def extract_frames(
config,
mode="automatic",
algo="kmeans",
crop=False,
userfeedback=True,
cluster_step=1,
cluster_resizewidth=30,
cluster_color=False,
opencv=True,
slider_width=25,
config3d=None,
extracted_cam=0,
videos_list=None,
):
"""
Extracts frames from the videos in the config.yaml file. Only the videos in the config.yaml will be used to select the frames.\n
Use the function ``add_new_video`` at any stage of the project to add new videos to the config file and extract their frames.
The provided function either selects frames from the videos in a randomly and temporally uniformly distributed way (uniform), \n
by clustering based on visual appearance (k-means), or by manual selection.
Three important parameters for automatic extraction: numframes2pick, start and stop are set in the config file.
After frames have been extracted from all videos from one camera, matched frames from other cameras can be extracted using mode = ``match``.
This is necessary if you plan to use epipolar lines to improve labeling across multiple camera angles. It will overwrite previously extracted
images from the second camera angle if necessary.
Please refer to the user guide for more details on methods and parameters https://www.nature.com/articles/s41596-019-0176-0
or the preprint: https://www.biorxiv.org/content/biorxiv/early/2018/11/24/476531.full.pdf
Parameters
----------
config : string
Full path of the config.yaml file as a string.
mode : string
String containing the mode of extraction. It must be either ``automatic`` or ``manual`` to extract the initial set of frames. It can also be ``match`` to match frames between
the cameras in preparation for the use of epipolar lines during labeling; namely, extract from camera_1 first, then run this to extract the matched frames in camera_2.
WARNING: if you use match, and you previously extracted and labeled frames from the second camera, this will overwrite your data. This will require you deleting the
collectdata.h5/.csv files before labeling.... Use with caution!
algo : string
String specifying the algorithm to use for selecting the frames. Currently, deeplabcut supports either ``kmeans`` or ``uniform`` based selection. This flag is
only required for ``automatic`` mode and the default is ``uniform``. For uniform, frames are picked in temporally uniform way, kmeans performs clustering on downsampled frames (see user guide for details).
Note: color information is discarded for kmeans, thus e.g. for camouflaged octopus clustering one might want to change this.
crop : bool, optional
If True, video frames are cropped according to the corresponding coordinates stored in the config.yaml.
Alternatively, if cropping coordinates are not known yet, crop='GUI' triggers a user interface
where the cropping area can be manually drawn and saved.
userfeedback: bool, optional
If this is set to false during automatic mode then frames for all videos are extracted. The user can set this to true, which will result in a dialog,
where the user is asked for each video if (additional/any) frames from this video should be extracted. Use this, e.g. if you have already labeled
some folders and want to extract data for new videos.
cluster_resizewidth: number, default: 30
For k-means one can change the width to which the images are downsampled (aspect ratio is fixed).
cluster_step: number, default: 1
By default each frame is used for clustering, but for long videos one could only use every nth frame (set by: cluster_step). This saves memory before clustering can start, however,
reading the individual frames takes longer due to the skipping.
cluster_color: bool, default: False
If false then each downsampled image is treated as a grayscale vector (discarding color information). If true, then the color channels are considered. This increases
the computational complexity.
opencv: bool, default: True
Uses openCV for loading & extractiong (otherwise moviepy (legacy))
slider_width: number, default: 25
Width of the video frames slider, in percent of window
config3d: string, optional
Path to the config.yaml file in the 3D project. This will be used to match frames extracted from all cameras present in the field 'camera_names' to the
frames extracted from the camera given by the parameter 'extracted_cam'
extracted_cam: number, default: 0
The index of the camera that already has extracted frames. This will match frame numbers to extract for all other cameras.
This parameter is necessary if you wish to use epipolar lines in the labeling toolbox. Only use if mode = 'match' and config3d is provided.
videos_list: list, default: None
A list of the string containing full paths to videos to extract frames for. If this is left as None all videos specified in the config file will have frames extracted.
Otherwise one can select a subset by passing those paths.
Examples
--------
for selecting frames automatically with 'kmeans' and want to crop the frames.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans',True)
--------
for selecting frames automatically with 'kmeans' and defining the cropping area at runtime.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans','GUI')
--------
for selecting frames automatically with 'kmeans' and considering the color information.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans',cluster_color=True)
--------
for selecting frames automatically with 'uniform' and want to crop the frames.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic',crop=True)
--------
for selecting frames manually,
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','manual')
--------
for selecting frames manually, with a 60% wide frames slider
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','manual', slider_width=60)
--------
for extracting frames from a second camera that match the frames extracted from the first
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml', mode='match', extracted_cam=0)
While selecting the frames manually, you do not need to specify the ``crop`` parameter in the command. Rather, you will get a prompt in the graphic user interface to choose
if you need to crop or not.
--------
"""
import os
import sys
import re
import glob
import numpy as np
from pathlib import Path
from skimage import io
from skimage.util import img_as_ubyte
from deeplabcut.utils import frameselectiontools
from deeplabcut.utils import auxiliaryfunctions
if mode == "manual":
wd = Path(config).resolve().parents[0]
os.chdir(str(wd))
from deeplabcut.gui import frame_extraction_toolbox
frame_extraction_toolbox.show(config, slider_width)
elif mode == "automatic":
config_file = Path(config).resolve()
cfg = auxiliaryfunctions.read_config(config_file)
print("Config file read successfully.")
numframes2pick = cfg["numframes2pick"]
start = cfg["start"]
stop = cfg["stop"]
# Check for variable correctness
if start > 1 or stop > 1 or start < 0 or stop < 0 or start >= stop:
raise Exception(
"Erroneous start or stop values. Please correct it in the config file."
)
if numframes2pick < 1 and not int(numframes2pick):
raise Exception(
"Perhaps consider extracting more, or a natural number of frames."
)
if videos_list is None:
videos = cfg.get("video_sets_original") or cfg["video_sets"]
else: #filter video_list by the ones in the config file
videos = [v for v in cfg["video_sets"] if v in videos_list]
if opencv:
from deeplabcut.utils.auxfun_videos import VideoReader
else:
from moviepy.editor import VideoFileClip
has_failed = []
for video in videos:
if userfeedback:
print(
"Do you want to extract (perhaps additional) frames for video:",
video,
"?",
)
askuser = input("yes/no")
else:
askuser = "******"
if (askuser == "y" or askuser == "yes" or askuser == "Ja"
or askuser == "ha" or askuser == "oui"
or askuser == "ouais"): # multilanguage support :)
if opencv:
cap = VideoReader(video)
nframes = len(cap)
else:
# Moviepy:
clip = VideoFileClip(video)
fps = clip.fps
nframes = int(np.ceil(clip.duration * 1.0 / fps))
if not nframes:
print("Video could not be opened. Skipping...")
