def main():
# Look at resize_op/resize_op.cpp to start this tutorial.
sc = sp.Client()
cwd = os.path.dirname(os.path.abspath(__file__))
if not os.path.isfile(os.path.join(cwd, 'resize_op/build/libresize_op.so')):
print(
'You need to build the custom op first: \n'
'$ pushd {}/resize_op; mkdir build && cd build; cmake ..; make; popd'.
format(cwd))
exit()
# To load a custom op into the Scanner runtime, we use db.load_op to open the
# shared library we compiled. If the op takes arguments, it also optionally
# takes a path to the generated python file for the arg protobuf.
sc.load_op(
os.path.join(cwd, 'resize_op/build/libresize_op.so'),
os.path.join(cwd, 'resize_op/build/resize_pb2.py'))
example_video_path = util.download_video()
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
frames = sc.io.Input([video_stream])
# Then we use our op just like in the other examples.
resized_frames = sc.ops.MyResize(frame=frames, width=200, height=300)
output_stream = sp.NamedVideoStream(sc, 'example_resized')
output = sc.io.Output(resized_frames, [output_stream])
sc.run(output, sp.PerfParams.estimate())
video_stream.delete(sc)
output_stream.delete(sc)
def main():
# Now we can use these new Ops in Scanner:
sc = sp.Client()
# Download an example video
example_video_path = util.download_video()
# Create a stream and input to read our example video
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
frames = sc.io.Input([video_stream])
resized_fn_frames = sc.ops.resize_fn(frame=frames, width=640, height=480)
resized_class_frames = sc.ops.ResizeClass(frame=frames,
width=320,
height=240)
fn_stream = sp.NamedVideoStream(sc, 'fn_frames')
fn_output = sc.io.Output(resized_fn_frames, [fn_stream])
class_stream = sp.NamedVideoStream(sc, 'class_frames')
class_output = sc.io.Output(resized_class_frames, [class_stream])
sc.run([fn_output, class_output], sp.PerfParams.estimate())
fn_stream.save_mp4('01_resized_fn')
class_stream.save_mp4('01_resized_class')
for stream in [fn_stream, class_stream]:
stream.delete(sc)
print('Finished! Two videos were saved to the current directory: '
'01_resized_fn.mp4, 01_resized_class.mp4')
def main():
sc = sp.Client()
# Frames on disk can either be stored uncompressed (raw bits) or compressed
# (encoded using some form of image or video compression). When Scanner
# reads frames from a table, it automatically decodes the data if necessary.
# The Op DAG only sees the raw frames. For example, this table is stored
# as compressed video.
def make_blurred_frame(streams):
frames = sc.io.Input(streams)
blurred_frames = sc.ops.Blur(frame=frames, kernel_size=3, sigma=0.5)
sampled_frames = sc.streams.Range(blurred_frames, [(0, 30)])
return frames, sampled_frames
example_video_path = util.download_video()
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
# By default, if an Op outputs a frame with 3 channels with type uint8,
# those frames will be compressed using video encoding. No other frame
# type is currently compressed.
frame, blurred_frame = make_blurred_frame([video_stream])
stream = sp.NamedVideoStream(sc, 'output_table_name')
output = sc.io.Output(blurred_frame, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.delete(sc)
frame, blurred_frame = make_blurred_frame([video_stream])
# The compression parameters can be controlled by annotating the output
# of an Op that produces frames
low_quality_frame = blurred_frame.compress_video(quality=35)
low_quality_stream = sp.NamedVideoStream(sc, 'low_quality_video')
output = sc.io.Output(low_quality_frame, [low_quality_stream])
sc.run(output, sp.PerfParams.estimate())
frame, blurred_frame = make_blurred_frame([video_stream])
# If no compression is desired, this can be specified by indicating that
# the Op output should be lossless.
lossless_frame = blurred_frame.lossless()
lossless_stream = sp.NamedVideoStream(sc, 'lossless_video')
output = sc.io.Output(lossless_frame, [lossless_stream])
sc.run(output, sp.PerfParams.estimate())
# Any sequence of frames which are saved as a compressed `NamedVideoStream` can
# be exported as an mp4 file by calling save_mp4 on the stream. This will output
# a file called 'low_quality_video.mp4' in the current directory.
low_quality_stream.save_mp4('low_quality_video')
low_quality_stream.delete(sc)
lossless_stream.delete(sc)
def main():
movie_path = util.download_video() if len(sys.argv) <= 1 else sys.argv[1]
print('Detecting shots in movie {}'.format(movie_path))
movie_name = os.path.basename(movie_path)
# Use GPU kernels if we have a GPU
if have_gpu():
device = DeviceType.GPU
scanner_montage = True
else:
device = DeviceType.CPU
scanner_montage = False
with Database() as db:
print('Loading movie into Scanner database...')
