Loading autocnet/matcher/mutual_information.py +0 −83 Original line number Diff line number Diff line Loading @@ -52,86 +52,3 @@ def mutual_information(reference_arr, moving_arr, **kwargs): nzs = pxy > 0 # Only non-zero pxy values contribute to the sum return np.sum(pxy[nzs] * np.log(pxy[nzs] / px_py[nzs])) def mutual_information_match(moving_roi, reference_roi, affine=tf.AffineTransform(), subpixel_size=3, func=None, **kwargs): """ Applies the mutual information matcher function over a search image using a defined template Parameters ---------- moving_roi : roi The input search template used to 'query' the destination image reference_roi : roi The image or sub-image to be searched subpixel_size : int Subpixel area size to search for the center of mass calculation func : function Function object to be used to compute the histogram comparison Returns ------- new_affine :AffineTransform The affine transformation max_corr : float The strength of the correlation in the range [0, 4]. corr_map : ndarray Map of corrilation coefficients when comparing the template to locations within the search area """ reference_template = reference_roi.clip() moving_image = moving_roi.clip(affine) if func == None: func = mutual_information image_size = moving_image.shape template_size = reference_template.shape y_diff = image_size[0] - template_size[0] x_diff = image_size[1] - template_size[1] max_corr = -np.inf corr_map = np.zeros((y_diff+1, x_diff+1)) for i in range(y_diff+1): for j in range(x_diff+1): sub_image = moving_image[i:i+template_size[1], # y j:j+template_size[0]] # x corr = func(sub_image, reference_template, **kwargs) if corr > max_corr: max_corr = corr corr_map[i, j] = corr y, x = np.unravel_index(np.argmax(corr_map, axis=None), corr_map.shape) upper = int(2 + floor(subpixel_size / 2)) lower = upper - 1 area = corr_map[y-lower:y+upper, x-lower:x+upper] # Compute the y, x shift (subpixel) using scipys center_of_mass function cmass = center_of_mass(area) if area.shape != (subpixel_size + 2, subpixel_size + 2): return None, 0, None subpixel_y_shift = subpixel_size - 1 - cmass[0] subpixel_x_shift = subpixel_size - 1 - cmass[1] y = abs(y - (corr_map.shape[1])/2) x = abs(x - (corr_map.shape[0])/2) y += subpixel_y_shift x += subpixel_x_shift new_affine = AffineTransform(translation=(-x, -y)) return new_affine, np.max(max_corr), corr_map No newline at end of file autocnet/matcher/subpixel.py +85 −1 Original line number Diff line number Diff line Loading @@ -28,7 +28,7 @@ import PIL from PIL import Image from autocnet.matcher.naive_template import pattern_match from autocnet.matcher.mutual_information import mutual_information_match from autocnet.matcher.mutual_information import mutual_information from autocnet.spatial import isis from autocnet.io.db.model import Measures, Points, Images, JsonEncoder from autocnet.graph.node import NetworkNode Loading Loading @@ -1400,3 +1400,87 @@ def smart_register_point(pointid, parameters=[], shared_kwargs={}, valid_reproje log.info(f'Ignoring measures: {measures_to_set_false}') return measures_to_update, measures_to_set_false def mutual_information_match(moving_roi, reference_roi, affine=tf.AffineTransform(), subpixel_size=3, func=None, **kwargs): """ Applies the mutual information matcher function over a search image using a defined template Parameters ---------- moving_roi : roi The input search template used to 'query' the destination image reference_roi : roi The image or sub-image to be searched subpixel_size : int Subpixel area size to search for the center of mass calculation func : function Function object to be used to compute the histogram comparison Returns ------- new_affine :AffineTransform The affine transformation max_corr : float The strength of the correlation in the range [0, 4]. corr_map : ndarray Map of corrilation coefficients when comparing the template to locations within the search area """ reference_template = reference_roi.clip() moving_image = moving_roi.clip(affine) if func == None: func = mutual_information image_size = moving_image.shape template_size = reference_template.shape y_diff = image_size[0] - template_size[0] x_diff = image_size[1] - template_size[1] max_corr = -np.inf corr_map = np.zeros((y_diff+1, x_diff+1)) for i in range(y_diff+1): for j in range(x_diff+1): sub_image = moving_image[i:i+template_size[1], # y j:j+template_size[0]] # x