I am trying to horizontally stretch an image in a very specific way. Each x prime coordinate should follow a tangent path with respect to the original x coordinate. I believe there are two ways to do this:
Inverse the tangent function and map it normally
Map the tangent function and then inverse the mapping
Using this answer for map inversion, Im trying to figure out why the two images are not the same. I know that the first method gives me the correct image that I'm looking for, so why doesnt the second method work? Is it because of the "limited precision" that #ChristophRackwitz commented on the answer?
import cv2
import glob
import numpy as np
import math
A = -1010
B = -3.931
C = 5.258
D = 978.3
M = -193.8
N = 1740
def get_tan_func_value(x):
return A * math.tan((((x-N)/M)+B)/C) + D
def get_inverse_tan_func_value(x):
return M * (C*math.atan((x-D)/A) - B) + N
# answer from linked post
def invert_map(F, shape):
I = np.zeros_like(F)
I[:,:,1], I[:,:,0] = np.indices(shape)
P = np.copy(I)
for i in range(10):
P += I - cv2.remap(F, P, None, interpolation=cv2.INTER_LINEAR)
return P
# import image
images = glob.glob('*.jpg')
img = cv2.imread(images[0])
h, w = img.shape[:2]
map_x_tan = np.zeros((img.shape[0], img.shape[1]), dtype=np.float32)
map_x_inverse_tan = np.zeros((img.shape[0], img.shape[1]), dtype=np.float32)
map_y = np.zeros((img.shape[0], img.shape[1]), dtype=np.float32)
# x tan function map
for i in range(map_x_tan.shape[0]):
map_x_tan[i,:] = [get_tan_func_value(x) for x in range(map_x_tan.shape[1])]
# x inverse tan function map
for i in range(map_x_inverse_tan.shape[0]):
map_x_inverse_tan[i,:] = [get_inverse_tan_func_value(x) for x in range(map_x_inverse_tan.shape[1])]
# default y map
for j in range(map_y.shape[1]):
map_y[:,j] = [y for y in range(map_y.shape[0])]
# convert x tan map to 2 channel (x,y) map
(xymap_tan, _) = cv2.convertMaps(map1=map_x_tan, map2=map_y, dstmap1type=cv2.CV_32FC2)
# invert the 2 channel x tan map
xymap_inverted = invert_map(xymap_tan, (h,w))
# remap and write the target image (inverse tan function with normal map)
target = cv2.remap(img, map_x_inverse_tan, map_y, cv2.INTER_LINEAR)
cv2.imwrite("target.jpg", target)
# remap and write the attempted image (normal tan function with inverted map)
attempt = cv2.remap(img, xymap_inverted, None, cv2.INTER_LINEAR)
cv2.imwrite("attempt.jpg", attempt)
Method 1: Target Image
Method 2: Attempt Image
The results show that the attempt (normal tan function with inverted map) has less stretching near the edges of the image than expected. Almost everywhere else on the images are identical except the edges. I did not post the original picture to save space.
I've played around with that invert_map procedure. It seems slightly susceptible to oscillation.
use this instead:
def invert_map(F):
(h, w) = F.shape[:2] # (h, w, 2), "xymap"
I = np.zeros_like(F)
I[:,:,1], I[:,:,0] = np.indices((h,w)) # identity map
P = np.copy(I)
for i in range(10):
correction = I - cv2.remap(F, P, None, interpolation=cv2.INTER_LINEAR)
P += correction * 0.5
return P
I simply damped the correction by 0.5, which makes the fixed point iteration tamer, converging a lot faster too.
In my experiments with your tan map, I've found that 5-10 iterations are good enough already, and there's no further progress in further iterations.
Entire notebook of my explorations: https://gist.github.com/crackwitz/67f76f8a9eff21476b080c06d20660d0
Feature request: https://github.com/opencv/opencv/issues/22120
I'm trying to implement the loss function of the classic Image Colorization paper by Levin et al (2004) in Tensorflow/Keras:
This is the weights equation (correlation between intensities):
y is every neighboring pixel of x in a 3x3 window and w is the weight for each of these pixels.
