh(x):
x0, y0, x1, y1 = x.unbind(-1)
b = [(x0 + x1) / 2, (y0 + y1) / 2,
(x1 - x0), (y1 - y0)]
return torch.stack(b, dim=-1)
# modified from torchvision to also return the union
def box_iou(boxes1, boxes2):
area1 = box_area(boxes1)
area2 = box_area(boxes2)
lt = torch.max(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2]
rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) # [N,M,2]
wh = (rb - lt).clamp(min=0) # [N,M,2]
inter = wh[:, :, 0] * wh[:, :, 1] # [N,M]
union = area1[:, None] + area2 - inter
iou = (inter+1e-6) / (union+1e-6)
return iou, union
def generalized_box_iou(boxes1, boxes2):
"""
Generalized IoU from https://giou.stanford.edu/
The boxes should be in [x0, y0, x1, y1] format
Returns a [N, M] pairwise matrix, where N = len(boxes1)
and M = len(boxes2)
"""
# degenerate boxes gives inf / nan results
# so do an early check
assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
assert (boxes2[:, 2:] >= boxes2[:, :2]).all()
iou, union = box_iou(boxes1, boxes2)
lt = torch.min(boxes1[:, None, :2], boxes2[:, :2])
rb = torch.max(boxes1[:, None, 2:], boxes2[:, 2:])
wh = (rb - lt).clamp(min=0) # [N,M,2]
area = wh[:, :, 0] * wh[:, :, 1]
return iou - ((area - union)+1e-6) / (area+1e-6)
def masks_to_boxes(masks):
"""Compute the bounding boxes around the provided masks
The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spatial dimensions.
Returns a [N, 4] tensors, with the boxes in xyxy format
"""
if masks.numel() == 0:
return torch.zeros((0, 4), device=masks.device)
h, w = masks.shape[-2:]
y = torch.arange(0, h, dtype=torch.float)
x = torch.arange(0, w, dtype=torch.float)
y, x = torch.meshgrid(y, x)
x_mask = (masks * x.unsqueeze(0))
x_max = x_mask.flatten(1).max(-1)[0]
x_min = x_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
y_mask = (masks * y.unsqueeze(0))
y_max = y_mask.flatten(1).max(-1)[0]
y_min = y_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
return torch.stack([x_min, y_min, x_max, y_max], 1) |