continue
indexlength = int(np.ceil(np.log10(nframes)))
fname = Path(video)
output_path = Path(
config).parents[0] / "labeled-data" / fname.stem
if output_path.exists():
if len(os.listdir(output_path)):
if userfeedback:
askuser = input(
"The directory already contains some frames. Do you want to add to it?(yes/no): "
)
if not (askuser == "y" or askuser == "yes"
or askuser == "Y" or askuser == "Yes"):
sys.exit("Delete the frames and try again later!")
if crop == "GUI":
cfg = select_cropping_area(config, [video])
try:
coords = cfg["video_sets"][video]["crop"].split(",")
except KeyError:
coords = cfg["video_sets_original"][video]["crop"].split(
",")
if crop and not opencv:
clip = clip.crop(
y1=int(coords[2]),
y2=int(coords[3]),
x1=int(coords[0]),
x2=int(coords[1]),
)
elif not crop:
coords = None
print("Extracting frames based on %s ..." % algo)
if algo == "uniform":
if opencv:
frames2pick = frameselectiontools.UniformFramescv2(
cap, numframes2pick, start, stop)
else:
frames2pick = frameselectiontools.UniformFrames(
clip, numframes2pick, start, stop)
elif algo == "kmeans":
if opencv:
frames2pick = frameselectiontools.KmeansbasedFrameselectioncv2(
cap,
numframes2pick,
start,
stop,
crop,
coords,
step=cluster_step,
resizewidth=cluster_resizewidth,
color=cluster_color,
)
else:
frames2pick = frameselectiontools.KmeansbasedFrameselection(
clip,
numframes2pick,
start,
stop,
step=cluster_step,
resizewidth=cluster_resizewidth,
color=cluster_color,
)
else:
print(
"Please implement this method yourself and send us a pull request! Otherwise, choose 'uniform' or 'kmeans'."
)
frames2pick = []
if not len(frames2pick):
print("Frame selection failed...")
return
output_path = (Path(config).parents[0] / "labeled-data" /
Path(video).stem)
is_valid = []
if opencv:
for index in frames2pick:
cap.set_to_frame(index) # extract a particular frame
frame = cap.read_frame()
if frame is not None:
image = img_as_ubyte(frame)
img_name = (str(output_path) + "/img" +
str(index).zfill(indexlength) + ".png")
if crop:
io.imsave(
img_name,
image[int(coords[2]):int(coords[3]),
int(coords[0]):int(coords[1]), :, ],
) # y1 = int(coords[2]),y2 = int(coords[3]),x1 = int(coords[0]), x2 = int(coords[1]
else:
io.imsave(img_name, image)
is_valid.append(True)
else:
print("Frame", index, " not found!")
is_valid.append(False)
cap.close()
else:
for index in frames2pick:
try:
image = img_as_ubyte(
clip.get_frame(index * 1.0 / clip.fps))
img_name = (str(output_path) + "/img" +
str(index).zfill(indexlength) + ".png")
io.imsave(img_name, image)
if np.var(image) == 0: # constant image
print(
"Seems like black/constant images are extracted from your video. Perhaps consider using opencv under the hood, by setting: opencv=True"
)
is_valid.append(True)
except FileNotFoundError:
print("Frame # ", index, " does not exist.")
is_valid.append(False)
clip.close()
del clip
if not any(is_valid):
has_failed.append(True)
else:
has_failed.append(False)
else: # NO!
has_failed.append(False)
if all(has_failed):
print("Frame extraction failed. Video files must be corrupted.")
return
elif any(has_failed):
print("Although most frames were extracted, some were invalid.")
else:
print(
"Frames were successfully extracted, for the videos listed in the config.yaml file."
)
print(
"\nYou can now label the frames using the function 'label_frames' "
"(Note, you should label frames extracted from diverse videos (and many videos; we do not recommend training on single videos!))."
)
elif mode == "match":
import cv2
config_file = Path(config).resolve()
cfg = auxiliaryfunctions.read_config(config_file)
print("Config file read successfully.")
videos = sorted(cfg["video_sets"].keys())
project_path = Path(config).parents[0]
labels_path = os.path.join(project_path, "labeled-data/")
video_dir = os.path.join(project_path, "videos/")
try:
cfg_3d = auxiliaryfunctions.read_config(config3d)
except:
raise Exception(
"You must create a 3D project and edit the 3D config file before extracting matched frames. \n"
)
cams = cfg_3d["camera_names"]
extCam_name = cams[extracted_cam]
del cams[extracted_cam]
label_dirs = sorted(
glob.glob(os.path.join(labels_path, "*" + extCam_name + "*")))
# select crop method
crop_list = []
for video in videos:
if extCam_name not in video:
if crop == "GUI":
cfg = select_cropping_area(config, [video])
print("in gui code")
coords = cfg["video_sets"][video]["crop"].split(",")
if crop and not opencv:
clip = clip.crop(
y1=int(coords[2]),
y2=int(coords[3]),
x1=int(coords[0]),
x2=int(coords[1]),
)
elif not crop:
coords = None
crop_list.append(coords)
print(crop_list)
for coords, dirPath in zip(crop_list, label_dirs):
extracted_images = glob.glob(os.path.join(dirPath, "*png"))
imgPattern = re.compile("[0-9]{1,10}")
for cam in cams:
output_path = re.sub(extCam_name, cam, dirPath)
for fname in os.listdir(output_path):
if fname.endswith(".png"):
os.remove(os.path.join(output_path, fname))
vid = os.path.join(video_dir,
os.path.basename(output_path)) + ".avi"
cap = cv2.VideoCapture(vid)
print("\n extracting matched frames from " +
os.path.basename(output_path) + ".avi")
for img in extracted_images:
imgNum = re.findall(imgPattern, os.path.basename(img))[0]
cap.set(1, int(imgNum))
ret, frame = cap.read()
if ret:
image = img_as_ubyte(
cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
img_name = str(output_path) + "/img" + imgNum + ".png"
if crop:
io.imsave(
img_name,
image[int(coords[2]):int(coords[3]),
int(coords[0]):int(coords[1]), :, ],
)
else:
io.imsave(img_name, image)
print(
"\n Done extracting matched frames. You can now begin labeling frames using the function label_frames\n"
)
else:
print(
"Invalid MODE. Choose either 'manual', 'automatic' or 'match'. Check ``help(deeplabcut.extract_frames)`` on python and ``deeplabcut.extract_frames?`` \
for ipython/jupyter notebook for more details.")
def extract_frames(config,
mode="automatic",
algo="kmeans",
crop=False,
userfeedback=True,
cluster_step=1,
cluster_resizewidth=30,
cluster_color=False,
opencv=True,
slider_width=25,
user_index=None):
"""
Extracts frames from the videos in the config.yaml file. Only the videos in the config.yaml will be used to select the frames.\n
Use the function ``add_new_video`` at any stage of the project to add new videos to the config file and extract their frames.
