[139527]: / eval / detection / bbox.py

Download this file

233 lines (203 with data), 9.1 kB

  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
from .utils import *
class BoundingBox:
def __init__(self,
imageName,
classId,
x,
y,
w,
h,
typeCoordinates=CoordinatesType.Absolute,
imgSize=None,
bbType=BBType.GroundTruth,
classConfidence=None,
format=BBFormat.XYWH):
"""Constructor.
Args:
imageName: String representing the image name.
classId: String value representing class id.
x: Float value representing the X upper-left coordinate of the bounding box.
y: Float value representing the Y upper-left coordinate of the bounding box.
w: Float value representing the width bounding box.
h: Float value representing the height bounding box.
typeCoordinates: (optional) Enum (Relative or Absolute) represents if the bounding box
coordinates (x,y,w,h) are absolute or relative to size of the image. Default:'Absolute'.
imgSize: (optional) 2D vector (width, height)=>(int, int) represents the size of the
image of the bounding box. If typeCoordinates is 'Relative', imgSize is required.
bbType: (optional) Enum (Groundtruth or Detection) identifies if the bounding box
represents a ground truth or a detection. If it is a detection, the classConfidence has
to be informed.
classConfidence: (optional) Float value representing the confidence of the detected
class. If detectionType is Detection, classConfidence needs to be informed.
format: (optional) Enum (BBFormat.XYWH or BBFormat.XYX2Y2) indicating the format of the
coordinates of the bounding boxes. BBFormat.XYWH: <left> <top> <width> <height>
BBFormat.XYX2Y2: <left> <top> <right> <bottom>.
"""
self._imageName = imageName
self._typeCoordinates = typeCoordinates
if typeCoordinates == CoordinatesType.Relative and imgSize is None:
raise IOError(
'Parameter \'imgSize\' is required. It is necessary to inform the image size.')
if bbType == BBType.Detected and classConfidence is None:
raise IOError(
'For bbType=\'Detection\', it is necessary to inform the classConfidence value.')
# if classConfidence != None and (classConfidence < 0 or classConfidence > 1):
# raise IOError('classConfidence value must be a real value between 0 and 1. Value: %f' %
# classConfidence)
self._classConfidence = classConfidence
self._bbType = bbType
self._classId = classId
self._format = format
# If relative coordinates, convert to absolute values
# For relative coords: (x,y,w,h)=(X_center/img_width ,
# Y_center/img_height)
if (typeCoordinates == CoordinatesType.Relative):
(self._x, self._y, self._w, self._h) = convertToAbsoluteValues(
imgSize, (x, y, w, h))
self._width_img = imgSize[0]
self._height_img = imgSize[1]
if format == BBFormat.XYWH:
self._x2 = self._w
self._y2 = self._h
self._w = self._x2 - self._x
self._h = self._y2 - self._y
else:
raise IOError(
'For relative coordinates, the format must be XYWH (x,y,width,height)')
# For absolute coords: (x,y,w,h)=real bb coords
else:
self._x = x
self._y = y
if format == BBFormat.XYWH:
self._w = w
self._h = h
self._x2 = self._x + self._w
self._y2 = self._y + self._h
else: # format == BBFormat.XYX2Y2: <left> <top> <right> <bottom>.
self._x2 = w
self._y2 = h
self._w = self._x2 - self._x
self._h = self._y2 - self._y
if imgSize is None:
self._width_img = None
self._height_img = None
else:
self._width_img = imgSize[0]
self._height_img = imgSize[1]
def getAbsoluteBoundingBox(self, format=BBFormat.XYWH):
if format == BBFormat.XYWH:
return (self._x, self._y, self._w, self._h)
elif format == BBFormat.XYX2Y2:
return (self._x, self._y, self._x2, self._y2)