The weights require computing the mean and variance for the neighborhood of every pixel.
I couldn't find a function that would allow me to write this loss function in a symbolic way, and I'm thinking I should write it in a loop where I calculate the w for each window.
How can I write this Loss function in Tensorflow In a Symbolic way or in loops?
Thanks so much.
EDIT: Here's the code I've come up for calculating the weights in Numpy:
import cv2
import numpy as np
im = cv2.resize(cv2.imread('./Image.jpg', 0), (256, 256)) / np.float32(255.0)
M = 3
N = 3
# Split the image into 3x3 windows
windows = [im[x:x + M, y:y + N] for x in range(0, im.shape[0], M) for y in range(0, im.shape[1], N)]
# Calculate the correlation for each window
weights = [1 + np.corrcoef(tile) for tile in windows]
I think this code computes the value in your formula:
import tensorflow as tf
from itertools import product
SIGMA = 1.0
dtype = tf.float32
# Input images batch
img = tf.placeholder(dtype, [None, None, None])
img_shape = tf.shape(img)
img_height = img_shape[1]
img_width = img_shape[2]
# Compute 3 x 3 block means
mean_filter = tf.ones((3, 3), dtype) / 9
img_mean = tf.nn.conv2d(img[:, :, :, tf.newaxis],
mean_filter[:, :, tf.newaxis, tf.newaxis],
[1, 1, 1, 1], 'VALID')[:, :, :, 0]
# Remove 1px border
img_clip = img[:, 1:-1, 1:-1]
# Difference between pixel intensity and its block mean
x_diff = img_clip - img_mean
# Compute neighboring pixel loss contributions
contributions = []
for i, j in product((-1, 0, 1), repeat=2):
if i == j == 0: continue
# Take "shifted" image
displaced_img = img[:, 1 + i:img_width - 1 + i, 1 + j:img_height - 1 + j]
# Compute difference with mean of corresponding pixel block
y_diff = displaced_img - img_mean
# Weights formula
weight = 1 + x_diff * y_diff / (SIGMA ** 2)
# Contribution of this displaced image to the loss of each pixel
contribution = weight * displaced_img
contributions.append(contribution)
contributions = tf.add_n(contributions)
# Compute loss value
loss = tf.reduce_sum(tf.squared_difference(img_clip, contributions))
The loss for the pixels along the image border is not computed, since in principle is not well defined in the formula, although you could make a few changes to take them into account if you want (change convolution to "'SAME'", pad where necessary, etc.).
this is a mean squared error of a 3 x 3 windows. right?
sounds like a GLCM matrix for texture analysis do you want apply this loss function for every 3x3 windows in the image?
I think that is better build the function that make this calculation with a Random weight in Numpy so after try build with TF to try a optimization.
I'm currently attempting to implement this algorithm for volume rendering in Python, and am conceptually confused about their method of generating the LH histogram (see section 3.1, page 4).
I have a 3D stack of DICOM images, and calculated its gradient magnitude and the 2 corresponding azimuth and elevation angles with it (which I found out about here), as well as finding the second derivative.
Now, the algorithm is asking me to iterate through a set of voxels, and "track a path by integrating the gradient field in both directions...using the second order Runge-Kutta method with an integration step of one voxel".
What I don't understand is how to use the 2 angles I calculated to integrate the gradient field in said direction. I understand that you can use trilinear interpolation to get intermediate voxel values, but I don't understand how to get the voxel coordinates I want using the angles I have.
In other words, I start at a given voxel position, and want to take a 1 voxel step in the direction of the 2 angles calculated for that voxel (one in the x-y direction, the other in the z-direction). How would I take this step at these 2 angles and retrieve the new (x, y, z) voxel coordinates?
Apologies in advance, as I have a very basic background in Calc II/III, so vector fields/visualization of 3D spaces is still a little rough for me.