The provided function either selects frames from the videos in a randomly and temporally uniformly distributed way (uniform), \n
by clustering based on visual appearance (k-means), or by manual selection.
Three important parameters for automatic extraction: numframes2pick, start and stop are set in the config file.
Please refer to the user guide for more details on methods and parameters https://www.nature.com/articles/s41596-019-0176-0
or the preprint: https://www.biorxiv.org/content/biorxiv/early/2018/11/24/476531.full.pdf
Parameters
----------
config : string
Full path of the config.yaml file as a string.
mode : string
String containing the mode of extraction. It must be either ``automatic`` or ``manual``.
algo : string
String specifying the algorithm to use for selecting the frames. Currently, deeplabcut supports either ``kmeans`` or ``uniform`` based selection. This flag is
only required for ``automatic`` mode and the default is ``uniform``. For uniform, frames are picked in temporally uniform way, kmeans performs clustering on downsampled frames (see user guide for details).
Note: color information is discarded for kmeans, thus e.g. for camouflaged octopus clustering one might want to change this.
crop : bool, optional
If True, video frames are cropped according to the corresponding coordinates stored in the config.yaml.
Alternatively, if cropping coordinates are not known yet, crop='GUI' triggers a user interface
where the cropping area can be manually drawn and saved.
userfeedback: bool, optional
If this is set to false during automatic mode then frames for all videos are extracted. The user can set this to true, which will result in a dialog,
where the user is asked for each video if (additional/any) frames from this video should be extracted. Use this, e.g. if you have already labeled
some folders and want to extract data for new videos.
cluster_resizewidth: number, default: 30
For k-means one can change the width to which the images are downsampled (aspect ratio is fixed).
cluster_step: number, default: 1
By default each frame is used for clustering, but for long videos one could only use every nth frame (set by: cluster_step). This saves memory before clustering can start, however,
reading the individual frames takes longer due to the skipping.
cluster_color: bool, default: False
If false then each downsampled image is treated as a grayscale vector (discarding color information). If true, then the color channels are considered. This increases
the computational complexity.
opencv: bool, default: True
Uses openCV for loading & extractiong (otherwise moviepy (legacy))
slider_width: number, default: 25
Width of the video frames slider, in percent of window
Examples
--------
for selecting frames automatically with 'kmeans' and want to crop the frames.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans',True)
--------
for selecting frames automatically with 'kmeans' and defining the cropping area at runtime.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans','GUI')
--------
for selecting frames automatically with 'kmeans' and considering the color information.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic','kmeans',cluster_color=True)
--------
for selecting frames automatically with 'uniform' and want to crop the frames.
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','automatic',crop=True)
--------
for selecting frames manually,
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','manual')
--------
for selecting frames manually, with a 60% wide frames slider
>>> deeplabcut.extract_frames('/analysis/project/reaching-task/config.yaml','manual', slider_width=60)
While selecting the frames manually, you do not need to specify the ``crop`` parameter in the command. Rather, you will get a prompt in the graphic user interface to choose
if you need to crop or not.
--------
"""
import os
import sys
import numpy as np
from pathlib import Path
from skimage import io
from skimage.util import img_as_ubyte
from deeplabcut.utils import frameselectiontools
from deeplabcut.utils import auxiliaryfunctions
if mode == "manual":
wd = Path(config).resolve().parents[0]
os.chdir(str(wd))
from deeplabcut.generate_training_dataset import frame_extraction_toolbox
frame_extraction_toolbox.show(config, slider_width)
elif mode == "automatic":
config_file = Path(config).resolve()
cfg = auxiliaryfunctions.read_config(config_file)
print("Config file read successfully.")
numframes2pick = cfg["numframes2pick"]
start = cfg["start"]
stop = cfg["stop"]
# Check for variable correctness
if start > 1 or stop > 1 or start < 0 or stop < 0 or start >= stop:
raise Exception(
"Erroneous start or stop values. Please correct it in the config file."
)
if numframes2pick < 1 and not int(numframes2pick):
raise Exception(
"Perhaps consider extracting more, or a natural number of frames."
)
videos = cfg["video_sets"].keys()
if opencv:
from deeplabcut.utils.auxfun_videos import VideoReader
else:
from moviepy.editor import VideoFileClip
has_failed = []
for vindex, video in enumerate(videos):
if userfeedback:
print(
"Do you want to extract (perhaps additional) frames for video:",
video,
"?",
)
askuser = input("yes/no")
else:
askuser = "******"
if (askuser == "y" or askuser == "yes" or askuser == "Ja"
or askuser == "ha" or askuser == "oui"
or askuser == "ouais"): # multilanguage support :)
if opencv:
cap = VideoReader(video)
nframes = len(cap)
else:
# Moviepy:
clip = VideoFileClip(video)
fps = clip.fps
nframes = int(np.ceil(clip.duration * 1.0 / fps))
if not nframes:
print("Video could not be opened. Skipping...")
continue
indexlength = int(np.ceil(np.log10(nframes)))
fname = Path(video)
output_path = Path(
config).parents[0] / "labeled-data" / fname.stem
if output_path.exists():
if len(os.listdir(output_path)):
if userfeedback:
askuser = input(
"The directory already contains some frames. Do you want to add to it?(yes/no): "
)
if not (askuser == "y" or askuser == "yes"
or askuser == "Y" or askuser == "Yes"):
sys.exit("Delete the frames and try again later!")
if crop == "GUI":
cfg = select_cropping_area(config, [video])
coords = cfg["video_sets"][video]["crop"].split(",")
if crop and not opencv:
clip = clip.crop(
y1=int(coords[2]),
y2=int(coords[3]),
x1=int(coords[0]),
x2=int(coords[1]),
)
elif not crop:
coords = None
print("Extracting frames based on %s ..." % algo)
if algo == "uniform":
if opencv:
frames2pick = frameselectiontools.UniformFramescv2(
cap, numframes2pick, start, stop)
else:
frames2pick = frameselectiontools.UniformFrames(
clip, numframes2pick, start, stop)
elif algo == "kmeans":
if opencv:
frames2pick = frameselectiontools.KmeansbasedFrameselectioncv2(
cap,
numframes2pick,
start,
stop,
crop,
coords,
step=cluster_step,
resizewidth=cluster_resizewidth,
color=cluster_color,
)
else:
frames2pick = frameselectiontools.KmeansbasedFrameselection(
clip,
numframes2pick,
start,
stop,
step=cluster_step,
resizewidth=cluster_resizewidth,
color=cluster_color,
)
elif algo == "user_supplied":
frames2pick = user_index[vindex]
else:
print(
"Please implement this method yourself and send us a pull request! Otherwise, choose 'uniform' or 'kmeans'."
