videos_to_colmap.py 24.4 KB
Newer Older
Clement Pinard's avatar
Clement Pinard committed
1
2
3
4
5
6
from colmap_util import read_model as rm, database as db
import anafi_metadata as am
from wrappers import FFMpeg, PDraw
from sklearn.cluster import KMeans
from sklearn.metrics import pairwise_distances_argmin_min
from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
nicolas's avatar
nicolas committed
7
from edit_exif import set_gps_location
Clement Pinard's avatar
Clement Pinard committed
8
9
10
11
12
from path import Path
import pandas as pd
import numpy as np
from pyproj import Proj
from tqdm import tqdm
13
import tempfile
Clement Pinard's avatar
Clement Pinard committed
14
15

parser = ArgumentParser(description='Take all the drone videos of a folder and put the frame '
Clément Pinard's avatar
Clément Pinard committed
16
                                    'location in a COLMAP file for visualization',
Clement Pinard's avatar
Clement Pinard committed
17
18
19
20
                        formatter_class=ArgumentDefaultsHelpFormatter)

parser.add_argument('--video_folder', metavar='DIR',
                    help='path to videos', type=Path)
Clément Pinard's avatar
Clément Pinard committed
21
22
23
24
25
26
parser.add_argument('--system', default='epsg:2154',
                    help='coordinates system used for GPS, should be the same as the LAS files used')
parser.add_argument('--centroid_path', default=None, help="path to centroid generated in las2ply.py")
parser.add_argument('--colmap_img_root', metavar='DIR', type=Path,
                    help="folder that will be used as \"image_path\" parameter when using COLMAP", required=True)
parser.add_argument('--output_format', metavar='EXT', default="bin", choices=["bin", "txt"],
Clément Pinard's avatar
Clément Pinard committed
27
                    help='format of the COLMAP file that will be outputed, used for visualization only')
Clément Pinard's avatar
Clément Pinard committed
28
29
30
31
parser.add_argument('--vid_ext', nargs='+', default=[".mp4", ".MP4"],
                    help="format of video files that will be scraped from input folder")
parser.add_argument('--pic_ext', nargs='+', default=[".jpg", ".JPG", ".png", ".PNG"],
                    help='format of images that will be scraped from already existing images in colmap image_path folder')
Clement Pinard's avatar
Clement Pinard committed
32
parser.add_argument('--nw', default='',
Clément Pinard's avatar
Clément Pinard committed
33
                    help="native-wrapper.sh file location (see Anafi SDK documentation)")
Clement Pinard's avatar
Clement Pinard committed
34
35
parser.add_argument('--fps', default=1, type=int,
                    help="framerate at which videos will be scanned WITH reconstruction")
Clément Pinard's avatar
Clément Pinard committed
36
37
38
39
40
41
42
parser.add_argument('--total_frames', default=200, type=int, help="number of frames used for thorough photogrammetry")
parser.add_argument('--max_sequence_length', default=1000, help='Number max of frames for a chunk. '
                    'This is for RAM purpose, as loading feature matches of thousands of frames can take up GBs of RAM')
parser.add_argument('--orientation_weight', default=1, type=float,
                    help="Weight applied to orientation during optimal sample. "
                    "Higher means two pictures with same location but different orientation will be considered farer apart")
parser.add_argument('--resolution_weight', default=1, type=float, help="same as orientation, but with image size")
Clément Pinard's avatar
Clément Pinard committed
43
44
parser.add_argument('--save_space', action="store_true",
                    help="if selected, will only extract from ffmpeg frames used for thorough photogrammetry")
Clément Pinard's avatar
Clément Pinard committed
45
parser.add_argument('--thorough_db', type=Path, help="output db file which will be used by COLMAP for photogrammetry")
Clément Pinard's avatar
Clément Pinard committed
46
47
48
parser.add_argument('--generic_model', default='OPENCV',
                    help='COLMAP model for generic videos. Same zoom level assumed throughout the whole video. '
                    'See https://colmap.github.io/cameras.html')
49
50
parser.add_argument('--include_lowfps_thorough', action='store_true',
                    help="if selected, will include videos frames at lowfps for thorough scan, even for generic or indoor videos")
Clément Pinard's avatar
Clément Pinard committed
51
parser.add_argument('-v', '--verbose', action="count", default=0)
Clement Pinard's avatar
Clement Pinard committed
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70