corr = func(sub_image, reference_template, **kwargs) if corr > max_corr: max_corr = corr corr_map[i, j] = corr y, x = np.unravel_index(np.argmax(corr_map, axis=None), corr_map.shape) upper = int(2 + floor(subpixel_size / 2)) lower = upper - 1 area = corr_map[y-lower:y+upper, x-lower:x+upper] # Compute the y, x shift (subpixel) using scipys center_of_mass function cmass = center_of_mass(area) if area.shape != (subpixel_size + 2, subpixel_size + 2): return None, 0, None subpixel_y_shift = subpixel_size - 1 - cmass[0] subpixel_x_shift = subpixel_size - 1 - cmass[1] y = abs(y - (corr_map.shape[1])/2) x = abs(x - (corr_map.shape[0])/2) y += subpixel_y_shift x += subpixel_x_shift new_affine = AffineTransform(translation=(-x, -y)) return new_affine, np.max(max_corr), corr_map No newline at end of file autocnet/matcher/tests/test_mutual_information.py +0 −12 Original line number Diff line number Diff line Loading @@ -20,15 +20,3 @@ def test_bad_mi(): corrilation = mutual_information.mutual_information(test_image1, test_image2) assert corrilation == pytest.approx(0) def test_mutual_information(): d_template = np.array([[i for i in range(50, 100)] for j in range(50)]) s_image = np.ones((100, 100)) s_image[25:75, 25:75] = d_template x_offset, y_offset, max_corr, corr_map = mutual_information.mutual_information_match(d_template, s_image, bins=20) assert x_offset == 0.01711861257171421 assert y_offset == 0.0 assert max_corr == 2.9755967600033015 assert corr_map.shape == (51, 51) assert np.min(corr_map) >= 0.0 autocnet/matcher/tests/test_subpixel.py +12 −0 Original line number Diff line number Diff line Loading @@ -267,3 +267,15 @@ def test_subpixel_phase_cooked(x, y, x1, y1, image_size, expected): assert dy == expected[1] def test_mutual_information(): d_template = np.array([[i for i in range(50, 100)] for j in range(50)]) s_image = np.ones((100, 100)) s_image[25:75, 25:75] = d_template x_offset, y_offset, max_corr, corr_map = sp.mutual_information_match(d_template, s_image, bins=20) assert x_offset == 0.01711861257171421 assert y_offset == 0.0 assert max_corr == 2.9755967600033015 assert corr_map.shape == (51, 51) assert np.min(corr_map) >= 0.0 Loading
autocnet/matcher/mutual_information.py +0 −83 Original line number Diff line number Diff line Loading @@ -52,86 +52,3 @@ def mutual_information(reference_arr, moving_arr, **kwargs): nzs = pxy > 0 # Only non-zero pxy values contribute to the sum return np.sum(pxy[nzs] * np.log(pxy[nzs] / px_py[nzs])) def mutual_information_match(moving_roi, reference_roi, affine=tf.AffineTransform(), subpixel_size=3, func=None, **kwargs): """ Applies the mutual information matcher function over a search image using a defined template Parameters ---------- moving_roi : roi The input search template used to 'query' the destination image reference_roi : roi The image or sub-image to be searched subpixel_size : int Subpixel area size to search for the center of mass calculation func : function Function object to be used to compute the histogram comparison Returns ------- new_affine :AffineTransform The affine transformation max_corr : float The strength of the correlation in the range [0, 4]. corr_map : ndarray Map of corrilation coefficients when comparing the template to locations within the search area """ reference_template = reference_roi.clip() moving_image = moving_roi.clip(affine) if func == None: func = mutual_information image_size = moving_image.shape template_size = reference_template.shape y_diff = image_size[0] - template_size[0] x_diff = image_size[1] - template_size[1] max_corr = -np.inf corr_map = np.zeros((y_diff+1, x_diff+1)) for i in range(y_diff+1): for j in range(x_diff+1): sub_image = moving_image[i:i+template_size[1], # y j:j+template_size[0]] # x corr = func(sub_image, reference_template, **kwargs) if corr > max_corr: max_corr = corr corr_map[i, j] = corr y, x = np.unravel_index(np.argmax(corr_map, axis=None), corr_map.shape) upper = int(2 + floor(subpixel_size / 2)) lower = upper - 1 area = corr_map[y-lower:y+upper, x-lower:x+upper] # Compute the y, x shift (subpixel) using scipys center_of_mass function cmass = center_of_mass(area) if area.shape != (subpixel_size + 2, subpixel_size + 2): return None, 0, None subpixel_y_shift = subpixel_size - 1 - cmass[0] subpixel_x_shift = subpixel_size - 1 - cmass[1] y = abs(y - (corr_map.shape[1])/2) x = abs(x - (corr_map.shape[0])/2) y += subpixel_y_shift x += subpixel_x_shift new_affine = AffineTransform(translation=(-x, -y)) return new_affine, np.max(max_corr), corr_map No newline at end of file