)
frames2pick = []
if not len(frames2pick):
print("Frame selection failed...")
return
output_path = (Path(config).parents[0] / "labeled-data" /
Path(video).stem)
is_valid = []
if opencv:
for index in frames2pick:
cap.set_to_frame(index) # extract a particular frame
frame = cap.read_frame()
if frame is not None:
image = img_as_ubyte(frame)
img_name = (str(output_path) + "/img" +
str(index).zfill(indexlength) + ".png")
if crop:
io.imsave(
img_name,
image[int(coords[2]):int(coords[3]),
int(coords[0]):int(coords[1]), :, ],
) # y1 = int(coords[2]),y2 = int(coords[3]),x1 = int(coords[0]), x2 = int(coords[1]
else:
io.imsave(img_name, image)
is_valid.append(True)
else:
print("Frame", index, " not found!")
is_valid.append(False)
cap.close()
else:
for index in frames2pick:
try:
image = img_as_ubyte(
clip.get_frame(index * 1.0 / clip.fps))
img_name = (str(output_path) + "/img" +
str(index).zfill(indexlength) + ".png")
io.imsave(img_name, image)
if np.var(image) == 0: # constant image
print(
"Seems like black/constant images are extracted from your video. Perhaps consider using opencv under the hood, by setting: opencv=True"
)
is_valid.append(True)
except FileNotFoundError:
print("Frame # ", index, " does not exist.")
is_valid.append(False)
clip.close()
del clip
if not any(is_valid):
has_failed.append(True)
else:
has_failed.append(False)
else: # NO!
has_failed.append(False)
if all(has_failed):
print("Frame extraction failed. Video files must be corrupted.")
return
elif any(has_failed):
print("Although most frames were extracted, some were invalid.")
else:
print(
"Frames were successfully extracted, for the videos of interest."
)
print(
"\nYou can now label the frames using the function 'label_frames' "
"(if you extracted enough frames for all videos).")
else:
print(
"Invalid MODE. Choose either 'manual' or 'automatic'. Check ``help(deeplabcut.extract_frames)`` on python and ``deeplabcut.extract_frames?`` \
for ipython/jupyter notebook for more details.")
class TrackletVisualizer:
def __init__(self, manager, videoname, trail_len=50):
self.manager = manager
self.cmap = plt.cm.get_cmap(manager.cfg["colormap"],
len(set(manager.tracklet2id)))
self.videoname = videoname
self.video = VideoReader(videoname)
self.nframes = len(self.video)
# Take into consideration imprecise OpenCV estimation of total number of frames
if abs(self.nframes - manager.nframes) >= 0.05 * manager.nframes:
print(
"Video duration and data length do not match. Continuing nonetheless..."
)
self.trail_len = trail_len
self.help_text = ""
self.draggable = False
self._curr_frame = 0
self.curr_frame = 0
self.picked = []
self.picked_pair = []
self.cuts = []
self.player = BackgroundPlayer(self)
self.thread_player = Thread(target=self.player.run, daemon=True)
self.thread_player.start()
self.dps = []
def _prepare_canvas(self, manager, fig):
params = {
"keymap.save": "s",
"keymap.back": "left",
"keymap.forward": "right",
"keymap.yscale": "l",
}
for k, v in params.items():
if v in plt.rcParams[k]:
plt.rcParams[k].remove(v)
self.dotsize = manager.cfg["dotsize"]
self.alpha = manager.cfg["alphavalue"]
if fig is None:
self.fig = plt.figure(figsize=(13, 8))
else:
self.fig = fig
gs = self.fig.add_gridspec(2, 2)
self.ax1 = self.fig.add_subplot(gs[:, 0])
self.ax2 = self.fig.add_subplot(gs[0, 1])
self.ax3 = self.fig.add_subplot(gs[1, 1], sharex=self.ax2)
plt.subplots_adjust(bottom=0.2)
for ax in self.ax1, self.ax2, self.ax3:
ax.axis("off")
self.colors = self.cmap(manager.tracklet2id)
self.colors[:, -1] = self.alpha
img = self.video.read_frame()
self.im = self.ax1.imshow(img)
self.scat = self.ax1.scatter([], [], s=self.dotsize**2, picker=True)
self.scat.set_offsets(manager.xy[:, 0])
self.scat.set_color(self.colors)
self.trails = sum(
[self.ax1.plot([], [], "-", lw=2, c=c) for c in self.colors], [])
self.lines_x = sum(
[
self.ax2.plot([], [], "-", lw=1, c=c, pickradius=5)
for c in self.colors
],
[],
)
self.lines_y = sum(
[
self.ax3.plot([], [], "-", lw=1, c=c, pickradius=5)
for c in self.colors
],
[],
)
self.vline_x = self.ax2.axvline(0, 0, 1, c="k", ls=":")
self.vline_y = self.ax3.axvline(0, 0, 1, c="k", ls=":")
custom_lines = [
plt.Line2D([0], [0], color=self.cmap(i), lw=4)
for i in range(len(manager.individuals))
]
self.leg = self.fig.legend(
custom_lines,
manager.individuals,
frameon=False,
fancybox=None,
ncol=len(manager.individuals),
fontsize="small",
bbox_to_anchor=(0, 0.9, 1, 0.1),
loc="center",
)
for line in self.leg.get_lines():
line.set_picker(5)
self.ax_slider = self.fig.add_axes([0.1, 0.1, 0.5, 0.03],
facecolor="lightgray")
self.ax_slider2 = self.fig.add_axes([0.1, 0.05, 0.3, 0.03],
facecolor="darkorange")
self.slider = Slider(
self.ax_slider,
"# Frame",
self.curr_frame,
manager.nframes - 1,
valinit=0,
valstep=1,
valfmt="%i",
)
self.slider.on_changed(self.on_change)
self.slider2 = Slider(
self.ax_slider2,
"Marker size",
1,
30,
valinit=self.dotsize,
valstep=1,
valfmt="%i",
)
self.slider2.on_changed(self.update_dotsize)
self.ax_drag = self.fig.add_axes([0.65, 0.1, 0.05, 0.03])
self.ax_lasso = self.fig.add_axes([0.7, 0.1, 0.05, 0.03])
self.ax_flag = self.fig.add_axes([0.75, 0.1, 0.05, 0.03])
self.ax_save = self.fig.add_axes([0.80, 0.1, 0.05, 0.03])
self.ax_help = self.fig.add_axes([0.85, 0.1, 0.05, 0.03])
self.save_button = Button(self.ax_save, "Save", color="darkorange")
self.save_button.on_clicked(self.save)
self.help_button = Button(self.ax_help, "Help")
self.help_button.on_clicked(self.display_help)
self.drag_toggle = CheckButtons(self.ax_drag, ["Drag"])
self.drag_toggle.on_clicked(self.toggle_draggable_points)
self.flag_button = Button(self.ax_flag, "Flag")
self.flag_button.on_clicked(self.flag_frame)