Creating 3D stack of DICOM images:
def collect_data(data_path):
print "collecting data"
files = [] # create an empty list
for dirName, subdirList, fileList in os.walk(data_path):
for filename in fileList:
if ".dcm" in filename:
files.append(os.path.join(dirName,filename))
# Get reference file
ref = dicom.read_file(files[0])
# Load dimensions based on the number of rows, columns, and slices (along the Z axis)
pixel_dims = (int(ref.Rows), int(ref.Columns), len(files))
# Load spacing values (in mm)
pixel_spacings = (float(ref.PixelSpacing[0]), float(ref.PixelSpacing[1]), float(ref.SliceThickness))
x = np.arange(0.0, (pixel_dims[0]+1)*pixel_spacings[0], pixel_spacings[0])
y = np.arange(0.0, (pixel_dims[1]+1)*pixel_spacings[1], pixel_spacings[1])
z = np.arange(0.0, (pixel_dims[2]+1)*pixel_spacings[2], pixel_spacings[2])
# Row and column directional cosines
orientation = ref.ImageOrientationPatient
# This will become the intensity values
dcm = np.zeros(pixel_dims, dtype=ref.pixel_array.dtype)
origins = []
# loop through all the DICOM files
for filename in files:
# read the file
ds = dicom.read_file(filename)
#get pixel spacing and origin information
origins.append(ds.ImagePositionPatient) #[0,0,0] coordinates in real 3D space (in mm)
# store the raw image data
dcm[:, :, files.index(filename)] = ds.pixel_array
return dcm, origins, pixel_spacings, orientation
Calculating gradient magnitude:
def calculate_gradient_magnitude(dcm):
print "calculating gradient magnitude"
gradient_magnitude = []
gradient_direction = []
gradx = np.zeros(dcm.shape)
sobel(dcm,0,gradx)
grady = np.zeros(dcm.shape)
sobel(dcm,1,grady)
gradz = np.zeros(dcm.shape)
sobel(dcm,2,gradz)
gradient = np.sqrt(gradx**2 + grady**2 + gradz**2)
azimuthal = np.arctan2(grady, gradx)
elevation = np.arctan(gradz,gradient)
azimuthal = np.degrees(azimuthal)
elevation = np.degrees(elevation)
return gradient, azimuthal, elevation
Converting to patient coordinate system to get actual voxel position:
def get_patient_position(dcm, origins, pixel_spacing, orientation):
"""
Image Space --> Anatomical (Patient) Space is an affine transformation
using the Image Orientation (Patient), Image Position (Patient), and
Pixel Spacing properties from the DICOM header
"""
print "getting patient coordinates"
world_coordinates = np.empty((dcm.shape[0], dcm.shape[1],dcm.shape[2], 3))
affine_matrix = np.zeros((4,4), dtype=np.float32)
rows = dcm.shape[0]
cols = dcm.shape[1]
num_slices = dcm.shape[2]
image_orientation_x = np.array([ orientation[0], orientation[1], orientation[2] ]).reshape(3,1)
image_orientation_y = np.array([ orientation[3], orientation[4], orientation[5] ]).reshape(3,1)
pixel_spacing_x = pixel_spacing[0]
# Construct affine matrix
# Method from:
# http://nipy.org/nibabel/dicom/dicom_orientation.html
T_1 = origins[0]
T_n = origins[num_slices-1]
affine_matrix[0,0] = image_orientation_y[0] * pixel_spacing[0]
affine_matrix[0,1] = image_orientation_x[0] * pixel_spacing[1]
affine_matrix[0,3] = T_1[0]
affine_matrix[1,0] = image_orientation_y[1] * pixel_spacing[0]
affine_matrix[1,1] = image_orientation_x[1] * pixel_spacing[1]
affine_matrix[1,3] = T_1[1]
affine_matrix[2,0] = image_orientation_y[2] * pixel_spacing[0]
affine_matrix[2,1] = image_orientation_x[2] * pixel_spacing[1]
affine_matrix[2,3] = T_1[2]
affine_matrix[3,3] = 1
k1 = (T_1[0] - T_n[0])/ (1 - num_slices)
k2 = (T_1[1] - T_n[1])/ (1 - num_slices)
k3 = (T_1[2] - T_n[2])/ (1 - num_slices)
affine_matrix[:3, 2] = np.array([k1,k2,k3])
for z in range(num_slices):
for r in range(rows):
for c in range(cols):
vector = np.array([r, c, 0, 1]).reshape((4,1))
result = np.matmul(affine_matrix, vector)
result = np.delete(result, 3, axis=0)
result = np.transpose(result)
world_coordinates[r,c,z] = result
# print "Finished slice ", str(z)
# np.save('./data/saved/world_coordinates_3d.npy', str(world_coordinates))
return world_coordinates
