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, Job
# The following performs the same computation as main.py, but now on a collection
# of videos instead of just one
db = Database()
# This is the list of videos we are going to process formatted as
# (table_name, video_path).
videos_to_process = [('sample-clip-1', 'sample-clip-1.mp4'),
('sample-clip-2', 'sample-clip-2.mp4'),
('sample-clip-3', 'sample-clip-3.mp4')]
# Ingest the videos into the database
db.ingest_videos(videos_to_process)
# Define the same Computation Graph
frame = db.sources.FrameColumn() # Read from the database
sampled_frame = db.streams.Stride(frame, 3) # Select every third frame
resized = db.ops.Resize(frame=sampled_frame, width=640,
height=480) # Resize input frame
output_frame = db.sinks.Column(columns={'frame':
resized}) # Save resized frame
# Create multiple jobs now, one for each video we want to process
jobs = []
for table_name, _ in videos_to_process:
job = Job(
op_args={
frame: db.table(table_name).column(
'frame'), # Column to read input frames from
port = sp.check_output('''
kubectl get svc/scanner-master -o json | \
jq '.spec.ports[0].nodePort' -r
''',
shell=True).strip().decode('utf-8')
master = '{}:{}'.format(ip, port)
print('Connecting to Scanner database...')
db = Database(master=master, start_cluster=False, config_path='./config.toml')
print('Running Scanner job...')
example_video_path = 'sample.mp4'
[input_table], _ = db.ingest_videos([('example', example_video_path)],
force=True,
inplace=True)
print(db.summarize())
frame = db.sources.FrameColumn()
r_frame = db.ops.Resize(frame=frame, width=320, height=240)
output_op = db.sinks.Column(columns={'frame': r_frame})
job = Job(op_args={
frame: db.table('example').column('frame'),
output_op: 'example_frame'
})
output_tables = db.run(output=output_op, jobs=[job], force=True)
output_tables[0].column('frame').save_mp4('resized_video')
from scannerpy import Database, Job
# Ingest a video into the database
db = Database()
db.ingest_videos([('example_table', 'sample-clip.mp4')])
# Define a Computation Graph
frame = db.sources.FrameColumn() # Read from the database
sampled_frame = db.ops.Stride(frame, 3) # Select every third frame
resized = db.ops.Resize(frame=sampled_frame, width=640,
height=480) # Resize input frame
output_frame = db.sinks.Column(columns={'frame':
resized}) # Save resized frame
job = Job(
op_args={
frame: db.table('example_table').column(
'frame'), # Column to read input frames from
output_frame: 'resized_example' # Name of output table
})
# Execute the computation graph and return a handle to the newly produced tables
output_tables = db.run(output=output_frame, jobs=[job], force=True)
# Save the resized video as an mp4 file
output_tables[0].column('frame').save_mp4('resized-video')
def main(movie_path):
total_start = time.time()
print('Detecting shots in movie {}'.format(movie_path))
movie_name = os.path.basename(movie_path)
# Use GPU kernels if we have a GPU
db = Database()
print('Loading movie into Scanner database...')
s = time.time()
if db.has_gpu():
device = DeviceType.GPU
else:
device = DeviceType.CPU
############ ############ ############ ############
# 0. Ingest the video into the database
############ ############ ############ ############
[movie_table], _ = db.ingest_videos([(movie_name, movie_path)], force=True)
print('Time: {:.1f}s'.format(time.time() - s))
print('Number of frames in movie: {:d}'.format(movie_table.num_rows()))
s = time.time()
############ ############ ############ ############
# 1. Run Histogram over the entire video in Scanner
############ ############ ############ ############
print('Computing a color histogram for each frame...')
frame = db.sources.FrameColumn()
histogram = db.ops.Histogram(frame=frame, device=device)
output = db.sinks.Column(columns={'histogram': histogram})
job = Job(op_args={
frame: movie_table.column('frame'),
output: movie_name + '_hist'
})
[hists_table] = db.run(output=output, jobs=[job], force=True)
print('\nTime: {:.1f}s, {:.1f} fps'.format(
time.time() - s,
movie_table.num_rows() / (time.time() - s)))
s = time.time()
############ ############ ############ ############
# 2. Load histograms and compute shot boundaries
# in python
############ ############ ############ ############
print('Computing shot boundaries...')