self.fig.canvas.mpl_connect("pick_event", self.on_pick)
self.fig.canvas.mpl_connect("key_press_event", self.on_press)
self.fig.canvas.mpl_connect("button_press_event", self.on_click)
self.fig.canvas.mpl_connect("close_event", self.player.terminate)
self.selector = PointSelector(self, self.ax1, self.scat, self.alpha)
self.lasso_toggle = CheckButtons(self.ax_lasso, ["Lasso"])
self.lasso_toggle.on_clicked(self.selector.toggle)
self.display_traces(only_picked=False)
self.ax1_background = self.fig.canvas.copy_from_bbox(self.ax1.bbox)
plt.show()
def show(self, fig=None):
self._prepare_canvas(self.manager, fig)
def fill_shaded_areas(self):
self.clean_collections()
if self.picked_pair:
mask = self.manager.get_nonoverlapping_segments(*self.picked_pair)
for ax in self.ax2, self.ax3:
ax.fill_between(
self.manager.times,
*ax.dataLim.intervaly,
mask,
facecolor="darkgray",
alpha=0.2,
)
trans = mtransforms.blended_transform_factory(
self.ax_slider.transData, self.ax_slider.transAxes)
self.ax_slider.vlines(np.flatnonzero(mask),
0,
0.5,
color="darkorange",
transform=trans)
def toggle_draggable_points(self, *args):
self.draggable = not self.draggable
if self.draggable:
self._curr_frame = self.curr_frame
self.scat.set_offsets(np.empty((0, 2)))
self.add_draggable_points()
else:
self.save_coords()
self.clean_points()
self.display_points(self._curr_frame)
self.fig.canvas.draw_idle()
def add_point(self, center, animal, bodypart, **kwargs):
circle = patches.Circle(center, **kwargs)
self.ax1.add_patch(circle)
dp = auxfun_drag.DraggablePoint(circle, bodypart, animal)
dp.connect()
self.dps.append(dp)
def clean_points(self):
for dp in self.dps:
dp.annot.set_visible(False)
dp.disconnect()
self.dps = []
for patch in self.ax1.patches[::-1]:
patch.remove()
def add_draggable_points(self):
self.clean_points()
xy, _, inds = self.manager.get_non_nan_elements(self.curr_frame)
for i, (animal, bodypart) in enumerate(self.manager._label_pairs):
if i in inds:
coords = xy[inds == i].squeeze()
self.add_point(
coords,
animal,
bodypart,
radius=self.dotsize,
fc=self.colors[i],
alpha=self.alpha,
)
def save_coords(self):
coords, nonempty, inds = self.manager.get_non_nan_elements(
self._curr_frame)
if not inds.size:
return
prob = self.manager.prob[:, self._curr_frame]
for dp in self.dps:
label = dp.individual_names, dp.bodyParts
ind = self.manager._label_pairs.index(label)
nrow = np.flatnonzero(inds == ind)
if not nrow.size:
return
nrow = nrow[0]
if not np.array_equal(
coords[nrow],
dp.point.center): # Keypoint has been displaced
coords[nrow] = dp.point.center
prob[ind] = 1
self.manager.xy[nonempty, self._curr_frame] = coords
def flag_frame(self, *args):
self.cuts.append(self.curr_frame)
self.ax_slider.axvline(self.curr_frame, color="r")
if len(self.cuts) == 2:
self.cuts.sort()
mask = np.zeros_like(self.manager.times, dtype=bool)
mask[self.cuts[0]:self.cuts[1] + 1] = True
for ax in self.ax2, self.ax3:
ax.fill_between(
self.manager.times,
*ax.dataLim.intervaly,
mask,
facecolor="darkgray",
alpha=0.2,
)
trans = mtransforms.blended_transform_factory(
self.ax_slider.transData, self.ax_slider.transAxes)
self.ax_slider.vlines(np.flatnonzero(mask),
0,
0.5,
color="darkorange",
transform=trans)
self.fig.canvas.draw_idle()
def on_scroll(self, event):
cur_xlim = self.ax1.get_xlim()
cur_ylim = self.ax1.get_ylim()
xdata = event.xdata
ydata = event.ydata
if event.button == "up":
scale_factor = 0.5
elif event.button == "down":
scale_factor = 2
else: # This should never happen anyway
scale_factor = 1
self.ax1.set_xlim([
xdata - (xdata - cur_xlim[0]) / scale_factor,
xdata + (cur_xlim[1] - xdata) / scale_factor,
])
self.ax1.set_ylim([
ydata - (ydata - cur_ylim[0]) / scale_factor,
ydata + (cur_ylim[1] - ydata) / scale_factor,
])
self.fig.canvas.draw()
def on_press(self, event):
if event.key == "n" or event.key == "right":
self.move_forward()
elif event.key == "b" or event.key == "left":
self.move_backward()
elif event.key == "s":
self.swap()
elif event.key == "i":
self.invert()
elif event.key == "x":
self.flag_frame()
if len(self.cuts) > 1:
self.cuts.sort()
if self.picked_pair:
self.manager.tracklet_swaps[self.picked_pair][
self.cuts] = ~self.manager.tracklet_swaps[
self.picked_pair][self.cuts]
self.fill_shaded_areas()
self.cuts = []
self.ax_slider.lines.clear()
elif event.key == "backspace":
if not self.dps: # Last flag deletion
try:
self.cuts.pop()
self.ax_slider.lines.pop()
if not len(self.cuts) == 2:
self.clean_collections()
except IndexError:
pass
else: # Smart point removal
i = np.nanargmin([
self.calc_distance(*dp.point.center, event.xdata,
event.ydata) for dp in self.dps
])
closest_dp = self.dps[i]
label = closest_dp.individual_names, closest_dp.bodyParts
closest_dp.disconnect()
closest_dp.point.remove()
self.dps.remove(closest_dp)
ind = self.manager._label_pairs.index(label)
self.manager.xy[ind, self._curr_frame] = np.nan
self.manager.prob[ind, self._curr_frame] = np.nan
self.fig.canvas.draw_idle()
elif event.key == "l":
self.lasso_toggle.set_active(not self.lasso_toggle.get_active)
elif event.key == "d":
self.drag_toggle.set_active(not self.drag_toggle.get_active)
elif event.key == "alt+right":
self.player.forward()
elif event.key == "alt+left":
self.player.rewind()
elif event.key == " " or event.key == "tab":
self.player.toggle()
def move_forward(self):
if self.curr_frame < self.manager.nframes - 1:
self.curr_frame += 1
self.slider.set_val(self.curr_frame)
def move_backward(self):
if self.curr_frame > 0:
self.curr_frame -= 1
self.slider.set_val(self.curr_frame)
def swap(self):
if self.picked_pair:
swap_inds = self.manager.get_swap_indices(*self.picked_pair)