Now I'm at the point where I want to write this function:
def create_lh_histogram(patient_positions, dcm, magnitude, azimuthal, elevation):
print "constructing LH histogram"
# Get 2nd derivative
second_derivative = gaussian_filter(magnitude, sigma=1, order=1)
# Determine if voxels lie on boundary or not (thresholding)
# Still have to code out: let's say the thresholded voxels are in
# a numpy array called voxels
#Iterate through all thresholded voxels and integrate gradient field in
# both directions using 2nd-order Runge-Kutta
vox_it = voxels.nditer(voxels, flags=['multi_index'])
while not vox_it.finished:
# ???
Can anyone provide me a sample code or some sort of example of Kalman filter implementation in python 2.7 and openCV 2.4.13
I want to implement it in a video to track a person but, I don't have any reference to learn and I couldn't find any python examples.
I know Kalman Filter exists in openCV as cv2.KalmanFilter but I have no idea how to use it. Any guidance would be appreciated
The kalman.py code below is the example included in OpenCV 3.2 source in github. It should be easy to change the syntax back to 2.4 if needed.
#!/usr/bin/env python
"""
Tracking of rotating point.
Rotation speed is constant.
Both state and measurements vectors are 1D (a point angle),
Measurement is the real point angle + gaussian noise.
The real and the estimated points are connected with yellow line segment,
the real and the measured points are connected with red line segment.
(if Kalman filter works correctly,
the yellow segment should be shorter than the red one).
Pressing any key (except ESC) will reset the tracking with a different speed.
Pressing ESC will stop the program.
"""
# Python 2/3 compatibility
import sys
PY3 = sys.version_info[0] == 3
if PY3:
long = int
import cv2
from math import cos, sin, sqrt
import numpy as np
if __name__ == "__main__":
img_height = 500
img_width = 500
kalman = cv2.KalmanFilter(2, 1, 0)
code = long(-1)
cv2.namedWindow("Kalman")
while True:
state = 0.1 * np.random.randn(2, 1)
kalman.transitionMatrix = np.array([[1., 1.], [0., 1.]])
kalman.measurementMatrix = 1. * np.ones((1, 2))
kalman.processNoiseCov = 1e-5 * np.eye(2)
kalman.measurementNoiseCov = 1e-1 * np.ones((1, 1))
kalman.errorCovPost = 1. * np.ones((2, 2))
kalman.statePost = 0.1 * np.random.randn(2, 1)
while True:
def calc_point(angle):
return (np.around(img_width/2 + img_width/3*cos(angle), 0).astype(int),
np.around(img_height/2 - img_width/3*sin(angle), 1).astype(int))
state_angle = state[0, 0]
state_pt = calc_point(state_angle)
prediction = kalman.predict()
predict_angle = prediction[0, 0]
predict_pt = calc_point(predict_angle)
measurement = kalman.measurementNoiseCov * np.random.randn(1, 1)
# generate measurement
measurement = np.dot(kalman.measurementMatrix, state) + measurement
measurement_angle = measurement[0, 0]
measurement_pt = calc_point(measurement_angle)
# plot points
def draw_cross(center, color, d):
cv2.line(img,
(center[0] - d, center[1] - d), (center[0] + d, center[1] + d),
color, 1, cv2.LINE_AA, 0)
cv2.line(img,
(center[0] + d, center[1] - d), (center[0] - d, center[1] + d),
color, 1, cv2.LINE_AA, 0)
img = np.zeros((img_height, img_width, 3), np.uint8)
draw_cross(np.int32(state_pt), (255, 255, 255), 3)
draw_cross(np.int32(measurement_pt), (0, 0, 255), 3)
draw_cross(np.int32(predict_pt), (0, 255, 0), 3)
cv2.line(img, state_pt, measurement_pt, (0, 0, 255), 3, cv2.LINE_AA, 0)
cv2.line(img, state_pt, predict_pt, (0, 255, 255), 3, cv2.LINE_AA, 0)
kalman.correct(measurement)
process_noise = sqrt(kalman.processNoiseCov[0,0]) * np.random.randn(2, 1)
state = np.dot(kalman.transitionMatrix, state) + process_noise
cv2.imshow("Kalman", img)
code = cv2.waitKey(100)
if code != -1:
break
if code in [27, ord('q'), ord('Q')]:
break
cv2.destroyWindow("Kalman")
Here is the OpenCV 2.4 Doc on Kalman Filter. Hope this help.