def world_coord_from_frame(frame_qvec, frame_tvec):
    '''
    frame_qvec is written in the NED system (north east down)
    frame_tvec is already is the world system (east norht up)
    '''
    world2NED = np.float32([[0, 1, 0],
                            [1, 0, 0],
                            [0, 0, -1]])
    NED2cam = np.float32([[0, 1, 0],
                          [0, 0, 1],
                          [1, 0, 0]])
    world2cam = NED2cam @ rm.qvec2rotmat(frame_qvec).T @ world2NED
    cam_tvec = - world2cam  @ frame_tvec
    cam_qvec = rm.rotmat2qvec(world2cam)
    return cam_qvec, cam_tvec


71
def set_gps(frames_list, metadata, colmap_img_root):
nicolas's avatar
nicolas committed
72
    for frame in frames_list:
73
        relative = str(frame.relpath(colmap_img_root))
nicolas's avatar
nicolas committed
74
75
76
        row = metadata[metadata["image_path"] == relative]
        if len(row) > 0:
            row = row.iloc[0]
77
            if row["location_valid"] and not row['indoor']:
78
79
80
81
                set_gps_location(frame,
                                 lat=row["location_latitude"],
                                 lng=row["location_longitude"],
                                 altitude=row["location_altitude"])
nicolas's avatar
nicolas committed
82
83
84
85
86
87


def get_georef(metadata):
    relevant_data = metadata[["location_valid", "image_path", "x", "y", "z"]]
    path_list = []
    georef_list = []
Clément Pinard's avatar
Clément Pinard committed
88
    for _, (loc_valid, path, x, y, alt) in relevant_data.iterrows():
nicolas's avatar
nicolas committed
89
        path_list.append(path)
Clément Pinard's avatar
Clément Pinard committed
90
        if loc_valid:
nicolas's avatar
nicolas committed
91
92
93
94
            georef_list.append("{} {} {} {}\n".format(path, x, y, alt))
    return georef_list, path_list


Clement Pinard's avatar
Clement Pinard committed
95
def optimal_sample(metadata, num_frames, orientation_weight, resolution_weight):
96
    # already sampled frames are discarded as we want to sample frames in addition to them
97
    valid_metadata = metadata[~metadata["sampled"]].dropna()
Clément Pinard's avatar
Clément Pinard committed
98
99
    if len(valid_metadata) == 0:
        return metadata
100
101
    XYZ = valid_metadata[["x", "y", "z"]].values
    axis_angle = valid_metadata[["frame_quat_x", "frame_quat_y", "frame_quat_z"]].values
102
    if "indoor" in valid_metadata.keys() and (True in valid_metadata["indoor"].unique()):
103
104
105
        # We have indoor videos, without absolute positions. We assume each video is very far
        # from the other ones. As such we will have an optimal subsampling of each video
        # It won't leverage video proximity from each other but it's better than nothing
Clement Pinard's avatar
Clement Pinard committed
106
        diameter = (XYZ.max(axis=0) - XYZ.min(axis=0))
107
108
109
110
        indoor_videos = valid_metadata.loc[valid_metadata["indoor"]]["video"].unique()
        new_centroids = 2 * diameter * np.linspace(0, 10, len(indoor_videos)).reshape(-1, 1)
        for centroid, v in zip(new_centroids, indoor_videos):
            video_index = (valid_metadata["video"] == v).values
Clement Pinard's avatar
Clement Pinard committed
111
112
113
114
115
116
117
            XYZ[video_index] += centroid

    weighted_point_cloud = np.concatenate([XYZ, orientation_weight * axis_angle], axis=1)

    if resolution_weight == 0:
        weights = None
    else:
118
        frame_size = valid_metadata["video_quality"].values
Clement Pinard's avatar
Clement Pinard committed
119
120
121
        weights = frame_size ** resolution_weight
    km = KMeans(n_clusters=num_frames).fit(weighted_point_cloud, sample_weight=weights)
    closest, _ = pairwise_distances_argmin_min(km.cluster_centers_, weighted_point_cloud)
122
    metadata.at[valid_metadata.index[closest], "sampled"] = True
Clement Pinard's avatar
Clement Pinard committed
123
124
125
    return metadata