autocnet/matcher/subpixel.py +85 −1 Original line number Diff line number Diff line Loading @@ -28,7 +28,7 @@ import PIL from PIL import Image from autocnet.matcher.naive_template import pattern_match from autocnet.matcher.mutual_information import mutual_information_match from autocnet.matcher.mutual_information import mutual_information from autocnet.spatial import isis from autocnet.io.db.model import Measures, Points, Images, JsonEncoder from autocnet.graph.node import NetworkNode Loading Loading @@ -1400,3 +1400,87 @@ def smart_register_point(pointid, parameters=[], shared_kwargs={}, valid_reproje log.info(f'Ignoring measures: {measures_to_set_false}') return measures_to_update, measures_to_set_false def mutual_information_match(moving_roi, reference_roi, affine=tf.AffineTransform(), subpixel_size=3, func=None, **kwargs): """ Applies the mutual information matcher function over a search image using a defined template Parameters ---------- moving_roi : roi The input search template used to 'query' the destination image reference_roi : roi The image or sub-image to be searched subpixel_size : int Subpixel area size to search for the center of mass calculation func : function Function object to be used to compute the histogram comparison Returns ------- new_affine :AffineTransform The affine transformation max_corr : float The strength of the correlation in the range [0, 4]. corr_map : ndarray Map of corrilation coefficients when comparing the template to locations within the search area """ reference_template = reference_roi.clip() moving_image = moving_roi.clip(affine) if func == None: func = mutual_information image_size = moving_image.shape template_size = reference_template.shape y_diff = image_size[0] - template_size[0] x_diff = image_size[1] - template_size[1] max_corr = -np.inf corr_map = np.zeros((y_diff+1, x_diff+1)) for i in range(y_diff+1): for j in range(x_diff+1): sub_image = moving_image[i:i+template_size[1], # y j:j+template_size[0]] # x corr = func(sub_image, reference_template, **kwargs) if corr > max_corr: max_corr = corr corr_map[i, j] = corr y, x = np.unravel_index(np.argmax(corr_map, axis=None), corr_map.shape) upper = int(2 + floor(subpixel_size / 2)) lower = upper - 1 area = corr_map[y-lower:y+upper, x-lower:x+upper] # Compute the y, x shift (subpixel) using scipys center_of_mass function cmass = center_of_mass(area) if area.shape != (subpixel_size + 2, subpixel_size + 2): return None, 0, None subpixel_y_shift = subpixel_size - 1 - cmass[0] subpixel_x_shift = subpixel_size - 1 - cmass[1] y = abs(y - (corr_map.shape[1])/2) x = abs(x - (corr_map.shape[0])/2) y += subpixel_y_shift x += subpixel_x_shift new_affine = AffineTransform(translation=(-x, -y)) return new_affine, np.max(max_corr), corr_map No newline at end of file
autocnet/matcher/tests/test_mutual_information.py +0 −12 Original line number Diff line number Diff line Loading @@ -20,15 +20,3 @@ def test_bad_mi(): corrilation = mutual_information.mutual_information(test_image1, test_image2) assert corrilation == pytest.approx(0) def test_mutual_information(): d_template = np.array([[i for i in range(50, 100)] for j in range(50)]) s_image = np.ones((100, 100)) s_image[25:75, 25:75] = d_template x_offset, y_offset, max_corr, corr_map = mutual_information.mutual_information_match(d_template, s_image, bins=20) assert x_offset == 0.01711861257171421 assert y_offset == 0.0 assert max_corr == 2.9755967600033015 assert corr_map.shape == (51, 51) assert np.min(corr_map) >= 0.0
autocnet/matcher/tests/test_subpixel.py +12 −0 Original line number Diff line number Diff line Loading @@ -267,3 +267,15 @@ def test_subpixel_phase_cooked(x, y, x1, y1, image_size, expected): assert dy == expected[1] def test_mutual_information(): d_template = np.array([[i for i in range(50, 100)] for j in range(50)]) s_image = np.ones((100, 100)) s_image[25:75, 25:75] = d_template x_offset, y_offset, max_corr, corr_map = sp.mutual_information_match(d_template, s_image, bins=20) assert x_offset == 0.01711861257171421 assert y_offset == 0.0 assert max_corr == 2.9755967600033015 assert corr_map.shape == (51, 51) assert np.min(corr_map) >= 0.0