I know you specifically mentioned that you needs "Python 2.7" code. Still, if anyone need, I provide some information about that.
A video from my channel on Multi-target tracking: https://www.youtube.com/watch?v=bkn6M4LAoHk
The basics that you should know about Kalman Filtering and Multiple-Human Tracking:
Camera as a sensor: You need a proper detector (YOLO etc.) that provides you frame-by-frame bounding box.
Tracking the bounding box:
The track handling is done by the Kalman filtering framework. The eight-dimensional state space that contains the bounding box center position, aspect ratio, height, and their respective velocities in image coordinates. A standard Kalman filter is used with constant velocity motion and linear observation model, where bounding coordinates are taken as direct observations of the object state.
Frame-to-Frame association: What if there are three people in scene? Since detectors does not provide any identification on bounding boxes, you need to match current frame's bounding boxes to previous bounding boxes. I suggest you to search "Gating" and "Data Association" keywords on that.
class KalmanFilter(object):
"""
A simple Kalman filter for tracking bounding boxes in image space.
The 8-dimensional state space
x, y, a, h, vx, vy, va, vh
contains the bounding box center position (x, y), aspect ratio a, height h,
and their respective velocities.
Object motion follows a constant velocity model. The bounding box location
(x, y, a, h) is taken as direct observation of the state space (linear
observation model).
"""
def __init__(self):
ndim, dt = 4, 1.
# Create Kalman filter model matrices.
self._motion_mat = np.eye(2 * ndim, 2 * ndim)
for i in range(ndim):
self._motion_mat[i, ndim + i] = dt
self._update_mat = np.eye(ndim, 2 * ndim)
# Motion and observation uncertainty are chosen relative to the current
# state estimate. These weights control the amount of uncertainty in
# the model. This is a bit hacky.
self._std_weight_position = 1. / 20
self._std_weight_velocity = 1. / 160
def initiate(self, measurement):
"""Create track from unassociated measurement.
Parameters
----------
measurement : ndarray
Bounding box coordinates (x, y, a, h) with center position (x, y),
aspect ratio a, and height h.
Returns
-------
(ndarray, ndarray)
Returns the mean vector (8 dimensional) and covariance matrix (8x8
dimensional) of the new track. Unobserved velocities are initialized
to 0 mean.
"""
mean_pos = measurement
mean_vel = np.zeros_like(mean_pos)
mean = np.r_[mean_pos, mean_vel]
std = [
2 * self._std_weight_position * measurement[3],
2 * self._std_weight_position * measurement[3],
1e-2,
2 * self._std_weight_position * measurement[3],
10 * self._std_weight_velocity * measurement[3],
10 * self._std_weight_velocity * measurement[3],
1e-5,
10 * self._std_weight_velocity * measurement[3]]
covariance = np.diag(np.square(std))
return mean, covariance
def predict(self, mean, covariance):
"""Run Kalman filter prediction step.
Parameters
----------
mean : ndarray
The 8 dimensional mean vector of the object state at the previous
time step.
covariance : ndarray
The 8x8 dimensional covariance matrix of the object state at the
previous time step.