s = time.time()
[movie_table], _ = db.ingest_videos([(movie_name, movie_path)],
force=True)
print('Time: {:.1f}s'.format(time.time() - s))
s = time.time()
print('Computing a color histogram for each frame...')
frame = movie_table.as_op().all()
histogram = db.ops.Histogram(frame=frame, device=device)
job = Job(columns=[histogram], name=movie_name + '_hist')
hists_table = db.run(job, force=True)
print('\nTime: {:.1f}s'.format(time.time() - s))
s = time.time()
print('Computing shot boundaries...')
# Read histograms from disk
hists = [
h for _, h in hists_table.load(['histogram'], parsers.histograms)
]
boundaries = compute_shot_boundaries(hists)
print('Time: {:.1f}s'.format(time.time() - s))
s = time.time()
print('Creating shot montage...')
if scanner_montage:
# Make montage in scanner
montage_img = make_montage_scanner(db, movie_table, boundaries)
else:
# Make montage in python
# Loading the frames for each shot boundary
frames = movie_table.load(['frame'], rows=boundaries)
montage_img = make_montage(len(boundaries), frames)
print('')
print('Time: {:.1f}s'.format(time.time() - s))
cv2.imwrite('shots.jpg', montage_img)
print('Successfully generated shots.jpg')
def main():
sc = sp.Client()
example_video_path = util.download_video()
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
frames = sc.io.Input([video_stream])
# You can tell Scanner which frames of the video (or which rows of a video
# table) you want to sample. Here, we indicate that we want to stride
# the frame column by 4 (select every 4th frame)
strided_frames = sc.streams.Stride(frames, [4])
# We process the sampled frame same as before.
hists = sc.ops.Histogram(frame=strided_frames)
hist_stream = sp.NamedVideoStream(sc, 'example_hist_strided')
output = sc.io.Output(hists, [hist_stream])
sc.run(output, sp.PerfParams.estimate())
# Loop over the column's rows. Each row is a tuple of the frame number and
# value for that row.
video_hists = hist_stream.load()
num_rows = 0
for frame_hists in video_hists:
assert len(frame_hists) == 3
assert frame_hists[0].shape[0] == 16
num_rows += 1
assert num_rows == round(video_stream.len() / 4)
video_stream.delete(sc)
hist_stream.delete(sc)
# Here's some examples of other sampling modes:
# Range takes a specific subset of a video. Here, it runs over all frames
# from 0 to 100
sc.streams.Range(frames, [(0, 100)])
# Gather takes an arbitrary list of frames from a video.
sc.streams.Gather(frames, [[10, 17, 32]])
def main():
# Now we can use these new Ops in Scanner:
db = Database()
# Download an example video
example_video_path = util.download_video()
# Ingest it into the database
[input_table], _ = db.ingest_videos([('example', example_video_path)],
force=True)
frame = db.sources.FrameColumn()
resized_frame_fn = db.ops.resize_fn(frame=frame, width=640, height=480)
resized_frame_class = db.ops.ResizeClass(frame=frame,
width=320,
height=240)
output = db.sinks.FrameColumn(columns={
'frame1': resized_frame_fn,
'frame2': resized_frame_class
})
job = Job(op_args={
frame: input_table.column('frame'),
output: 'example_python_op'
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('frame1').save_mp4('01_resized_fn')
table.column('frame2').save_mp4('01_resized_class')
print('Finished! Two videos were saved to the current directory: '
'01_resized_fn.mp4, 01_resized_class.mp4')
from scannerpy import Database, DeviceType, Job
from scannerpy.stdlib import NetDescriptor
import numpy as np
import cv2
import struct
import sys
import os
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
video_path = util.download_video() if len(sys.argv) <= 1 else sys.argv[1]
print('Performing classification on video {}'.format(video_path))
video_name = os.path.splitext(os.path.basename(video_path))[0]
with Database() as db:
[input_table], _ = db.ingest_videos([(video_name, video_path)], force=True)
descriptor = NetDescriptor.from_file(db, 'nets/resnet.toml')
batch_size = 48
frame = db.sources.FrameColumn()
caffe_input = db.ops.CaffeInput(frame=frame,
net_descriptor=descriptor.as_proto(),
batch_size=batch_size,
device=DeviceType.GPU)
caffe_output = db.ops.Caffe(caffe_frame=caffe_input,
net_descriptor=descriptor.as_proto(),
batch_size=batch_size,
batch=batch_size,
device=DeviceType.GPU)
from scannerpy import Database, DeviceType, Job, ColumnType
from scannerpy.stdlib import NetDescriptor, parsers, pipelines
import math
import os
import subprocess
import cv2
import sys
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
script_dir = os.path.dirname(os.path.abspath(__file__))
util.download_video()
with Database() as db:
video_path = util.download_video()
if not db.has_table('example'):
print('Ingesting video into Scanner ...')