def getRelativeBoundingBox(self, imgSize=None):
if imgSize is None and self._width_img is None and self._height_img is None:
raise IOError(
'Parameter \'imgSize\' is required. It is necessary to inform the image size.')
if imgSize is not None:
return convertToRelativeValues(
(imgSize[0], imgSize[1]), (self._x, self._x2, self._y, self._y2))
else:
return convertToRelativeValues(
(self._width_img, self._height_img), (self._x, self._x2, self._y, self._y2))
def getImageName(self):
return self._imageName
def getConfidence(self):
return self._classConfidence
def getFormat(self):
return self._format
def getClassId(self):
return self._classId
def getImageSize(self):
return (self._width_img, self._height_img)
def getCoordinatesType(self):
return self._typeCoordinates
def getBBType(self):
return self._bbType
@staticmethod
def compare(det1, det2):
det1BB = det1.getAbsoluteBoundingBox()
det1ImgSize = det1.getImageSize()
det2BB = det2.getAbsoluteBoundingBox()
det2ImgSize = det2.getImageSize()
if det1.getClassId() == det2.getClassId() and \
det1.classConfidence == det2.classConfidenc() and \
det1BB[0] == det2BB[0] and \
det1BB[1] == det2BB[1] and \
det1BB[2] == det2BB[2] and \
det1BB[3] == det2BB[3] and \
det1ImgSize[0] == det1ImgSize[0] and \
det2ImgSize[1] == det2ImgSize[1]:
return True
return False
@staticmethod
def clone(boundingBox):
absBB = boundingBox.getAbsoluteBoundingBox(format=BBFormat.XYWH)
# return (self._x,self._y,self._x2,self._y2)
newBoundingBox = BoundingBox(
boundingBox.getImageName(),
boundingBox.getClassId(),
absBB[0],
absBB[1],
absBB[2],
absBB[3],
typeCoordinates=boundingBox.getCoordinatesType(),
imgSize=boundingBox.getImageSize(),
bbType=boundingBox.getBBType(),
classConfidence=boundingBox.getConfidence(),
format=BBFormat.XYWH)
return newBoundingBox
class BoundingBoxes:
def __init__(self):
self._boundingBoxes = []
def addBoundingBox(self, bb):
self._boundingBoxes.append(bb)
def removeBoundingBox(self, _boundingBox):
for d in self._boundingBoxes:
if BoundingBox.compare(d, _boundingBox):
del self._boundingBoxes[d]
return
def removeAllBoundingBoxes(self):
self._boundingBoxes = []
def getBoundingBoxes(self):
return self._boundingBoxes
def getBoundingBoxByClass(self, classId):
boundingBoxes = []
for d in self._boundingBoxes:
if d.getClassId() == classId: # get only specified bounding box type
boundingBoxes.append(d)
return boundingBoxes
def getClasses(self):
classes = []
for d in self._boundingBoxes:
c = d.getClassId()
if c not in classes:
classes.append(c)
return classes
def getBoundingBoxesByType(self, bbType):
# get only specified bb type
return [d for d in self._boundingBoxes if d.getBBType() == bbType]
def getBoundingBoxesByImageName(self, imageName):
# get only specified bb type
return [d for d in self._boundingBoxes if d.getImageName() == imageName]
def count(self, bbType=None):
if bbType is None: # Return all bounding boxes
return len(self._boundingBoxes)
count = 0
for d in self._boundingBoxes:
if d.getBBType() == bbType: # get only specified bb type
count += 1
return count
def clone(self):
newBoundingBoxes = BoundingBoxes()
for d in self._boundingBoxes:
det = BoundingBox.clone(d)
newBoundingBoxes.addBoundingBox(det)
return newBoundingBoxes
def drawAllBoundingBoxes(self, image, imageName):
bbxes = self.getBoundingBoxesByImageName(imageName)
for bb in bbxes:
if bb.getBBType() == BBType.GroundTruth: # if ground truth
image = add_bb_into_image(image, bb, color=(0, 255, 0)) # green
else: # if detection
image = add_bb_into_image(image, bb, color=(255, 0, 0)) # red
return image