Returns
-------
(ndarray, ndarray)
Returns the mean vector and covariance matrix of the predicted
state. Unobserved velocities are initialized to 0 mean.
"""
std_pos = [
self._std_weight_position * mean[3],
self._std_weight_position * mean[3],
1e-2,
self._std_weight_position * mean[3]]
std_vel = [
self._std_weight_velocity * mean[3],
self._std_weight_velocity * mean[3],
1e-5,
self._std_weight_velocity * mean[3]]
motion_cov = np.diag(np.square(np.r_[std_pos, std_vel]))
mean = np.dot(self._motion_mat, mean)
covariance = np.linalg.multi_dot((
self._motion_mat, covariance, self._motion_mat.T)) + motion_cov
return mean, covariance
def project(self, mean, covariance):
"""Project state distribution to measurement space.
Parameters
----------
mean : ndarray
The state's mean vector (8 dimensional array).
covariance : ndarray
The state's covariance matrix (8x8 dimensional).
Returns
-------
(ndarray, ndarray)
Returns the projected mean and covariance matrix of the given state
estimate.
"""
std = [
self._std_weight_position * mean[3],
self._std_weight_position * mean[3],
1e-1,
self._std_weight_position * mean[3]]
innovation_cov = np.diag(np.square(std))
mean = np.dot(self._update_mat, mean)
covariance = np.linalg.multi_dot((
self._update_mat, covariance, self._update_mat.T))
return mean, covariance + innovation_cov
def update(self, mean, covariance, measurement):
"""Run Kalman filter correction step.
Parameters
----------
mean : ndarray
The predicted state's mean vector (8 dimensional).
covariance : ndarray
The state's covariance matrix (8x8 dimensional).
measurement : ndarray
The 4 dimensional measurement vector (x, y, a, h), where (x, y)
is the center position, a the aspect ratio, and h the height of the
bounding box.
Returns
-------
(ndarray, ndarray)
Returns the measurement-corrected state distribution.
"""
projected_mean, projected_cov = self.project(mean, covariance)
chol_factor, lower = scipy.linalg.cho_factor(
projected_cov, lower=True, check_finite=False)
kalman_gain = scipy.linalg.cho_solve(
(chol_factor, lower), np.dot(covariance, self._update_mat.T).T,
check_finite=False).T
innovation = measurement - projected_mean
new_mean = mean + np.dot(innovation, kalman_gain.T)
new_covariance = covariance - np.linalg.multi_dot((
kalman_gain, projected_cov, kalman_gain.T))
return new_mean, new_covariance
def gating_distance(self, mean, covariance, measurements,
only_position=False):
"""Compute gating distance between state distribution and measurements.
A suitable distance threshold can be obtained from `chi2inv95`. If
`only_position` is False, the chi-square distribution has 4 degrees of
freedom, otherwise 2.
Parameters
----------
mean : ndarray
Mean vector over the state distribution (8 dimensional).
covariance : ndarray
Covariance of the state distribution (8x8 dimensional).
measurements : ndarray
An Nx4 dimensional matrix of N measurements, each in
format (x, y, a, h) where (x, y) is the bounding box center
position, a the aspect ratio, and h the height.
only_position : Optional[bool]
If True, distance computation is done with respect to the bounding
box center position only.
Returns
-------
ndarray
Returns an array of length N, where the i-th element contains the
squared Mahalanobis distance between (mean, covariance) and
`measurements[i]`.
"""
mean, covariance = self.project(mean, covariance)
if only_position:
mean, covariance = mean[:2], covariance[:2, :2]
measurements = measurements[:, :2]
cholesky_factor = np.linalg.cholesky(covariance)
d = measurements - mean
z = scipy.linalg.solve_triangular(
cholesky_factor, d.T, lower=True, check_finite=False,
overwrite_b=True)
squared_maha = np.sum(z * z, axis=0)
return squared_maha
And this is a basic multi-target tracker.
class Tracker:
"""
This is the multi-target tracker.