db.ingest_videos([('example', video_path)], force=True)
input_table = db.table('example')
poses_table = pipelines.detect_poses(
db, [input_table], lambda t: t.range(0, 100, task_size = 25),
'example_poses',
height = 360)[0]
height = 720)[0]
print('Drawing on frames...')
db.register_op('PoseDraw', [('frame', ColumnType.Video), 'poses'],
[('frame', ColumnType.Video)])
db.register_python_kernel('PoseDraw', DeviceType.CPU,
def main():
# Initialize a connection to the Scanner database. Loads configuration from the
# ~/.scanner.toml configuration file.
db = Database()
# Create a Scanner table from our video in the format (table name,
# video path). If any videos fail to ingest, they'll show up in the failed
# list. If force is true, it will overwrite existing tables of the same
# name.
example_video_path = util.download_video()
_, failed = db.ingest_videos([('example', example_video_path),
('example2', example_video_path),
('thisshouldfail', 'thisshouldfail.mp4')],
force=True)
print(db.summarize())
print('Failures:', failed)
# Scanner processes videos by forming a graph of operations that operate
# on input frames from a table and produce outputs to a new table.
# FrameColumn declares that we want to read from a table column that
# represents a video frame.
frame = db.sources.FrameColumn()
# These frames are input into a Histogram op that computes a color histogram
# for each frame.
hist = db.ops.Histogram(frame=frame)
# Finally, any columns provided to Output will be saved to the output
# table at the end of the computation. Here, 'hist' is the name of the
# column for the output table.
output_op = db.sinks.Column(columns={'hist': hist})
# A job defines a table you want to create. In op_args, we bind the
# FrameColumn from above to the table we want to read from and name
# the output table 'example_hist' by binding a string to output_op.
job = Job(op_args={
frame: db.table('example').column('frame'),
output_op: 'example_hist'
})
job2 = Job(op_args={
frame: db.table('example2').column('frame'),
output_op: 'example_hist2'
})
# This executes the job and produces the output table. You'll see a progress
# bar while Scanner is computing the outputs.
output_tables = db.run(output=output_op, jobs=[job, job2], force=True)
# Load the histograms from a column of the output table. The
# readers.histograms function converts the raw bytes output by Scanner
# into a numpy array for each channel.
video_hists = output_tables[0].column('hist').load(readers.histograms)
# Loop over the column's values, a set of 3 histograms (for each color channel) per element.
num_rows = 0
for frame_hists in video_hists:
assert len(frame_hists) == 3
assert frame_hists[0].shape[0] == 16
num_rows += 1
assert num_rows == db.table('example').num_rows()
def main():
# Startup the Scanner runtime and setup a connection to it. Loads configuration from the
# ~/.scanner.toml configuration file.
sc = sp.Client()
example_video_path = util.download_video()
# Scanner processes videos by forming a graph of operations that operate
# on input streams and produce output streams. For example, here we can
# construct a `NamedVideoStream` which reads from an example video:
video_stream1 = sp.NamedVideoStream(sc,
'example1',
path=example_video_path)
# Now we can start constructing a computation graph. First, we need to declare
# our input streams that we are going to be reading from. We'll use the
# `NamedVideoStream` we just created to build an `Input` operation:
frames = sc.io.Input([video_stream1])
# The output of the `Input` op is an edge in the computation graph which represents
# the sequence of values produced by `Input`, which in this case are frames from
# the video stream we provided.
# Now we will process the frames from `Input` using a `Histogram` op that computes
# a color histogram for each frame.
hists = sc.ops.Histogram(frame=frames)