126
def register_new_cameras(metadata, device, fields, database, camera_dict):
Clement Pinard's avatar
Clement Pinard committed
127
    camera_ids = []
128
    cameras_dataframe = metadata[metadata["device"] == device][["device"] + fields].drop_duplicates()
Clément Pinard's avatar
Clément Pinard committed
129
    for _, row in cameras_dataframe.iterrows():
130
        camera_model, w, h, params = row.reindex(["camera_model", "width", "height", "camera_params"])
131
132
        model_id = rm.CAMERA_MODEL_NAMES[camera_model].model_id
        num_params = rm.CAMERA_MODEL_NAMES[camera_model].num_params
133
134
135
136
137
138
139
140
141
142
143
        assert num_params >= len(params), "Got {} params for camera {}".format(len(params), camera_model)
        # Single focal models are SIMPLE_PINHOLE, SIMPLE_RADIAL, SIMPLE_RADIAL_FISHEYE, RADIAL and RADIAL_FISHEYE
        single_focal = ('SIMPLE' in camera_model) or ('RADIAL' in camera_model)
        num_focals = 1 if single_focal else 2
        params = np.array(list(params) + [0] * (num_params - len(params)))

        # prior_focal_length is whether or not COLMAP should rely on it.
        prior_focal_length = all(params[:num_focals] != 0)
        # For unknown focal_length, put a generic placeholder
        params[:num_focals][params[:num_focals] == 0] = w / 2
        # We can get less params than actual params if they are unknown. We then pad it with zeros
Clément Pinard's avatar
Clément Pinard committed
144
        db_id = database.add_camera(model_id, int(w), int(h), params, prior_focal_length=prior_focal_length)
Clement Pinard's avatar
Clement Pinard committed
145
146
        camera_ids.append(db_id)
        camera_dict[db_id] = rm.Camera(id=db_id,
147
                                       model=camera_model,
Clement Pinard's avatar
Clement Pinard committed
148
149
150
                                       width=int(w),
                                       height=int(h),
                                       params=params)
151
        metadata.loc[(metadata[["device"] + fields] == row).all(axis=1), "camera_id"] = db_id
Clement Pinard's avatar
Clement Pinard committed
152
153
154
155
    ids_series = pd.Series(camera_ids)
    return cameras_dataframe.set_index(ids_series)


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
def get_video_metadata(v, output_video_folder, system, generic_model='OPENCV', ** env):
    width, height, framerate, num_frames = env["ffmpeg"].get_size_and_framerate(v)
    video_output_folder = output_video_folder / "{}x{}".format(width, height) / v.stem

    def string_to_tuple(tuple_string):
        assert(tuple_string[0] == '(' and tuple_string[-1] == ')')
        return tuple([float(f) for f in tuple_string[1:-1].split(', ')])

    def generic_metadata():
        metadata = pd.DataFrame({"video": [v] * num_frames})
        metadata["height"] = height
        metadata["width"] = width
        metadata["framerate"] = framerate
        metadata["video_quality"] = height * width / framerate
        metadata['frame'] = metadata.index + 1
        # timestemp is in microseconds
        metadata['time'] = 1e6 * metadata.index / framerate
        metadata['indoor'] = True
        metadata['location_valid'] = False
        metadata["device"] = "generic"
        metadata["camera_model"] = generic_model
        metadata["frame_quat_w"] = np.NaN
        metadata["frame_quat_x"] = np.NaN
        metadata["frame_quat_y"] = np.NaN
        metadata["frame_quat_z"] = np.NaN
        metadata["x"] = np.NaN
        metadata["y"] = np.NaN
        metadata["z"] = np.NaN
        metadata["camera_params"] = [tuple()] * len(metadata)
        return metadata

    # First, try to open the CSV file {video name}_metadata.csv which should contain the metadata
    # If it fails, try to get metadata from MP4 by using PDraw
    # At last resort, simply assume generic parameters