Parameters
----------
metric : nn_matching.NearestNeighborDistanceMetric
A distance metric for measurement-to-track association.
max_age : int
Maximum number of missed misses before a track is deleted.
n_init : int
Number of consecutive detections before the track is confirmed. The
track state is set to `Deleted` if a miss occurs within the first
`n_init` frames.
Attributes
----------
metric : nn_matching.NearestNeighborDistanceMetric
The distance metric used for measurement to track association.
max_age : int
Maximum number of missed misses before a track is deleted.
n_init : int
Number of frames that a track remains in initialization phase.
kf : kalman_filter.KalmanFilter
A Kalman filter to filter target trajectories in image space.
tracks : List[Track]
The list of active tracks at the current time step.
"""
def __init__(self, metric, max_iou_distance=0.7, max_age=30, n_init=3):
self.metric = metric
self.max_iou_distance = max_iou_distance
self.max_age = max_age
self.n_init = n_init
self.kf = kalman_filter.KalmanFilter()
self.tracks = []
self._next_id = 1
def predict(self):
"""Propagate track state distributions one time step forward.
This function should be called once every time step, before `update`.
"""
for track in self.tracks:
track.predict(self.kf)
def update(self, detections):
"""Perform measurement update and track management.
Parameters
----------
detections : List[deep_sort.detection.Detection]
A list of detections at the current time step.
"""
# Run matching cascade.
matches, unmatched_tracks, unmatched_detections = \
self._match(detections)
# Update track set.
for track_idx, detection_idx in matches:
self.tracks[track_idx].update(
self.kf, detections[detection_idx])
for track_idx in unmatched_tracks:
self.tracks[track_idx].mark_missed()
for detection_idx in unmatched_detections:
self._initiate_track(detections[detection_idx])
self.tracks = [t for t in self.tracks if not t.is_deleted()]
# Update distance metric.
active_targets = [t.track_id for t in self.tracks if t.is_confirmed()]
features, targets = [], []
for track in self.tracks:
if not track.is_confirmed():
continue
features += track.features
targets += [track.track_id for _ in track.features]
track.features = []
self.metric.partial_fit(
np.asarray(features), np.asarray(targets), active_targets)
def _match(self, detections):
def gated_metric(tracks, dets, track_indices, detection_indices):
features = np.array([dets[i].feature for i in detection_indices])
targets = np.array([tracks[i].track_id for i in track_indices])
cost_matrix = self.metric.distance(features, targets)
cost_matrix = linear_assignment.gate_cost_matrix(
self.kf, cost_matrix, tracks, dets, track_indices,
detection_indices)
return cost_matrix
# Split track set into confirmed and unconfirmed tracks.
confirmed_tracks = [
i for i, t in enumerate(self.tracks) if t.is_confirmed()]
unconfirmed_tracks = [
i for i, t in enumerate(self.tracks) if not t.is_confirmed()]
# Associate confirmed tracks using appearance features.
matches_a, unmatched_tracks_a, unmatched_detections = \
linear_assignment.matching_cascade(
gated_metric, self.metric.matching_threshold, self.max_age,
self.tracks, detections, confirmed_tracks)
# Associate remaining tracks together with unconfirmed tracks using IOU.
iou_track_candidates = unconfirmed_tracks + [
k for k in unmatched_tracks_a if
self.tracks[k].time_since_update == 1]
unmatched_tracks_a = [
k for k in unmatched_tracks_a if
self.tracks[k].time_since_update != 1]
matches_b, unmatched_tracks_b, unmatched_detections = \
linear_assignment.min_cost_matching(
iou_matching.iou_cost, self.max_iou_distance, self.tracks,
detections, iou_track_candidates, unmatched_detections)
matches = matches_a + matches_b
unmatched_tracks = list(set(unmatched_tracks_a + unmatched_tracks_b))
return matches, unmatched_tracks, unmatched_detections
def _initiate_track(self, detection):
mean, covariance = self.kf.initiate(detection.to_xyah())
self.tracks.append(Track(
mean, covariance, self._next_id, self.n_init, self.max_age,
detection.feature))
self._next_id += 1
This is more a question on theory of Gaussian filters, than specific coding question.