# Finally, we define an output stream to write the computed histograms to.
# To do this, we will create a `NamedStream` (which is just like a `NamedVideoStream`
# but for non-video data):
named_stream1 = sp.NamedStream(sc, 'example1_hist')
# Then, just like we defined an `Input` op to read the input stream, we'll define
# an `Output` op to write to the output stream we just defined:
output_op = sc.io.Output(hists, [named_stream1])
# Now we can execute this computation graph to produce the output stream.
# You'll see a progress bar while Scanner is computing the outputs.
# Note that the .run function also takes as input a PerfParams object which contains some
# parameters that tune the performance of the job, e.g. how many video frames can fit into memory.
# By default, you can use PerfParams.estimate() which heuristically guesses an appropriate set of
# parameters (but is not guaranteed to work!). Later tutorials will address how to tune these params.
job_id = sc.run(output_op, sp.PerfParams.estimate())
# Scanner also supports operating over batches of streams to allow for more parallelism.
# For example, let's define a new graph that operates on two copies of our example video:
named_stream1.delete(sc)
video_stream2 = sp.NamedVideoStream(sc,
'example2',
path=example_video_path)
frames = sc.io.Input([video_stream1, video_stream2])
hists = sc.ops.Histogram(frame=frames)
named_stream2 = sp.NamedStream(sc, 'example2_hist')
output_op = sc.io.Output(hists, [named_stream1, named_stream2])
job_id = sc.run(output_op, sp.PerfParams.estimate())
# For each of the streams we provided to the one `Input` op in our graph, Scanner will
# execute the computation graph on the frames from those streams independently. This
# mechanism allows you to provide Scanner with potentially thousands of videos you
# would like to process, up front. If Scanner was executing on a cluster of machines,
# it would be able to parallelize the processing of those videos across the entire cluster.
# Now that the graph has been processed, we can load the histograms from our computed stream:
num_rows = 0
for hist in named_stream1.load():
assert len(hist) == 3
assert hist[0].shape[0] == 16
num_rows += 1
assert num_rows == video_stream1.len()
# Just to cleanup, we'll delete the streams we created:
streams = [video_stream1, video_stream2, named_stream1, named_stream2]
streams[0].storage().delete(sc, streams)
def main():
db = Database()
example_video_path = util.download_video()
[input_table], _ = db.ingest_videos([('example', example_video_path)],
force=True)
frame = db.sources.FrameColumn()
# When working with bounded or unbounded stateful operations, it is sometimes
# useful to introduce boundaries between sequences of frames which restrict
# state being shared between them. For example, if you are tracking objects
# in a movie, you likely do not want the same trackers when the camera changes
# scenes since the objects you were tracking are no longer there!
# Scanner provides support for limiting state propagation across frames through
# "slicing" operations.
sliced_frame = db.streams.Slice(frame, db.partitioner.all(50))
# Here, we sliced the input frame stream into chunks of 50 elements. What this
# means is that any ops which process 'sliced_frame' will *only* be able to
# maintain state within each chunk of 50 elements.
# For example, let's say we grab the background subtraction op from the previous
# tutorial (02_op_attributes) and want to run it on a static camera video which
# sometimes jumps forward in time:
@scannerpy.register_python_op(bounded_state=60)
class BackgroundSubtraction(scannerpy.Kernel):
def __init__(self, config):
self.config = config
self.alpha = config.args['alpha']
self.thresh = config.args['threshold']
def reset(self):
self.average_image = None
def execute(self, frame: FrameType) -> FrameType:
if self.average_image is None:
self.average_image = frame
mask = np.abs(frame - self.average_image) < 255 * self.thresh
mask = np.any(mask, axis=2)
masked_image = np.copy(frame)
wmask = np.where(mask)
masked_image[wmask[0], wmask[1], :] = 0
self.average_image = (self.average_image * (1.0 - self.alpha) +
frame * self.alpha)
return masked_image
# First, we download the static camera video from youtube
# subprocess.check_call(
# 'youtube-dl -f 137 \'https://youtu.be/cVHqFqNz7eM\' -o test.mp4',
# shell=True)
# [static_table], _ = db.ingest_videos([('static_video', 'test.mp4')],
# force=True)
static_table = input_table
frame = db.sources.FrameColumn()
