# for image in proj.image_list:
# if image.sum_count > 0:
# image.z_avg = image.sum_values / float(image.sum_count)
# print(image.name, 'avg elev:', image.z_avg)
# else:
# image.z_avg = 0
# compute the uv grid for each image and project each point out into
# ned space, then intersect each vector with the srtm / ground /
# delauney surface.
name_list = []
for image in proj.image_list:
name_list.append(image.name)
#print(image.name, image.z_avg)
width, height = camera.get_image_params()
# scale the K matrix if we have scaled the images
K = camera.get_K(optimized=True)
IK = np.linalg.inv(K)
grid_list = []
u_list = np.linspace(0, width, ac3d_steps + 1)
v_list = np.linspace(0, height, ac3d_steps + 1)
#print "u_list:", u_list
#print "v_list:", v_list
for v in v_list:
for u in u_list:
grid_list.append([u, v])
#print 'grid_list:', grid_list
image.distorted_uv = proj.redistort(grid_list, optimized=True)
i1 = proj.image_list[i]
i2 = proj.image_list[j]
# print(i1.match_list)
num_matches = len(i1.match_list[i2.name])
print("dist: %.1f" % dist, "yaw: %.1f" % yaw_diff, i1.name, i2.name,
num_matches)
print("rev matches:", len(i2.match_list[i1.name]))
if num_matches >= 25:
continue
if not len(i1.kp_list) or not len(i1.des_list):
i1.detect_features(args.scale)
if not len(i2.kp_list) or not len(i2.des_list):
i2.detect_features(args.scale)
w, h = camera.get_image_params()
diag = int(math.sqrt(h * h + w * w))
print("h:", h, "w:", w)
print("scaled diag:", diag)
rgb1 = i1.load_rgb()
rgb2 = i2.load_rgb()
FLANN_INDEX_KDTREE = 1
flann_params = {'algorithm': FLANN_INDEX_KDTREE, 'trees': 5}
search_params = dict(checks=100)
matcher = cv2.FlannBasedMatcher(flann_params, search_params)
matches = matcher.knnMatch(i1.des_list, i2.des_list, k=2)
print("Raw matches:", len(matches))
# numpy rotation matrix