I've got an implementation of a 2D D.O.G. filter in python. I want to make noise masks at different spatial frequency bands e.g. 1-5 cpd. To do this I first create a white noise array and then I will add the DOG filters to bandpass filter the noise across different spatial ranges.
Is there a way to explicitly define the bandwidth of a Difference of Gaussian filter from the parameters of each contributing Gaussian filter?
(BONUS Q's: Would it be possible to take a Fourier transform of each of these Gaussians and then view this as a spectrum of their individual bandwidths, and then DOG bandwidth? What would the units be in the Fourier space? How could I convert this into a spatial frequency scale? Sorry lots of questions)
Many thanks,
NOTE: I use the conv2 function, rather than inbuilt python 2d convolutions, for speed (other applications).
import numpy as np
import math
import matplotlib.pylab as plt
from scipy.ndimage.filters import convolve
def Gaussian2D(GCenter, Gamp, Ggamma,Gconst): #new_theta > 0.4:
"""
Produces a 2D Gaussian pulse *EDITED BY WMBM
Parameters
----------
GCenter : int
Centre point of Gaussian pulse
Gamp : int
Amplitude of Gaussian pulse
Ggamma : int
FWHM of Gaussian pulse
Gconst : float
Unkown parameter of density function
Returns
----------
GKernel : array_like
Gaussian kernel
"""
new_theta = math.sqrt(Gconst**-1)*Ggamma
SizeHalf = np.int(math.floor(9*new_theta))
[y, x] = np.meshgrid(np.arange(-SizeHalf,SizeHalf+1), np.arange(-SizeHalf,SizeHalf+1))
part1=(x-GCenter[0])**2+(y-GCenter[1])**2
GKernel = Gamp*np.exp(-0.5*Ggamma**-2*Gconst*part1)
return GKernel
def conv2(x,y,mode='same'):
"""
Emulate the Matlab function conv2 from Mathworks.
Usage:
z = conv2(x,y,mode='same')
"""
if not(mode == 'same'):
raise Exception("Mode not supported")
# Add singleton dimensions
if (len(x.shape) < len(y.shape)):
dim = x.shape
for i in range(len(x.shape),len(y.shape)):
dim = (1,) + dim
x = x.reshape(dim)
elif (len(y.shape) < len(x.shape)):
dim = y.shape
for i in range(len(y.shape),len(x.shape)):
dim = (1,) + dim
y = y.reshape(dim)
origin = ()
# Apparently, the origin must be set in a special way to reproduce
# the results of scipy.signal.convolve and Matlab
for i in range(len(x.shape)):
if ( (x.shape[i] - y.shape[i]) % 2 == 0 and
x.shape[i] > 1 and
y.shape[i] > 1):
origin = origin + (-1,)
else:
origin = origin + (0,)
z = convolve(x,y, mode='constant', origin=origin)
return z
# Create white noise array
N=50 # Noise array dimension
A=10 # Noise amplitude
noise = np.random.rand(N,N)*A
# Gaussian Noise paramerers
GCenter=[0,0]
Gconst=1
# First gaussian filter
cutoff_f1 = 0.05 # < pi/10
gamma1 = 1/(2*np.pi*cutoff_f1) #minimum gamma == 0.5
Gamp1 = 1/(2*np.pi*gamma1)
filtr1 = Gaussian2D([0,0],Gamp1,gamma1,Gconst)
# Second gaussian filter
cutoff_f2 = 0.04 # < pi/10
gamma2 = 1/(2*np.pi*cutoff_f2) #minimum gamma == 0.5
Gamp2 = 1/(2*np.pi*gamma2)
filtr2 = Gaussian2D([0,0],Gamp2,gamma2,Gconst)
# Convolve filters with noise
noise_filtr1 = conv2(noise, filtr1, mode='same')
noise_filtr2 = conv2(noise, filtr2, mode='same')
# Difference of Gaussian Output
noise_out = noise_filtr1- noise_filtr2