# Imagine that there are scene changes at frames 1100, 1200, and 1500, To tell
# scanner that we do not want background subtraction to cross these boundaries,
# we can create a 'partitioner' which splits the input.
scene_partitions = db.partitioner.ranges([(1100, 1200), (1200, 1500)])
# Now we slice the input frame sequence into these two partitions using a
# slice operation
sliced_frame = db.streams.Slice(frame, partitioner=scene_partitions)
# Then we perform background subtraction and indicate we need 60 prior
# frames to produce correct output
masked_frame = db.ops.BackgroundSubtraction(frame=sliced_frame,
alpha=0.02,
threshold=0.05,
bounded_state=60)
# Since the background subtraction operation is done, we can unslice the
# sequence to join it back into a single contiguous stream. You must unslice
# sequences before feeding them back into sinks
unsliced_frame = db.streams.Unslice(masked_frame)
output = db.sinks.Column(columns={'frame': unsliced_frame})
job = Job(op_args={
frame: static_table.column('frame'),
output: '04_masked_video',
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('frame').save_mp4('04_masked')
videos = []
videos.append('04_masked.mp4')
print('Finished! The following videos were written: {:s}'.format(
', '.join(videos)))
def main():
sc = sp.Client()
example_video_path = util.download_video()
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
frame = sc.io.Input([video_stream])
# When working with bounded or unbounded stateful operations, it is sometimes
# useful to introduce boundaries between sequences of frames which restrict
# state being shared between them. For example, if you are tracking objects
# in a movie, you likely do not want the same trackers when the camera changes
# scenes since the objects you were tracking are no longer there!
# Scanner provides support for limiting state propagation across frames through
# "slicing" operations.
sliced_frame = sc.streams.Slice(frame, partitions=[sc.partitioner.all(50)])
# Here, we sliced the input frame stream into chunks of 50 elements. What this
# means is that any ops which process 'sliced_frame' will *only* be able to
# maintain state within each chunk of 50 elements.
# For example, let's say we grab the background subtraction op from the previous
# tutorial (02_op_attributes) and want to run it on our example video:
@sp.register_python_op(bounded_state=60)
class BackgroundSubtraction(sp.Kernel):
def __init__(self, config, alpha, threshold):
self.config = config
self.alpha = alpha
self.thresh = threshold
def reset(self):
self.average_image = None
def execute(self, frame: sp.FrameType) -> sp.FrameType:
if self.average_image is None:
self.average_image = frame
mask = np.abs(frame - self.average_image) < 255 * self.thresh
mask = np.any(mask, axis=2)
masked_image = np.copy(frame)
wmask = np.where(mask)
masked_image[wmask[0], wmask[1], :] = 0
self.average_image = (self.average_image * (1.0 - self.alpha) +
frame * self.alpha)
return masked_image
frame = sc.io.Input([video_stream])
# Imagine that there are scene changes at frames 1100, 1200, and 1400, To tell
# scanner that we do not want background subtraction to cross these boundaries,
# we can create a 'partitioner' which splits the input.
scene_partitions = sc.partitioner.ranges([(1100, 1200), (1200, 1400)])
# Now we slice the input frame sequence into these two partitions using a
# slice operation
sliced_frame = sc.streams.Slice(frame, partitions=[scene_partitions])
# Then we perform background subtraction and indicate we need 60 prior
# frames to produce correct output
masked_frame = sc.ops.BackgroundSubtraction(frame=sliced_frame,
alpha=0.02,
threshold=0.05,
bounded_state=60)
# Since the background subtraction operation is done, we can unslice the
# sequence to join it back into a single contiguous stream. You must unslice
# sequences before feeding them back into sinks
unsliced_frame = sc.streams.Unslice(masked_frame)
stream = sp.NamedVideoStream(sc, '04_masked_video')
output = sc.io.Output(unsliced_frame, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.save_mp4('04_masked')
stream.delete(sc)
videos = []
videos.append('04_masked.mp4')
print('Finished! The following videos were written: {:s}'.format(
', '.join(videos)))
from scannerpy import Database, Job, DeviceType, BulkJob
from scannerpy.stdlib import parsers
import numpy as np
import cv2
import sys
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
from timeit import default_timer as now
with Database() as db:
# Create a Scanner table from our video in the format (table name,
# video path). If any videos fail to ingest, they'll show up in the failed
# list. If force is true, it will overwrite existing tables of the same
# name.
example_video_path1 = util.download_video(1)
example_video_path2 = util.download_video(2)
# test time of ingest
start = now()
input_tables, failed = db.ingest_videos(
[('test_raw1', example_video_path1),
('test_raw2', example_video_path2)],
force=True)
print('Time to ingest videos: {:.6f}s'.format(now() - start))
print(db.summarize())
print('Failures:', failed)
# Scanner processes videos by forming a graph of operations that operate
# on input frames from a table and produce outputs to a new table.
from scannerpy import Database, DeviceType, Job
from scannerpy.stdlib import NetDescriptor, parsers, bboxes
import math
import os
import subprocess
import cv2
import sys
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
util.download_video()
with Database() as db:
