Spaces:
Running
on
T4
Running
on
T4
File size: 12,214 Bytes
e5dd705 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 |
# Ultralytics YOLO 🚀, AGPL-3.0 license
import copy
import cv2
import numpy as np
from ultralytics.yolo.utils import LOGGER
class GMC:
def __init__(self, method='sparseOptFlow', downscale=2, verbose=None):
"""Initialize a video tracker with specified parameters."""
super().__init__()
self.method = method
self.downscale = max(1, int(downscale))
if self.method == 'orb':
self.detector = cv2.FastFeatureDetector_create(20)
self.extractor = cv2.ORB_create()
self.matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
elif self.method == 'sift':
self.detector = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
self.extractor = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
self.matcher = cv2.BFMatcher(cv2.NORM_L2)
elif self.method == 'ecc':
number_of_iterations = 5000
termination_eps = 1e-6
self.warp_mode = cv2.MOTION_EUCLIDEAN
self.criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, number_of_iterations, termination_eps)
elif self.method == 'sparseOptFlow':
self.feature_params = dict(maxCorners=1000,
qualityLevel=0.01,
minDistance=1,
blockSize=3,
useHarrisDetector=False,
k=0.04)
# self.gmc_file = open('GMC_results.txt', 'w')
elif self.method in ['file', 'files']:
seqName = verbose[0]
ablation = verbose[1]
if ablation:
filePath = r'tracker/GMC_files/MOT17_ablation'
else:
filePath = r'tracker/GMC_files/MOTChallenge'
if '-FRCNN' in seqName:
seqName = seqName[:-6]
elif '-DPM' in seqName or '-SDP' in seqName:
seqName = seqName[:-4]
self.gmcFile = open(f'{filePath}/GMC-{seqName}.txt')
if self.gmcFile is None:
raise ValueError(f'Error: Unable to open GMC file in directory:{filePath}')
elif self.method in ['none', 'None']:
self.method = 'none'
else:
raise ValueError(f'Error: Unknown CMC method:{method}')
self.prevFrame = None
self.prevKeyPoints = None
self.prevDescriptors = None
self.initializedFirstFrame = False
def apply(self, raw_frame, detections=None):
"""Apply object detection on a raw frame using specified method."""
if self.method in ['orb', 'sift']:
return self.applyFeatures(raw_frame, detections)
elif self.method == 'ecc':
return self.applyEcc(raw_frame, detections)
elif self.method == 'sparseOptFlow':
return self.applySparseOptFlow(raw_frame, detections)
elif self.method == 'file':
return self.applyFile(raw_frame, detections)
elif self.method == 'none':
return np.eye(2, 3)
else:
return np.eye(2, 3)
def applyEcc(self, raw_frame, detections=None):
"""Initialize."""
height, width, _ = raw_frame.shape
frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
H = np.eye(2, 3, dtype=np.float32)
# Downscale image (TODO: consider using pyramids)
if self.downscale > 1.0:
frame = cv2.GaussianBlur(frame, (3, 3), 1.5)
frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
width = width // self.downscale
height = height // self.downscale
# Handle first frame
if not self.initializedFirstFrame:
# Initialize data
self.prevFrame = frame.copy()
# Initialization done
self.initializedFirstFrame = True
return H
# Run the ECC algorithm. The results are stored in warp_matrix.
# (cc, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria)
try:
(cc, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria, None, 1)
except Exception as e:
LOGGER.warning(f'WARNING: find transform failed. Set warp as identity {e}')
return H
def applyFeatures(self, raw_frame, detections=None):
"""Initialize."""
height, width, _ = raw_frame.shape
frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
H = np.eye(2, 3)
# Downscale image (TODO: consider using pyramids)
if self.downscale > 1.0:
# frame = cv2.GaussianBlur(frame, (3, 3), 1.5)
frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
width = width // self.downscale
height = height // self.downscale
# Find the keypoints
mask = np.zeros_like(frame)
# mask[int(0.05 * height): int(0.95 * height), int(0.05 * width): int(0.95 * width)] = 255
mask[int(0.02 * height):int(0.98 * height), int(0.02 * width):int(0.98 * width)] = 255
if detections is not None:
for det in detections:
tlbr = (det[:4] / self.downscale).astype(np.int_)
mask[tlbr[1]:tlbr[3], tlbr[0]:tlbr[2]] = 0
keypoints = self.detector.detect(frame, mask)
# Compute the descriptors
keypoints, descriptors = self.extractor.compute(frame, keypoints)
# Handle first frame
if not self.initializedFirstFrame:
# Initialize data
self.prevFrame = frame.copy()
self.prevKeyPoints = copy.copy(keypoints)
self.prevDescriptors = copy.copy(descriptors)