inds = np.insert(swap_inds, [0, len(swap_inds)],
[0, self.manager.nframes - 1])
if len(inds):
ind = np.argmax(inds > self.curr_frame)
self.manager.swap_tracklets(
*self.picked_pair, range(inds[ind - 1], inds[ind] + 1))
self.display_traces()
self.slider.set_val(self.curr_frame)
def invert(self):
if not self.picked_pair and len(self.picked) == 2:
self.picked_pair = self.picked
if self.picked_pair:
self.manager.swap_tracklets(*self.picked_pair, [self.curr_frame])
self.display_traces()
self.slider.set_val(self.curr_frame)
def on_pick(self, event):
artist = event.artist
if artist.axes == self.ax1:
self.picked = list(event.ind)
elif artist.axes == self.ax2:
if isinstance(artist, plt.Line2D):
self.picked = [self.lines_x.index(artist)]
elif artist.axes == self.ax3:
if isinstance(artist, plt.Line2D):
self.picked = [self.lines_y.index(artist)]
else: # Click on the legend lines
if self.picked:
num_individual = self.leg.get_lines().index(artist)
nrow = self.manager.tracklet2id.index(num_individual)
inds = [
nrow + self.manager.to_num_bodypart(pick)
for pick in self.picked
]
xy = self.manager.xy[self.picked]
p = self.manager.prob[self.picked]
mask = np.zeros(xy.shape[1], dtype=bool)
if len(self.cuts) > 1:
mask[self.cuts[-2]:self.cuts[-1] + 1] = True
self.cuts = []
self.ax_slider.lines.clear()
self.clean_collections()
else:
return
sl_inds = np.ix_(inds, mask)
sl_picks = np.ix_(self.picked, mask)
old_xy = self.manager.xy[sl_inds].copy()
old_prob = self.manager.prob[sl_inds].copy()
self.manager.xy[sl_inds] = xy[:, mask]
self.manager.prob[sl_inds] = p[:, mask]
self.manager.xy[sl_picks] = old_xy
self.manager.prob[sl_picks] = old_prob
self.picked_pair = []
if len(self.picked) == 1:
for pair in self.manager.swapping_pairs:
if self.picked[0] in pair:
self.picked_pair = pair
break
self.clean_collections()
self.display_traces()
if self.picked_pair:
self.fill_shaded_areas()
self.slider.set_val(self.curr_frame)
def on_click(self, event):
if (event.inaxes in (self.ax2, self.ax3) and event.button == 1
and not any(
line.contains(event)[0]
for line in self.lines_x + self.lines_y)):
x = max(0, min(event.xdata, self.manager.nframes - 1))
self.update_vlines(x)
self.slider.set_val(x)
elif event.inaxes == self.ax1 and not self.scat.contains(event)[0]:
self.display_traces(only_picked=False)
self.clean_collections()
def clean_collections(self):
for coll in (self.ax2.collections + self.ax3.collections +
self.ax_slider.collections):
coll.remove()
def display_points(self, val):
data = self.manager.xy[:, val]
self.scat.set_offsets(data)
def display_trails(self, val):
sl = slice(val - self.trail_len // 2, val + self.trail_len // 2)
for n, trail in enumerate(self.trails):
if n in self.picked:
xy = self.manager.xy[n, sl]
trail.set_data(*xy.T)
else:
trail.set_data([], [])
def display_traces(self, only_picked=True):
if only_picked:
inds = self.picked + list(self.picked_pair)
else:
inds = self.manager.swapping_bodyparts
for n, (line_x, line_y) in enumerate(zip(self.lines_x, self.lines_y)):
if n in inds:
line_x.set_data(self.manager.times, self.manager.xy[n, :, 0])
line_y.set_data(self.manager.times, self.manager.xy[n, :, 1])
else:
line_x.set_data([], [])
line_y.set_data([], [])
for ax in self.ax2, self.ax3:
ax.relim()
ax.autoscale_view()
def display_help(self, event):
if not self.help_text:
self.help_text = """
Key D: activate "drag" so you can adjust bodyparts in that particular frame
Key I: invert the position of a pair of bodyparts
Key L: toggle the lasso selector
Key S: swap two tracklets
Key X: cut swapping tracklets
Left/Right arrow OR Key B/Key N: navigate through the video (back/next)
Tab or SPACE: play/pause the video
Alt+Right/Left: fast forward/rewind - toggles through 5 speed levels
Backspace: deletes last flag (if set) or deletes point
Key P: toggles on pan/zoom tool - left button and drag to pan, right button and drag to zoom
"""
self.text = self.fig.text(
0.5,
0.5,
self.help_text,
horizontalalignment="center",
verticalalignment="center",
fontsize=12,
color="red",
)
else:
self.help_text = ""
self.text.remove()
def update_vlines(self, val):
self.vline_x.set_xdata([val, val])
self.vline_y.set_xdata([val, val])
def on_change(self, val):
self.curr_frame = int(val)
self.video.set_to_frame(self.curr_frame)
img = self.video.read_frame()
if img is not None:
# Automatically disable the draggable points
if self.draggable:
self.drag_toggle.set_active(False)
self.im.set_array(img)
self.display_points(self.curr_frame)
self.display_trails(self.curr_frame)
self.update_vlines(self.curr_frame)
def update_dotsize(self, val):
self.dotsize = val
self.scat.set_sizes([self.dotsize**2])
@staticmethod
def calc_distance(x1, y1, x2, y2):
return np.sqrt((x1 - x2)**2 + (y1 - y2)**2)
def save(self, *args):
self.save_coords()
self.manager.save()
def export_to_training_data(self, pcutoff=0.1):
import os
from skimage import io
inds = self.manager.find_edited_frames()
if not len(inds):
print("No frames have been manually edited.")
return
# Save additional frames to the labeled-data directory
strwidth = int(np.ceil(np.log10(self.nframes)))
tmpfolder = os.path.join(self.manager.cfg["project_path"],
"labeled-data", self.video.name)
if os.path.isdir(tmpfolder):
print(
"Frames from video",
self.video.name,
" already extracted (more will be added)!",
)
else:
attempttomakefolder(tmpfolder)
index = []
for ind in inds:
imagename = os.path.join(tmpfolder,
"img" + str(ind).zfill(strwidth) + ".png")
index.append(os.path.join(*imagename.rsplit(os.path.sep, 3)[-3:]))
if not os.path.isfile(imagename):
self.video.set_to_frame(ind)
frame = self.video.read_frame()
if frame is None:
print("Frame could not be read. Skipping...")