    metadata_file_path = v.parent / "{}_metadata.csv".format(v.stem)
    if metadata_file_path.isfile():
        metadata = pd.read_csv(metadata_file_path)
        # check that the pandas dataframe is well formed
        keys_to_check = ["camera_model", "camera_params", "x", "y", "z",
                         "frame_quat_w", "frame_quat_x", "frame_quat_y", "frame_quat_z",
                         "location_valid", "time"]
        for k in keys_to_check:
            assert k in metadata.keys(), "Metadata file does not contain required field {}".format(k)
        metadata["camera_params"] = metadata["camera_params"].apply(string_to_tuple)
        if "frame" not in metadata.keys():
            metadata["frame"] = range(1, len(metadata) + 1)
        metadata['video'] = v
        if 'indoor' not in metadata.keys():
            metadata['indoor'] = len(metadata[metadata["location_valid"]]) > 0
        if 'video_quality' not in metadata.keys():
            metadata["video_quality"] = height * width / framerate
        device = "other"
    else:
        try:
            proj = Proj(system)
            metadata = am.extract_metadata(v.parent, v, env["pdraw"], proj,
                                           width, height, framerate)
            metadata["camera_model"] = "PINHOLE"
            device = "anafi"
216
217
        except Exception as e:
            raise e
218
219
220
221
222
223
224
225
            # No metadata found, construct a simpler dataframe without location
            metadata = generic_metadata()
            device = "generic"
    metadata["num_frames"] = num_frames
    metadata["device"] = device
    return metadata, device, video_output_folder


226
def process_video_folder(videos_list, individual_pictures, output_video_folder, colmap_img_root, centroid,
Clément Pinard's avatar
Clément Pinard committed
227
                         thorough_db, fps=1, total_frames=500, orientation_weight=1, resolution_weight=1,
228
                         output_colmap_format="bin", save_space=False, include_lowfps_thorough=False,
229
230
                         max_sequence_length=1000, num_neighbours=10,
                         existing_georef=False, existing_metadata=None, **env):
231
    metadata_list = []
Clement Pinard's avatar
Clement Pinard committed
232
233
234
    video_output_folders = {}
    images = {}
    colmap_cameras = {}
235
    tempfile_database = Path(tempfile.NamedTemporaryFile().name)
Clément Pinard's avatar
Clément Pinard committed
236
237
    if thorough_db.isfile():
        thorough_db.copy(thorough_db.stripext() + "_backup.db")
238
239
240
241
242
243
244
245
246
247
    if existing_metadata is not None:
        already_treated_videos = existing_metadata["video"].unique()
        videos_to_treat = [v for v in videos_list if v not in already_treated_videos]
        if len(videos_to_treat) == 0:
            print("All videos already treated. "
                  "Remove the file {} if you want to reprocess everything".format(env["full_metadata"]))
            return None, {}, existing_metadata
        print("Skipping {} already treated videos".format(len(already_treated_videos)))
    else:
        videos_to_treat = videos_list
Clement Pinard's avatar
Clement Pinard committed
248
    path_lists_output = {}
249
    database = db.COLMAPDatabase.connect(thorough_db)
Clement Pinard's avatar
Clement Pinard committed
250
251
    database.create_tables()
    print("extracting metadata for {} videos...".format(len(videos_list)))
252
253
254
    videos_summary = {"anafi": {"indoor": 0, "outdoor": 0},
                      "other": {"indoor": 0, "outdoor": 0},
                      "generic": 0}
255
    for v in tqdm(videos_to_treat):
256
257
258
        metadata, device, output_folder = get_video_metadata(v, output_video_folder, **env)
        video_output_folders[v] = output_folder
        output_folder.makedirs_p()
Clement Pinard's avatar
Clement Pinard committed
259

260
261
262
263
264
265
266
267
268
        if include_lowfps_thorough:
            by_time = metadata.set_index(pd.to_datetime(metadata["time"], unit="us"))
            by_time_lowfps = by_time.resample("{:.3f}S".format(1/fps)).first()
            metadata["sampled"] = by_time["time"].isin(by_time_lowfps["time"]).values
        else:
            metadata["sampled"] = False
        if device == "generic":
            videos_summary["generic"] += 1
        else:
Clément Pinard's avatar
Clément Pinard committed
269
            raw_positions = metadata[["x", "y", "z"]]
270
            if metadata["indoor"].iloc[0]:
271
                videos_summary[device]["indoor"] += 1
272
            else:
273
                videos_summary[device]["outdoor"] += 1
274
            if sum(metadata["location_valid"]) > 0:
275
                if centroid is None:
276
                    '''No centroid (possibly because there was no georeferenced lidar pointcloud in the first place)
277
                    set it as the first valid GPS position of the first outdoor video'''
Clément Pinard's avatar
Clément Pinard committed
278
                    centroid = raw_positions[metadata["location_valid"]].iloc[0].values
279
                zero_centered_positions = raw_positions.values - centroid
Clément Pinard's avatar
bug fix    
Clément Pinard committed
280
281
282
283
                radius = np.max(np.abs(zero_centered_positions))
                if radius > 1000:
                    print("Warning, your positions coordinates are most likely too high, have you configured the right GPS system ?")
                    print("It should be the same as the one used for the Lidar point cloud")
284
                metadata["x"], metadata["y"], metadata["z"] = zero_centered_positions.transpose()
285
286
        metadata_list.append(metadata)
    final_metadata = pd.concat(metadata_list, ignore_index=True)
287
288
    print("{} outdoor anafi videos".format(videos_summary["anafi"]["outdoor"]))
    print("{} indoor anafi videos".format(videos_summary["anafi"]["indoor"]))
289
290
    print("{} indoor other videos".format(videos_summary["other"]["outdoor"]))
    print("{} indoor other videos".format(videos_summary["other"]["indoor"]))
291
    print("{} generic videos".format(videos_summary["generic"]))
Clement Pinard's avatar
Clement Pinard committed
292