# Initialization done
self.initializedFirstFrame = True
return H
# Match descriptors.
knnMatches = self.matcher.knnMatch(self.prevDescriptors, descriptors, 2)
# Filtered matches based on smallest spatial distance
matches = []
spatialDistances = []
maxSpatialDistance = 0.25 * np.array([width, height])
# Handle empty matches case
if len(knnMatches) == 0:
# Store to next iteration
self.prevFrame = frame.copy()
self.prevKeyPoints = copy.copy(keypoints)
self.prevDescriptors = copy.copy(descriptors)
return H
for m, n in knnMatches:
if m.distance < 0.9 * n.distance:
prevKeyPointLocation = self.prevKeyPoints[m.queryIdx].pt
currKeyPointLocation = keypoints[m.trainIdx].pt
spatialDistance = (prevKeyPointLocation[0] - currKeyPointLocation[0],
prevKeyPointLocation[1] - currKeyPointLocation[1])
if (np.abs(spatialDistance[0]) < maxSpatialDistance[0]) and \
(np.abs(spatialDistance[1]) < maxSpatialDistance[1]):
spatialDistances.append(spatialDistance)
matches.append(m)
meanSpatialDistances = np.mean(spatialDistances, 0)
stdSpatialDistances = np.std(spatialDistances, 0)
inliers = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances
goodMatches = []
prevPoints = []
currPoints = []
for i in range(len(matches)):
if inliers[i, 0] and inliers[i, 1]:
goodMatches.append(matches[i])
prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt)
currPoints.append(keypoints[matches[i].trainIdx].pt)
prevPoints = np.array(prevPoints)
currPoints = np.array(currPoints)
# Draw the keypoint matches on the output image
# if False:
# import matplotlib.pyplot as plt
# matches_img = np.hstack((self.prevFrame, frame))
# matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR)
# W = np.size(self.prevFrame, 1)
# for m in goodMatches:
# prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
# curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
# curr_pt[0] += W
# color = np.random.randint(0, 255, 3)
# color = (int(color[0]), int(color[1]), int(color[2]))
#
# matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)
# matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1)
# matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1)
#
# plt.figure()
# plt.imshow(matches_img)
# plt.show()
# Find rigid matrix
if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)):
H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)
# Handle downscale
if self.downscale > 1.0:
H[0, 2] *= self.downscale
H[1, 2] *= self.downscale
else:
LOGGER.warning('WARNING: not enough matching points')
# Store to next iteration
self.prevFrame = frame.copy()
self.prevKeyPoints = copy.copy(keypoints)
self.prevDescriptors = copy.copy(descriptors)
return H
def applySparseOptFlow(self, raw_frame, detections=None):
"""Initialize."""
# t0 = time.time()
height, width, _ = raw_frame.shape
frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
H = np.eye(2, 3)
# Downscale image
if self.downscale > 1.0:
# frame = cv2.GaussianBlur(frame, (3, 3), 1.5)
frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
# Find the keypoints
keypoints = cv2.goodFeaturesToTrack(frame, mask=None, **self.feature_params)
# Handle first frame
if not self.initializedFirstFrame:
# Initialize data
self.prevFrame = frame.copy()
self.prevKeyPoints = copy.copy(keypoints)
# Initialization done
self.initializedFirstFrame = True
return H
# Find correspondences
matchedKeypoints, status, err = cv2.calcOpticalFlowPyrLK(self.prevFrame, frame, self.prevKeyPoints, None)
# Leave good correspondences only
prevPoints = []
currPoints = []
for i in range(len(status)):
if status[i]:
prevPoints.append(self.prevKeyPoints[i])
currPoints.append(matchedKeypoints[i])
prevPoints = np.array(prevPoints)
currPoints = np.array(currPoints)
# Find rigid matrix
if (np.size(prevPoints, 0) > 4) and (np.size(prevPoints, 0) == np.size(prevPoints, 0)):
H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)
# Handle downscale
if self.downscale > 1.0:
H[0, 2] *= self.downscale
H[1, 2] *= self.downscale
else:
LOGGER.warning('WARNING: not enough matching points')
# Store to next iteration
self.prevFrame = frame.copy()
self.prevKeyPoints = copy.copy(keypoints)
# gmc_line = str(1000 * (time.time() - t0)) + "\t" + str(H[0, 0]) + "\t" + str(H[0, 1]) + "\t" + str(
# H[0, 2]) + "\t" + str(H[1, 0]) + "\t" + str(H[1, 1]) + "\t" + str(H[1, 2]) + "\n"
# self.gmc_file.write(gmc_line)
return H
def applyFile(self, raw_frame, detections=None):
"""Return the homography matrix based on the GCPs in the next line of the input GMC file."""
line = self.gmcFile.readline()
tokens = line.split('\t')
H = np.eye(2, 3, dtype=np.float_)
H[0, 0] = float(tokens[1])
H[0, 1] = float(tokens[2])
H[0, 2] = float(tokens[3])
H[1, 0] = float(tokens[4])
H[1, 1] = float(tokens[5])
H[1, 2] = float(tokens[6])
return H
|