continue
frame = frame.astype(np.ubyte)
if self.manager.cfg["cropping"]:
x1, x2, y1, y2 = [
int(self.manager.cfg[key])
for key in ("x1", "x2", "y1", "y2")
]
frame = frame[y1:y2, x1:x2]
io.imsave(imagename, frame)
# Store the newly-refined data
data = self.manager.format_data()
df = data.iloc[inds]
# Uncertain keypoints are ignored
def filter_low_prob(cols, prob):
mask = cols.iloc[:, 2] < prob
cols.loc[mask] = np.nan
return cols
df = df.groupby(level="bodyparts", axis=1).apply(filter_low_prob,
prob=pcutoff)
df.index = index
machinefile = os.path.join(
tmpfolder,
"machinelabels-iter" + str(self.manager.cfg["iteration"]) + ".h5")
if os.path.isfile(machinefile):
df_old = pd.read_hdf(machinefile)
df_joint = pd.concat([df_old, df])
df_joint = df_joint[~df_joint.index.duplicated(keep="first")]
df_joint.to_hdf(machinefile, key="df_with_missing", mode="w")
df_joint.to_csv(os.path.join(tmpfolder, "machinelabels.csv"))
else:
df.to_hdf(machinefile, key="df_with_missing", mode="w")
df.to_csv(os.path.join(tmpfolder, "machinelabels.csv"))
# Merge with the already existing annotated data
df.columns.set_levels([self.manager.cfg["scorer"]],
level="scorer",
inplace=True)
df.drop("likelihood", level="coords", axis=1, inplace=True)
output_path = os.path.join(
tmpfolder, f'CollectedData_{self.manager.cfg["scorer"]}.h5')
if os.path.isfile(output_path):
print(
"A training dataset file is already found for this video. The refined machine labels are merged to this data!"
)
df_orig = pd.read_hdf(output_path)
df_joint = pd.concat([df, df_orig])
# Now drop redundant ones keeping the first one [this will make sure that the refined machine file gets preference]
df_joint = df_joint[~df_joint.index.duplicated(keep="first")]
df_joint.sort_index(inplace=True)
df_joint.to_hdf(output_path, key="df_with_missing", mode="w")
df_joint.to_csv(output_path.replace("h5", "csv"))
else:
df.sort_index(inplace=True)
df.to_hdf(output_path, key="df_with_missing", mode="w")
df.to_csv(output_path.replace("h5", "csv"))
def create_labeled_video_3d(
config,
path,
videofolder=None,
start=0,
end=None,
trailpoints=0,
videotype="avi",
view=(-113, -270),
xlim=None,
ylim=None,
zlim=None,
draw_skeleton=True,
color_by="bodypart",
figsize=(20, 8),
fps=30,
dpi=300,
):
"""
Creates a video with views from the two cameras and the 3d reconstruction for a selected number of frames.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
path : list
A list of strings containing the full paths to triangulated files for analysis or a path to the directory, where all the triangulated files are stored.
videofolder: string
Full path of the folder where the videos are stored. Use this if the vidoes are stored in a different location other than where the triangulation files are stored. By default is ``None`` and therefore looks for video files in the directory where the triangulation file is stored.
start: int
Integer specifying the start of frame index to select. Default is set to 0.
end: int
Integer specifying the end of frame index to select. Default is set to None, where all the frames of the video are used for creating the labeled video.
trailpoints: int
Number of revious frames whose body parts are plotted in a frame (for displaying history). Default is set to 0.
videotype: string, optional
Checks for the extension of the video in case the input is a directory.\nOnly videos with this extension are analyzed. The default is ``.avi``
view: list
A list that sets the elevation angle in z plane and azimuthal angle in x,y plane of 3d view. Useful for rotating the axis for 3d view
xlim: list
A list of integers specifying the limits for xaxis of 3d view. By default it is set to [None,None], where the x limit is set by taking the minimum and maximum value of the x coordinates for all the bodyparts.
ylim: list
A list of integers specifying the limits for yaxis of 3d view. By default it is set to [None,None], where the y limit is set by taking the minimum and maximum value of the y coordinates for all the bodyparts.
zlim: list
A list of integers specifying the limits for zaxis of 3d view. By default it is set to [None,None], where the z limit is set by taking the minimum and maximum value of the z coordinates for all the bodyparts.
draw_skeleton: bool
If ``True`` adds a line connecting the body parts making a skeleton on on each frame. The body parts to be connected and the color of these connecting lines are specified in the config file. By default: ``True``
color_by : string, optional (default='bodypart')
Coloring rule. By default, each bodypart is colored differently.
If set to 'individual', points belonging to a single individual are colored the same.
Example
-------
Linux/MacOs
>>> deeplabcut.create_labeled_video_3d(config,['/data/project1/videos/3d.h5'],start=100, end=500)
To create labeled videos for all the triangulated files in the folder
>>> deeplabcut.create_labeled_video_3d(config,['/data/project1/videos'],start=100, end=500)
To set the xlim, ylim, zlim and rotate the view of the 3d axis
>>> deeplabcut.create_labeled_video_3d(config,['/data/project1/videos'],start=100, end=500,view=[30,90],xlim=[-12,12],ylim=[15,25],zlim=[20,30])
"""
start_path = os.getcwd()
# Read the config file and related variables
cfg_3d = auxiliaryfunctions.read_config(config)
cam_names = cfg_3d["camera_names"]
pcutoff = cfg_3d["pcutoff"]
markerSize = cfg_3d["dotsize"]
alphaValue = cfg_3d["alphaValue"]
cmap = cfg_3d["colormap"]
bodyparts2connect = cfg_3d["skeleton"]
skeleton_color = cfg_3d["skeleton_color"]
scorer_3d = cfg_3d["scorername_3d"]
if color_by not in ("bodypart", "individual"):
raise ValueError(f"Invalid color_by={color_by}")
file_list = auxiliaryfunctions_3d.Get_list_of_triangulated_and_videoFiles(
path, videotype, scorer_3d, cam_names, videofolder)
print(file_list)
if file_list == []:
raise Exception(
"No corresponding video file(s) found for the specified triangulated file or folder. Did you specify the video file type? If videos are stored in a different location, please use the ``videofolder`` argument to specify their path."
)
for file in file_list:
path_h5_file = Path(file[0]).parents[0]
triangulate_file = file[0]
# triangulated file is a list which is always sorted as [triangulated.h5,camera-1.videotype,camera-2.videotype]
# name for output video
file_name = str(Path(triangulate_file).stem)
videooutname = os.path.join(path_h5_file, file_name + ".mp4")
if os.path.isfile(videooutname):
print("Video already created...")
else:
string_to_remove = str(Path(triangulate_file).suffix)
pickle_file = triangulate_file.replace(string_to_remove,
"_meta.pickle")
metadata_ = auxiliaryfunctions_3d.LoadMetadata3d(pickle_file)
base_filename_cam1 = str(Path(file[1]).stem).split(videotype)[
0] # required for searching the filtered file
base_filename_cam2 = str(Path(file[2]).stem).split(videotype)[
0] # required for searching the filtered file
cam1_view_video = file[1]
cam2_view_video = file[2]
cam1_scorer = metadata_["scorer_name"][cam_names[0]]
cam2_scorer = metadata_["scorer_name"][cam_names[1]]
print("Creating 3D video from %s and %s using %s" % (
Path(cam1_view_video).name,
Path(cam2_view_video).name,
Path(triangulate_file).name,
))
# Read the video files and corresponfing h5 files
vid_cam1 = VideoReader(cam1_view_video)
vid_cam2 = VideoReader(cam2_view_video)
# Look for the filtered predictions file
try:
print("Looking for filtered predictions...")