293
    if((not existing_georef) and (sum(final_metadata["location_valid"]) == 0) and (videos_summary["anafi"]["indoor"] > 0)):
Clément Pinard's avatar
Clément Pinard committed
294
295
        # We have no GPS data but we have navdata, which will help rescale the colmap model
        # Take the longest video and do as if the GPS was valid
296
297
298
299
300
301
302
303
304
305
306
307
308
309
        indoor_video_diameters = {}
        for md in metadata_list:
            if (metadata["device"].iloc[0] != "anafi") or (not metadata["indoor"].iloc[0]):
                continue
            positions = md[["x", "y", "z"]].values
            video_displacement_diameter = np.linalg.norm(positions.max(axis=0) - positions.min(axis=0))
            if not np.isnan(video_displacement_diameter):
                indoor_video_diameters[video_displacement_diameter] = v

        if len(indoor_video_diameters) > 0:
            longest_video = indoor_video_diameters[max(indoor_video_diameters)]
            print("Only indoor videos used, will use {} for COLMAP rescaling".format(longest_video))
            video_index = final_metadata["video"] == longest_video
            final_metadata.loc[video_index, "location_valid"] = True
Clément Pinard's avatar
Clément Pinard committed
310

Clement Pinard's avatar
Clement Pinard committed
311
312
313
    print("{} frames in total".format(len(final_metadata)))

    final_metadata["camera_id"] = 0
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
    # Set up Anafi cameras, zoom included
    cam_fields = ["camera_model", "width", "height", "camera_params"]
    cam_dfs = []

    if any(final_metadata["device"] == "other"):
        cam_dfs.append(register_new_cameras(final_metadata, "other", cam_fields, database, colmap_cameras))
    if any(final_metadata["device"] == "anafi"):
        # For anafi we don't treat cameras the same if the framerate is different
        # because potentially different rectification algorithms are applied
        anafi_cam_fields = cam_fields + ["framerate"]
        cam_dfs.append(register_new_cameras(final_metadata, "anafi", anafi_cam_fields, database, colmap_cameras))
    if any(final_metadata["device"] == "generic"):
        print("Undefined remaining devices, assigning generic models to them")
        # Fix a single camera per video. This doesn't support different levels of zoom, but
        # COLMAP is not robust to too many different independant camera models
Clément Pinard's avatar
Clément Pinard committed
329
        generic_cam_fields = cam_fields + ["video"]
330
        cam_dfs.append(register_new_cameras(final_metadata, "generic", generic_cam_fields, database, colmap_cameras))
331
    print("Cameras : ")
332
    print(pd.concat(cam_dfs))
333

334
335
    already_sampled = sum(final_metadata["sampled"]) + (existing_metadata["sampled"] if existing_metadata is not None else 0)
    to_extract = total_frames - len(individual_pictures) - already_sampled
Clement Pinard's avatar
Clement Pinard committed
336

Clément Pinard's avatar
Clément Pinard committed
337
    if to_extract <= 0:
338
        pass
Clément Pinard's avatar
Clément Pinard committed
339
    elif to_extract < len(final_metadata):
Clement Pinard's avatar
Clement Pinard committed
340
341
        print("subsampling based on K-Means, to get {}"
              " frames from videos, for a total of {} frames".format(to_extract, total_frames))
342
        final_metadata = optimal_sample(final_metadata, to_extract,
Clement Pinard's avatar
Clement Pinard committed
343
344
345
                                        orientation_weight,
                                        resolution_weight)
        print("Done.")
Clément Pinard's avatar
Clément Pinard committed
346
347
    else:
        final_metadata["sampled"] = True
Clement Pinard's avatar
Clement Pinard committed
348