# Read histograms from disk
hists = [
h for h in hists_table.column('histogram').load(parsers.histograms)
]
boundaries = compute_shot_boundaries(hists)
print('Found {:d} shots.'.format(len(boundaries)))
print('Time: {:.1f}s'.format(time.time() - s))
s = time.time()
############ ############ ############ ############
# 3. Create montage in Scanner
############ ############ ############ ############
print('Creating shot montage...')
row_length = min(16, len(boundaries))
rows_per_item = 1
target_width = 256
# Compute partial row montages that we will stack together
# at the end
frame = db.sources.FrameColumn()
gather_frame = frame.sample()
sliced_frame = gather_frame.slice()
montage = db.ops.Montage(frame=sliced_frame,
num_frames=row_length * rows_per_item,
target_width=target_width,
frames_per_row=row_length,
device=device)
sampled_montage = montage.sample()
output = db.sinks.Column(
columns={'montage': sampled_montage.unslice().lossless()})
item_size = row_length * rows_per_item
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'
})
[montage_table] = db.run(output=output, jobs=[job], force=True)
# Stack all partial montages together
montage_img = np.zeros((1, target_width * row_length, 3), dtype=np.uint8)
for img in montage_table.column('montage').load():
img = np.flip(img, 2)
montage_img = np.vstack((montage_img, img))
print('')
print('Time: {:.1f}s'.format(time.time() - s))
############ ############ ############ ############
# 4. Write montage to disk
############ ############ ############ ############
cv2.imwrite('shots.jpg', montage_img)
print('Successfully generated shots.jpg')
print('Total time: {:.2f} s'.format(time.time() - total_start))
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)))
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)))
return frame
if len(sys.argv) <= 1:
print('Usage: main.py <video_file>')
exit(1)
movie_path = sys.argv[1]
print('Detecting poses in video {}'.format(movie_path))
movie_name = os.path.splitext(os.path.basename(movie_path))[0]
db = Database()
video_path = movie_path
if not db.has_table(movie_name):
print('Ingesting video into Scanner ...')
db.ingest_videos([(movie_name, video_path)], force=True)
input_table = db.table(movie_name)
sampler = db.streams.Range
sampler_args = {'start': 120, 'end': 480}
[poses_table] = pipelines.detect_poses(db, [input_table.column('frame')],
sampler, sampler_args,
'{:s}_poses'.format(movie_name))
print('Drawing on frames...')
frame = db.sources.FrameColumn()
sampled_frame = sampler(frame)
poses = db.sources.Column()
drawn_frame = db.ops.PoseDraw(frame=sampled_frame, poses=poses)
output = db.sinks.Column(columns={'frame': drawn_frame})
import subprocess
import cv2
import sys
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/../..')
import util
import numpy as np
util.download_video()
db = Database()
video_path = util.download_video()
if True or not db.has_table('example'):
print('Ingesting video into Scanner ...')
db.ingest_videos([('example', video_path)], force=True)
input_table = db.table('example')
descriptor = NetDescriptor.from_file(db, 'nets/faster_rcnn_coco.toml')
caffe_args = db.protobufs.CaffeArgs()
caffe_args.net_descriptor.CopyFrom(descriptor.as_proto())
caffe_args.batch_size = 1
frame = db.ops.FrameInput()
caffe_frame = db.ops.CaffeInput(frame=frame,
args=caffe_args,
device=DeviceType.CPU)
cls_prob, rois, fc7 = db.ops.FasterRCNN(caffe_input=caffe_frame,
args=caffe_args,
device=DeviceType.GPU)
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)
frame = db.sources.FrameColumn()
# We know that there are scene change at frames 5100, 5400, and 5730, To tell
# scanner that we do not want background subtraction to cross these boundaries,
# we can create a 'partitioner' which splits the input. For demonstration, we
# are going to split into only two sequences (5100, 5350) and (5400, 5830).
scene_partitions = db.partitioner.ranges([(5100, 5350), (5400, 5830)])
# Since the second sequence (5400, 5830) has a scene change in it at frame 5730,
# we will see smearing in the output video.
# Now we slice the input frame sequence into these two partitions using a
# slice operation
sliced_frame = db.streams.Slice(frame, partitioner=scene_partitions)
import sys
import os.path
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
import util
################################################################################
# This tutorial provides an overview of the more advanced features of Scanner #
# ops and when you would want to use them. #
################################################################################
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
# This file shows a sample end-to-end pipeline that ingests a video into #
# Scanner, runs a computation, and extracts the results. #
################################################################################
# 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()
[input_table
], failed = db.ingest_videos([('example', 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)
# result = np.dstack((template, template, template))*255
out = rgb.astype(np.uint8)
return out
movie_path = '/home/krematas/Mountpoints/grail/data/barcelona/test.mp4'
print('Detecting faces in movie {}'.format(movie_path))
movie_name = os.path.splitext(os.path.basename(movie_path))[0]
mask_path = '/home/krematas/Mountpoints/grail/data/barcelona/mask.mp4'
db = Database()
print('Ingesting video into Scanner ...')