# TODO(wcrichto): comment the demo. Make the Scanner philosophy more clear.
# Add some figures to the wiki perhaps explaining the high level
descriptor = NetDescriptor.from_file(db, 'nets/caffe_facenet.toml')
facenet_args = db.protobufs.FacenetArgs()
facenet_args.threshold = 0.5
caffe_args = facenet_args.caffe_args
caffe_args.net_descriptor.CopyFrom(descriptor.as_proto())
caffe_args.batch_size = 2
print('Ingesting video into Scanner ...')
[input_table], _ = db.ingest_videos([('example', util.download_video())], force=True)
base_batch = 4
base_size = 1280*720
# TODO(apoms): determine automatically from video
current_size = 1280*720
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
################################################################################
# This tutorial shows how to organize your videos into Collections. #
################################################################################
with Database() as db:
# Instead of ingesting each video into a table individually, we can group
# video # tables into a single entity called a collection. Here, we create
# a collection # called "example_collection" from the video in the previous
# example. # Collections do not incur any runtime overhead, but are simply
# an abstraction for more easily managing your videos.
example_video_path = util.download_video()
input_collection, _ = db.ingest_video_collection('example_collection',
[example_video_path],
force=True)
print(db.summarize())
# You can retrieve table objects off the collection.
table = output_collection.tables(0)
frame = db.ops.FrameInput()
hist = db.ops.Histogram(frame=frame)
output_op = db.ops.Output(columns=[hist])
# You can use a collection to enumerate tables
jobs = []
for table in input_collection.tables():
job = Job(op_args={
def main(num = 1):
movie_path = util.download_video(num)
print('Detecting shots in movie {}'.format(movie_path))
movie_name = 'shot_detect'
# Use GPU kernels if we have a GPU
if util.have_gpu():
device = DeviceType.GPU
else:
device = DeviceType.CPU
device = DeviceType.CPU
with Database() as db:
print('Loading movie into Scanner DB...')
total_time = 0.0
start = now()
############ ############ ############ ############
# 0. Ingest the video into the database
############ ############ ############ ############
[movie_table], _ = db.ingest_videos([(movie_name, movie_path)],
force=True)
stop = now()
total_time += stop - start
print('Ingest time: {:.4f}s '.format(stop - start))
print('Number of frames in movie: {:d}'.format(movie_table.num_rows()))
start = now()
############ ############ ############ ############
# 1. Run Histogram over the entire video in Scanner
############ ############ ############ ############
frame = db.ops.FrameInput()
histogram = db.ops.Histogram(
frame = frame,
device = device)
output = db.ops.Output(columns=[histogram])
job = Job(op_args={
frame: movie_table.column('frame'),
output: movie_name + '_hist'
})
bulk_job = BulkJob(output=output, jobs=[job])
[hists_table] = db.run(bulk_job, force=True)
stop = now()
total_time += stop - start
print('Compute histogram time: {:.4f}s, {:.1f} fps'.format(
stop - start, movie_table.num_rows() / (stop - start)))
hists_table.profiler().write_trace('shot_detect_hist.trace')
start = now()
############ ############ ############ ############
# 2. Load histograms and compute shot boundaries
# in python
############ ############ ############ ############
# Read histograms from disk
hists = [h for _, h in hists_table.load(['histogram'],
parsers.histograms)]
boundaries = compute_shot_boundaries(hists)
stop = now()
total_time += stop - start
print('Found {:d} shots.'.format(len(boundaries)))
print('Find boundaries time: {:.4f}s'.format(stop - start))
start = now()
############ ############ ############ ############
# 3. Create montage in Scanner
############ ############ ############ ############
row_length = 16
rows_per_item = 1
target_width = 256
item_size = row_length * rows_per_item
# Compute partial row montages that we will stack together
# at the end
frame = db.ops.FrameInput()
gather_frame = frame.sample()