349
    print("Constructing COLMAP model with {:,} frames".format(sum(final_metadata["sampled"])))
Clement Pinard's avatar
Clement Pinard committed
350

351
352
353
354
    database.commit()
    thorough_db.copy(tempfile_database)
    temp_database = db.COLMAPDatabase.connect(tempfile_database)

Clement Pinard's avatar
Clement Pinard committed
355
    final_metadata["image_path"] = ""
356
357
    final_metadata["db_id"] = -1
    for current_id, row in tqdm(final_metadata.iterrows(), total=len(final_metadata)):
Clement Pinard's avatar
Clement Pinard committed
358
359
360
        video = row["video"]
        frame = row["frame"]
        camera_id = row["camera_id"]
361
        current_image_path = video_output_folders[video].relpath(colmap_img_root) / video.stem + "_{:05d}.jpg".format(frame)
Clement Pinard's avatar
Clement Pinard committed
362

363
364
365
        final_metadata.at[current_id, "image_path"] = current_image_path
        db_image_id = temp_database.add_image(current_image_path, int(camera_id))
        final_metadata.at[current_id, "db_id"] = db_image_id
Clement Pinard's avatar
Clement Pinard committed
366
367
368
369
370
371

        if row["sampled"]:
            frame_qvec = row[["frame_quat_w",
                              "frame_quat_x",
                              "frame_quat_y",
                              "frame_quat_z"]].values
372
373
            if True in pd.isnull(frame_qvec):
                frame_qvec = np.array([1, 0, 0, 0])
nicolas's avatar
nicolas committed
374
375
            x, y, z = row[["x", "y", "z"]]
            frame_tvec = np.array([x, y, z])
376
            if row["location_valid"] and not row['indoor']:
Clement Pinard's avatar
Clement Pinard committed
377
378
379
380
381
                frame_gps = row[["location_longitude", "location_latitude", "location_altitude"]]
            else:
                frame_gps = np.full(3, np.NaN)

            world_qvec, world_tvec = world_coord_from_frame(frame_qvec, frame_tvec)
382
383
384
385
            database.add_image(current_image_path, int(camera_id), prior_t=frame_gps, image_id=db_image_id)
            images[db_image_id] = rm.Image(id=db_image_id, qvec=world_qvec, tvec=world_tvec,
                                           camera_id=camera_id, name=current_image_path,
                                           xys=[], point3D_ids=[])
Clement Pinard's avatar
Clement Pinard committed
386
387
388

    database.commit()
    database.close()
389
390
    temp_database.commit()
    temp_database.close()
Clement Pinard's avatar
Clement Pinard committed
391
392
393
    rm.write_model(colmap_cameras, images, {}, output_video_folder, "." + output_colmap_format)
    print("COLMAP model created")

nicolas's avatar
nicolas committed
394
395
396
397
    thorough_georef, thorough_paths = get_georef(final_metadata[final_metadata["sampled"]])
    path_lists_output["thorough"] = {}
    path_lists_output["thorough"]["frames"] = thorough_paths
    path_lists_output["thorough"]["georef"] = thorough_georef
Clement Pinard's avatar
Clement Pinard committed
398
399
400

    print("Extracting frames from videos")

401
    for v in tqdm(videos_to_treat):
Clement Pinard's avatar
Clement Pinard committed
402
        video_metadata = final_metadata[final_metadata["video"] == v]
nicolas's avatar
nicolas committed
403
        by_time = video_metadata.set_index(pd.to_datetime(video_metadata["time"], unit="us"))
Clement Pinard's avatar
Clement Pinard committed
404
405
        video_folder = video_output_folders[v]
        video_metadata.to_csv(video_folder/"metadata.csv")
nicolas's avatar
nicolas committed
406
407
408
409
410
        path_lists_output[v] = {}
        video_metadata_1fps = by_time.resample("{:.3f}S".format(1/fps)).first()
        georef, frame_paths = get_georef(video_metadata_1fps)
        path_lists_output[v]["frames_lowfps"] = frame_paths
        path_lists_output[v]["georef_lowfps"] = georef
Clément Pinard's avatar
Clément Pinard committed
411
        num_chunks = len(video_metadata) // max_sequence_length + 1
412
413
414
415
        chunks = [list(frames) for frames in np.array_split(video_metadata["image_path"],
                                                            num_chunks)]
        # Add some overlap between chunks, in order to ease the model merging afterwards
        for chunk, next_chunk in zip(chunks, chunks[1:]):
Clément Pinard's avatar
Clément Pinard committed
416
            chunk.extend(next_chunk[:num_neighbours])
417
418
        path_lists_output[v]["frames_full"] = chunks