input_tables, failed = db.ingest_videos([(movie_name, movie_path), ('mask', mask_path)], force=True)
print(db.summarize())
print('Failures:', failed)
cam_data = np.load('/home/krematas/Mountpoints/grail/data/barcelona/calib/00114.npy').item()
# db.register_op('Calibrate', [('frame', ColumnType.Video), ('mask', ColumnType.Video)], [('resized', ColumnType.Video)])
# Custom Python kernels for ops reside in a separate file, here calibrate_kernel.py.
# cwd = '/home/krematas/code/scanner/examples/apps/soccer'
# db.register_python_kernel('Calibrate', DeviceType.CPU, cwd + '/calibrate_kernel.py')
frame = db.sources.FrameColumn()
mask = db.sources.FrameColumn()
from scannerpy import Database, DeviceType, Job
from scannerpy.stdlib import parsers
import os.path as osp
import numpy as np
db = Database()
if not db.has_table('example'):
db.ingest_videos([('example', 'example.mp4')])
input_table = db.table('example')
frame, frame_info = input_table.as_op().all(warmup_size = 1)
flow = db.ops.OpticalFlow(
frame = frame, frame_info = frame_info,
device=DeviceType.GPU)
job = Job(columns = [flow, frame_info], name = 'example_flows')
output_table = db.run(job)
vid_flows = [flow for _, flow in output_table.load(['flow', 'frame_info'], parsers.flow)]
np.save('flows.npy', vid_flows)
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()
'--video-path',
type=str,
required=True,
help=('Path to video to process.'))
args = p.parse_args()
weights_path = args.weights_path
config_path = args.config_path
movie_path = args.video_path
print('Detecting objects in movie {}'.format(movie_path))
movie_name = os.path.splitext(os.path.basename(movie_path))[0]
db = Database()
[input_table], failed = db.ingest_videos(
[('example', movie_path)], force=True)
frame = db.sources.FrameColumn()
strided_frame = db.streams.Range(frame, 0, 60)
# Call the newly created object detect op
cls_boxes, cls_segms, cls_keyps = db.ops.Detectron(
frame=strided_frame,
config_path=config_path,
weights_path=weights_path,
device=DeviceType.GPU)
objdet_frame = db.ops.DetectronVizualize(
frame=strided_frame,
cls_boxes=cls_boxes,
cls_segms=cls_segms,
from scannerpy import Database, Job
db = Database()
# Ingest a video into the database
# The input is formatted as a list of (table_name, video_path).
db.ingest_videos([('sample-clip', 'sample-clip.mp4')], force=True)
# Define a Computation Graph
frame = db.sources.FrameColumn() # Read from the database
sampled_frame = db.streams.Stride(frame, 3) # Select every third frame
resized = db.ops.Resize(frame=sampled_frame, width=640,
height=480) # Resize input frame
output_frame = db.sinks.Column(columns={'frame':
resized}) # Save resized frame
# Bind arguments to the source and sink nodes
job = Job(
op_args={
frame: db.table(table_name).column(
'frame'), # Column to read input frames from
output_frame: 'resized-{:s}'.format(table_name) # Name of output table
})
# Execute the computation graph and return a handle to the newly produced tables
output_tables = db.run(output=output_frame, jobs=[job], force=True)
# Save the resized video as an mp4 file
output_tables[0].column('frame').save_mp4(output_tables[0].name())
import os.path as osp
import numpy as np
import time
import sys
if len(sys.argv) <= 1:
print('Usage: main.py <video_file>')
exit(1)
video_path = sys.argv[1]
print('Performing optical flow on {}...'.format(video_path))
video_name = os.path.splitext(os.path.basename(video_path))[0]
db = Database()
if not db.has_table(video_name):
db.ingest_videos([(video_name, video_path)])
input_table = db.table(video_name)
frame = db.sources.FrameColumn()
flow = db.ops.OpticalFlow(
frame = frame,
device=DeviceType.CPU)
sampled_flow = db.streams.Range(flow, 0, 60)
output = db.sinks.Column(columns={'flow': sampled_flow})
job = Job(op_args={
frame: input_table.column('frame'),
output: input_table.name() + '_flow'
})
[output_table] = db.run(output=output, jobs=[job],
pipeline_instances_per_node=1, force=True)
image_paths = os.listdir(dir_name)
image_paths = [os.path.join(dir_name, p) for p in image_paths]
print('Ingesting images into Scanner ...')
[input_table] = pipelines.ingest_images(db,
image_paths,
dir_name,
force=True)
table_name = dir_name
elif os.path.isfile(sys.argv[1]):
is_movie = True
movie_path = sys.argv[1]
print('Detecting faces in movie {}'.format(movie_path))
movie_name = os.path.splitext(os.path.basename(movie_path))[0]
print('Ingesting video into Scanner ...')
[input_table], _ = db.ingest_videos([(movie_name, movie_path)],
force=True)
table_name = movie_name
else:
usage()
exit(1)
sampler = db.streams.All
sampler_args = {}
print('Detecting faces...')
[bboxes_table] = pipelines.detect_faces(db, [input_table.column('frame')],
sampler, sampler_args,
table_name + '_faces')
print('Drawing faces onto frames...')
frame = db.sources.FrameColumn()