sliced_frame = gather_frame.slice()
montage = db.ops.Montage(
frame = sliced_frame,
num_frames = item_size,
target_width = target_width,
frames_per_row = row_length,
device = device)
sampled_montage = montage.sample()
output = db.ops.Output(
columns=[sampled_montage.unslice().lossless()])
starts_remainder = len(boundaries) % item_size
evenly_divisible = (starts_remainder == 0)
if not evenly_divisible:
boundaries = boundaries[0:len(boundaries) - starts_remainder]
job = Job(op_args={
frame: movie_table.column('frame'),
gather_frame: db.sampler.gather(boundaries),
sliced_frame: db.partitioner.all(item_size),
sampled_montage: [db.sampler.gather([item_size - 1])
for _ in range(len(boundaries) / item_size)],
output: 'montage_image'
})
bulk_job = BulkJob(output=output, jobs=[job])
[montage_table] = db.run(bulk_job, force=True)
# Stack all partial montages together
montage_img = np.zeros((1, target_width * row_length, 3), dtype=np.uint8)
for idx, img in montage_table.column('montage').load():
img = np.flip(img, 2)
montage_img = np.vstack((montage_img, img))
stop = now()
total_time += stop - start
print('Create Montage time: {:.4f}s'.format(stop - start))
montage_table.profiler().write_trace('shot_detect_montage.trace')
start = now()
############ ############ ############ ############
# 4. Write montage to disk
############ ############ ############ ############
cv2.imwrite('detected_shots.jpg', montage_img)
stop = now()
total_time += stop - start
print('Successfully generated detected_shots.jpg')
print('Write image time: {:.4f}s'.format(stop - start))
print('Total time: {:.4f}s'.format(total_time))
def main():
db = Database()
example_video_path = util.download_video()
[input_table], _ = db.ingest_videos([('example', example_video_path)],
force=True)
videos = []
# Many ops simply involve applying some processing to their inputs and then
# returning their outputs. But there are also many operations in video
# processing that require the ability to see adjacent frames (such as for
# computing optical flow), need to keep state over time (such as for tracking
# objects), or need to process multiple elements for efficiency reasons (such as
# batching for DNNs).
# Scanner ops therefore have several optional attributes that enable them to
# support these forms of operations:
# 1. Device Type:
# Ops can specify that they require CPUs or GPUs by declaring their device
# type. By default, the device_type is DeviceType.CPU.
@scannerpy.register_python_op(device_type=DeviceType.CPU)
def device_resize(config, frame: FrameType) -> FrameType:
return cv2.resize(frame, (config.args['width'], config.args['height']))
frame = db.sources.FrameColumn()
resized_frame = db.ops.device_resize(frame=frame, width=640, height=480)
output = db.sinks.FrameColumn(columns={'frame': resized_frame})
job = Job(op_args={
frame: input_table.column('frame'),
output: 'example_resize'
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('frame').save_mp4('02_device_resize')
videos.append('02_device_resize.mp4')
# 2. Batch:
# The Op can receive multiple elements at once to enable SIMD or
# vector-style processing.
@scannerpy.register_python_op(batch=10)
def batch_resize(config,
frame: Sequence[FrameType]) -> Sequence[FrameType]:
output_frames = []
for fr in frame:
output_frames.append(
cv2.resize(fr, (config.args['width'], config.args['height'])))
return output_frames
# Here we specify that the resize op should receive a batch of 10
# input elements at once. Logically, each element is still processed
# independently but multiple elements are provided to enable efficient
# batch processing. If there are not enough elements left in a stream,
# the Op may receive less than a batch worth of elements.
frame = db.sources.FrameColumn()
resized_frame = db.ops.batch_resize(frame=frame,
width=640,
height=480,
batch=10)
output = db.sinks.FrameColumn(columns={'frame': resized_frame})
job = Job(op_args={
frame: input_table.column('frame'),
output: 'example_batch_resize'
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('frame').save_mp4('02_batch_resize')
videos.append('02_batch_resize.mp4')