Clement Pinard's avatar
Clement Pinard committed
419
        if save_space:
Clément Pinard's avatar
Clément Pinard committed
420
421
            frame_ids = set(video_metadata[video_metadata["sampled"]]["frame"].values) | \
                set(video_metadata_1fps["frame"].values)
422
            frame_ids = sorted(list(frame_ids))
Clément Pinard's avatar
Clément Pinard committed
423
            if len(frame_ids) > 0:
nicolas's avatar
nicolas committed
424
                extracted_frames = env["ffmpeg"].extract_specific_frames(v, video_folder, frame_ids)
Clement Pinard's avatar
Clement Pinard committed
425
        else:
nicolas's avatar
nicolas committed
426
            extracted_frames = env["ffmpeg"].extract_images(v, video_folder)
427
428
429
430
        set_gps(extracted_frames, video_metadata, colmap_img_root)
    if existing_metadata is not None:
        final_metadata = pd.concat([existing_metadata, final_metadata], ignore_index=True)
    return path_lists_output, video_output_folders, final_metadata
Clement Pinard's avatar
Clement Pinard committed
431
432
433
434
435
436


if __name__ == '__main__':
    args = parser.parse_args()
    env = vars(args)
    env["videos_list"] = sum((list(args.video_folder.walkfiles('*{}'.format(ext))) for ext in args.vid_ext), [])
Clément Pinard's avatar
Clément Pinard committed
437
    output_video_folder = args.colmap_img_root / "Videos"
Clement Pinard's avatar
Clement Pinard committed
438
439
    output_video_folder.makedirs_p()
    env["output_video_folder"] = output_video_folder
440
    env["individual_pictures"] = sum((list(args.colmap_img_root.walkfiles('*{}'.format(ext))) for ext in args.pic_ext), [])
Clément Pinard's avatar
Clément Pinard committed
441
442
443
    env["pdraw"] = PDraw(args.nw, verbose=args.verbose)
    env["ffmpeg"] = FFMpeg(verbose=args.verbose)
    env["output_colmap_format"] = args.output_format
Clement Pinard's avatar
Clement Pinard committed
444
445
446
447
448
449

    if args.centroid_path is not None:
        centroid = np.loadtxt(args.centroid_path)
    else:
        centroid = np.zeros(3)
    env["centroid"] = centroid
450
    lists, extracted_video_folders, full_metadata = process_video_folder(**env)
Clement Pinard's avatar
Clement Pinard committed
451
452

    if lists is not None:
453
        full_metadata.to_csv(args.colmap_img_root/"full_video_metadata.csv")
Clément Pinard's avatar
Clément Pinard committed
454
455
456
        with open(args.colmap_img_root/"video_frames_for_thorough_scan.txt", "w") as f:
            f.write("\n".join(lists["thorough"]["frames"]) + "\n")
        with open(args.colmap_img_root/"georef.txt", "w") as f:
Clément Pinard's avatar
Clément Pinard committed
457
            f.write("\n".join(lists["thorough"]["georef"]))
Clement Pinard's avatar
Clement Pinard committed
458
        for v in env["videos_list"]:
459
460
            if v not in extracted_video_folders.keys():
                continue
Clément Pinard's avatar
Clément Pinard committed
461
462
463
464
465
466
467
468
469
            video_folder = extracted_video_folders[v]
            with open(video_folder / "lowfps.txt", "w") as f:
                f.write("\n".join(lists[v]["frames_lowfps"]) + "\n")
            with open(video_folder / "georef.txt", "w") as f:
                f.write("\n".join(lists["thorough"]["georef"]) + "\n")
                f.write("\n".join(lists[v]["georef_lowfps"]) + "\n")
            for j, l in enumerate(lists[v]["frames_full"]):
                with open(video_folder / "full_chunk_{}.txt".format(j), "w") as f:
                    f.write("\n".join(l) + "\n")