def transform_folder_to_world(sub_dir):
base_dir = "E:\Datasets\DataHack\Train"
base_res_dir = "E:\Datasets\DataHack\World\Train"
print('Working on sub_dir: {}'.format(sub_dir))
for idx in data_utils.enumerate_frames(os.path.join(base_dir, sub_dir)):
pc_file = os.path.join(
base_res_dir,
data_utils.frame_to_filename(sub_dir, idx, 'pointcloud'))
if os.path.exists(pc_file):
continue
pc, ego, label = data_utils.read_all_data(
os.path.join(base_dir, sub_dir), idx)
ego_pc = transform_frame_to_world(pc, ego)
ego_pc = np.concatenate((ego_pc, pc[:, 3:4]), -1)
df = (pd.DataFrame(ego_pc) * 100).astype(int)
res_dir = os.path.join(base_res_dir, sub_dir)
if not os.path.exists(res_dir):
os.makedirs(res_dir)
file_name = os.path.join(res_dir, str(idx).zfill(7))
df.to_csv(file_name + '_pointcloud.csv', header=None, index=False)
pd.DataFrame([0] * df.shape[0]).to_csv(file_name + '_labels.csv',
header=None,
index=False)
pd.DataFrame([0.] * 6).T.to_csv(file_name + '_egomotion.csv',
header=None,
index=False)
#elMin = 9999
#azMin = 9999
#elMax = -9999
#azMax = -9999
# agg_point_cloud_list=[]
prev_img=np.zeros((EL_NUM,AZ_NUM)) # init
imgSum = np.zeros((EL_NUM,AZ_NUM))
prev_img_list=[]
idxXY_list = []
label_list = []
fn_list = []
cloud_len_list=[]
for idx, frame in enumerate(data_utils.enumerate_frames(video_dir)):
if idx < min_idx or idx % decimate != 0:
continue
pc, ego, label,label_pred_new,fn = data_utils.read_all_data(video_dir, frame)
# label=label_pred_new
ego_rt = RotationTranslationData(vecs=(ego[:3], ego[3:]))
ego_pc = ego_rt.apply_transform(pc[:, :3])
ego_pc = np.concatenate((ego_pc, pc[:, 3:4]), -1)
# labeled_pc = np.concatenate((ego_pc, label), -1)
# agg_point_cloud_list.append(labeled_pc)
# img = np.zeros((EL_NUM,AZ_NUM))
# # img1 = np.zeros((EL_NUM,AZ_NUM))
# el = np.rad2deg(np.arctan2(pc[:,2],pc[:,0]))
# az = np.rad2deg(np.arctan2(pc[:,1],pc[:,0]))
# rng = np.sqrt(pc[:,0]**2 + pc[:,1]**2 + pc[:,2]**2)
# idxEl = np.round((elMax - el)/elRes).astype('uint32')
from visualizations.vis import pcshow
from utilities import data_utils
if __name__ == '__main__':
base_dir = os.path.dirname(os.getcwd())
video_dir = os.path.join(base_dir, 'data_examples', 'test_video')
agg_point_cloud_list = []
max_frames_to_keep = 10
min_idx = 0
decimate = 1
max_dist = 100
for idx in data_utils.enumerate_frames(video_dir):
if idx < min_idx or idx % decimate != 0:
continue
pc_file = data_utils.frame_to_filename(video_dir, idx, 'pointcloud')
pc, ego, label = data_utils.read_all_data(video_dir, idx)
ego_rt = RotationTranslationData(vecs=(ego[:3], ego[3:]))
ego_pc = ego_rt.apply_transform(pc[:, :3])
ego_pc = np.concatenate((ego_pc, pc[:, 3:4]), -1)
labeled_pc = np.concatenate((ego_pc, label), -1)
agg_point_cloud_list.append(labeled_pc)
if len(agg_point_cloud_list) > max_frames_to_keep:
agg_point_cloud_list = agg_point_cloud_list[1:]
agg_point_cloud = np.concatenate(agg_point_cloud_list, 0)
pc2disp = ego_rt.inverse().apply_transform(agg_point_cloud[:, :3])
pc2disp = np.concatenate((pc2disp, agg_point_cloud[:, 3:]), -1)
pc2disp = pc2disp[np.linalg.norm(pc2disp[:, :3], axis=1) < max_dist]
pcshow(pc2disp,
on_screen_text=pc_file,
max_points=32000 * max_frames_to_keep)
# of the BSD 3-Clause license. See the LICENSE file for details.
import os
os.chdir("D:\\DataHack2018\\from_shlomi")
import os.path as osp
from visualizations.vis import pcshow
import numpy as np
from utilities import data_utils
if __name__ == '__main__':
# base_dir = os.path.dirname(os.getcwd())
base_dir = os.getcwd()
#video_dir = os.path.join(base_dir, 'data_examples', 'test_video')
# video_dir='D:\\DataHack18\\Dataset\\Train\\vid_2'
#video_dir='D:\\DataHack18\\Dataset\\DataHack2018-master\\data_examples\\test_video'
video_dir = 'D:\\DataHack2018\\from_shlomi\\data\\Test\\vid_21'
frame_num = data_utils.count_frames(video_dir)
min_idx = 900
decimate = 1
for idx, frame in enumerate(data_utils.enumerate_frames(video_dir)):
if idx < min_idx or idx % decimate != 0:
continue
pc, ego, label, label_tmp, fn = data_utils.read_all_data(
video_dir, frame)
labeled_pc = np.concatenate((pc, label), -1)
pcshow(labeled_pc,
on_screen_text=osp.join(video_dir, str(frame)),
max_points=80000)
if idx == min_idx + 100:
break
#import pdb;pdb.set_trace()
frame_num = data_utils.count_frames(video_dir)
min_idx = 31
decimate = 1
#elMin = 9999
#azMin = 9999
#elMax = -9999
#azMax = -9999
ego_last = 0
img_last = np.zeros((EL_NUM, AZ_NUM, 3)).astype('uint8')
#fgbg = cv2.createBackgroundSubtractorMOG2()
for idx, frame in enumerate(data_utils.enumerate_frames(video_dir)):
if idx < min_idx or idx % decimate != 0:
continue
pc, ego, label, label_pred, fn = data_utils.read_all_data(
video_dir, frame, (0.0, 0.0, 0.0))
if idx == min_idx:
pc_last = pc.copy()
img_dil_new = pc2img(pc)
img_dil_old = pc2img(pc_last)
pc_last = pc.copy()
if idx == min_idx:
keyFrame = img_dil_old.copy()
if idx > 0:
imReg, h = alignImages(img_dil_new, keyFrame)
rows, cols, ch = img_dil_new.shape
imReg = cv2.warpPerspective(img_dil_new, h, (cols, rows))
print(h, ego)
imgDiff = (