df_cam1 = pd.read_hdf(
glob.glob(
os.path.join(
path_h5_file,
str("*" + base_filename_cam1 + cam1_scorer +
"*filtered.h5"),
))[0])
df_cam2 = pd.read_hdf(
glob.glob(
os.path.join(
path_h5_file,
str("*" + base_filename_cam2 + cam2_scorer +
"*filtered.h5"),
))[0])
# print("Found filtered predictions, will be use these for triangulation.")
print(
"Found the following filtered data: ",
os.path.join(
path_h5_file,
str("*" + base_filename_cam1 + cam1_scorer +
"*filtered.h5"),
),
os.path.join(
path_h5_file,
str("*" + base_filename_cam2 + cam2_scorer +
"*filtered.h5"),
),
)
except FileNotFoundError:
print(
"No filtered predictions found, the unfiltered predictions will be used instead."
)
df_cam1 = pd.read_hdf(
glob.glob(
os.path.join(
path_h5_file,
str(base_filename_cam1 + cam1_scorer +
"*.h5")))[0])
df_cam2 = pd.read_hdf(
glob.glob(
os.path.join(
path_h5_file,
str(base_filename_cam2 + cam2_scorer +
"*.h5")))[0])
df_3d = pd.read_hdf(triangulate_file)
try:
num_animals = df_3d.columns.get_level_values(
"individuals").unique().size
except KeyError:
num_animals = 1
if end is None:
end = len(df_3d) # All the frames
end = min(end, min(len(vid_cam1), len(vid_cam2)))
frames = list(range(start, end))
output_folder = Path(
os.path.join(path_h5_file, "temp_" + file_name))
output_folder.mkdir(parents=True, exist_ok=True)
# Flatten the list of bodyparts to connect
bodyparts2plot = list(
np.unique(
[val for sublist in bodyparts2connect for val in sublist]))
# Format data
mask2d = df_cam1.columns.get_level_values('bodyparts').isin(
bodyparts2plot)
xy1 = df_cam1.loc[:, mask2d].to_numpy().reshape(
(len(df_cam1), -1, 3))
visible1 = xy1[..., 2] >= pcutoff
xy1[~visible1] = np.nan
xy2 = df_cam2.loc[:, mask2d].to_numpy().reshape(
(len(df_cam1), -1, 3))
visible2 = xy2[..., 2] >= pcutoff
xy2[~visible2] = np.nan
mask = df_3d.columns.get_level_values('bodyparts').isin(
bodyparts2plot)
xyz = df_3d.loc[:, mask].to_numpy().reshape((len(df_3d), -1, 3))
xyz[~(visible1 & visible2)] = np.nan
bpts = df_3d.columns.get_level_values('bodyparts')[mask][::3]
links = make_labeled_video.get_segment_indices(
bodyparts2connect,
bpts,
)
ind_links = tuple(zip(*links))
if color_by == "bodypart":
color = plt.cm.get_cmap(cmap, len(bodyparts2plot))
colors_ = color(range(len(bodyparts2plot)))
colors = np.tile(colors_, (num_animals, 1))
elif color_by == "individual":
color = plt.cm.get_cmap(cmap, num_animals)
colors_ = color(range(num_animals))
colors = np.repeat(colors_, len(bodyparts2plot), axis=0)
# Trick to force equal aspect ratio of 3D plots
minmax = np.nanpercentile(xyz[frames], q=[25, 75], axis=(0, 1)).T
minmax *= 1.1
minmax_range = (minmax[:, 1] - minmax[:, 0]).max() / 2
if xlim is None:
mid_x = np.mean(minmax[0])
xlim = mid_x - minmax_range, mid_x + minmax_range
if ylim is None:
mid_y = np.mean(minmax[1])
ylim = mid_y - minmax_range, mid_y + minmax_range
if zlim is None:
mid_z = np.mean(minmax[2])
zlim = mid_z - minmax_range, mid_z + minmax_range
# Set up the matplotlib figure beforehand
fig, axes1, axes2, axes3 = set_up_grid(figsize, xlim, ylim, zlim,
view)
points_2d1 = axes1.scatter(
*np.zeros((2, len(bodyparts2plot))),
s=markerSize,
alpha=alphaValue,
)
im1 = axes1.imshow(np.zeros((vid_cam1.height, vid_cam1.width)))
points_2d2 = axes2.scatter(
*np.zeros((2, len(bodyparts2plot))),
s=markerSize,
alpha=alphaValue,
)
im2 = axes2.imshow(np.zeros((vid_cam2.height, vid_cam2.width)))
points_3d = axes3.scatter(
*np.zeros((3, len(bodyparts2plot))),
s=markerSize,
alpha=alphaValue,
)
if draw_skeleton:
# Set up skeleton LineCollections
segs = np.zeros((2, len(ind_links), 2))
coll1 = LineCollection(segs, colors=skeleton_color)
coll2 = LineCollection(segs, colors=skeleton_color)
axes1.add_collection(coll1)
axes2.add_collection(coll2)
segs = np.zeros((2, len(ind_links), 3))
coll_3d = Line3DCollection(segs, colors=skeleton_color)
axes3.add_collection(coll_3d)
writer = FFMpegWriter(fps=fps)
with writer.saving(fig, videooutname, dpi=dpi):
for k in tqdm(frames):
vid_cam1.set_to_frame(k)
vid_cam2.set_to_frame(k)
frame_cam1 = vid_cam1.read_frame()
frame_cam2 = vid_cam2.read_frame()
if frame_cam1 is None or frame_cam2 is None:
raise IOError("A video frame is empty.")
im1.set_data(frame_cam1)
im2.set_data(frame_cam2)
sl = slice(max(0, k - trailpoints), k + 1)
coords3d = xyz[sl]
coords1 = xy1[sl, :, :2]
coords2 = xy2[sl, :, :2]
points_3d._offsets3d = coords3d.reshape((-1, 3)).T
points_3d.set_color(colors)
points_2d1.set_offsets(coords1.reshape((-1, 2)))
points_2d1.set_color(colors)
points_2d2.set_offsets(coords2.reshape((-1, 2)))
points_2d2.set_color(colors)
if draw_skeleton:
segs3d = xyz[k][tuple([ind_links])].swapaxes(0, 1)
coll_3d.set_segments(segs3d)
segs1 = xy1[k, :, :2][tuple([ind_links
])].swapaxes(0, 1)
coll1.set_segments(segs1)
segs2 = xy2[k, :, :2][tuple([ind_links
])].swapaxes(0, 1)
coll2.set_segments(segs2)
writer.grab_frame()