# 3. Stencil:
# The Op requires a window of input elements (for example, the
# previous and next element) at the same time to produce an
# output.
# Here, we use the stencil attribute to write an optical flow op which
# computes flow between the current and next frame.
@scannerpy.register_python_op(stencil=[0, 1])
def optical_flow(config, frame: Sequence[FrameType]) -> FrameType:
gray1 = cv2.cvtColor(frame[0], cv2.COLOR_BGR2GRAY)
gray2 = cv2.cvtColor(frame[1], cv2.COLOR_BGR2GRAY)
flow = cv2.calcOpticalFlowFarneback(gray1, gray2, None, 0.5, 3, 15, 3,
5, 1.2, 0)
return flow
# This op visualizes the flow field by converting it into an rgb image
@scannerpy.register_python_op()
def visualize_flow(config, flow: FrameType) -> FrameType:
hsv = np.zeros(shape=(flow.shape[0], flow.shape[1], 3), dtype=np.uint8)
hsv[..., 1] = 255
mag, ang = cv2.cartToPolar(flow[..., 0], flow[..., 1])
hsv[..., 0] = ang * 180 / np.pi / 2
hsv[..., 2] = cv2.normalize(mag, None, 0, 255, cv2.NORM_MINMAX)
rgb = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
return rgb
frame = db.sources.FrameColumn()
# This next line is using a feature we'll discuss in the next tutorial, but you
# can think of it as selecting a subset of elements from the stream (here,
# frames 0 to 30)
range_frame = db.streams.Range(frame, 0, 30)
flow = db.ops.optical_flow(frame=range_frame, stencil=[0, 1])
flow_viz = db.ops.visualize_flow(flow=flow)
output = db.sinks.FrameColumn(columns={'flow_viz': flow_viz})
job = Job(op_args={
frame: input_table.column('frame'),
output: 'example_flow'
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('flow_viz').save_mp4('02_flow')
videos.append('02_flow.mp4')
# 4. Bounded State:
# For each output, the Op requires at least W sequential
# "warmup" elements before it can produce a valid output.
# For example, if the output of this Op is sampled
# sparsely, this guarantees that the Op can "warmup"
# its state on a stream of W elements before producing the
# requested output.
import subprocess
@scannerpy.register_python_op(bounded_state=60)
class BackgroundSubtraction(scannerpy.Kernel):
def __init__(self, config):
self.config = config
self.alpha = config.args['alpha']
self.thresh = config.args['threshold']
# Reset is called when the kernel switches to a new part of the stream
# and so shouldn't maintain it's previous state
def reset(self):
self.average_image = None
def execute(self, frame: FrameType) -> FrameType:
if self.average_image is None:
self.average_image = frame
mask = np.abs(frame - self.average_image) < 255 * self.thresh
mask = np.any(mask, axis=2)
masked_image = np.copy(frame)
wmask = np.where(mask)
masked_image[wmask[0], wmask[1], :] = 0
self.average_image = (self.average_image * (1.0 - self.alpha) +
frame * self.alpha)
return masked_image
# Here we wrote an op that performs background subtraction by keeping a
# running average image over the past frames. We set `bounded_state=60`
# to indicate that this kernel needs at least 60 frames before the output
# should be considered reasonable.
# First, we download a static camera video from youtube
# subprocess.check_call(
# 'youtube-dl -f 137 \'https://youtu.be/cVHqFqNz7eM\' -o test.mp4',
# shell=True)
# [static_table], _ = db.ingest_videos([('static_video', 'test.mp4')],
# force=True)
static_table = input_table
# Then we perform background subtraction and indicate we need 60 prior
# frames to produce correct output
frame = db.sources.FrameColumn()
masked_frame = db.ops.BackgroundSubtraction(frame=frame,
alpha=0.05,
threshold=0.05,
bounded_state=60)
# Here, we say that we only want the outputs for this range of frames
sampled_frame = db.streams.Range(masked_frame, 0, 120)
output = db.sinks.Column(columns={'frame': sampled_frame})
job = Job(op_args={
frame: static_table.column('frame'),
output: 'masked_video',
})
[table] = db.run(output=output, jobs=[job], force=True)
table.column('frame').save_mp4('02_masked')
videos.append('02_masked.mp4')
# 5. Unbounded State:
# This Op will always process all preceding elements of
# its input streams before producing a requested output.
# This means that sampling operations after this Op
# can not change how many inputs it receives. In the next
# tutorial, we will show how this can be relaxed for
# sub-streams of the input.
@scannerpy.register_python_op(unbounded_state=True)
class Example(scannerpy.Kernel):
def __init__(self, config):
pass
def reset(self):
pass
def execute(self, frame: FrameType) -> bytes:
pass
print('Finished! The following videos were written: {:s}'.format(
', '.join(videos)))
