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()
# Create a stored stream to represent the input video
input_stream = sp.NamedVideoStream(sc,
'sample-clip',
path='sample-clip.mp4')
# Define a Computation Graph
frames = sc.io.Input([input_stream])
sampled_frames = sc.streams.Stride(frames, [2]) # Select every other frame
resized_frames = sc.ops.Resize(frame=sampled_frames,
width=[640],
height=[480]) # Resize input frame
grayscale_frames = sc.ops.ConvertColor(frame=resized_frames,
conversion=['COLOR_RGB2GRAY'])
grayscale3_frames = sc.ops.CloneChannels(frame=grayscale_frames,
replications=3)
# Create a stored stream to represent the output video
output_stream = sp.NamedVideoStream(sc, 'sample-grayscale')
output = sc.io.Output(grayscale3_frames, [output_stream])
# Execute the computation graph
sc.run(output, sp.PerfParams.manual(50, 250))
# Save the resized video as an mp4 file
output_stream.save_mp4('sample-grayscale')
input_stream.delete(sc)
output_stream.delete(sc)
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():
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():
os.environ['PATH'] = os.environ['PATH'] + ":."
example_video_path = 'star_wars_heros.mp4'
''' Get the media locally '''
if not os.path.isfile(example_video_path):
print("File does not exist: %s" % example_video_path)
retcode = oscmd(
"wget https://storage.googleapis.com/scanner-data/tutorial_assets/star_wars_heros.mp4"
)
partlist = [example_video_path]
print('Connecting to Scanner database/client...')
db = scan.Client()
print(db.summarize())
db.load_op("/opt/scanner/examples/tutorials/resize_op/libresize_op.so",
"/opt/scanner/examples/tutorials/resize_op/resize_pb2.py")
instreamlist = []
outstreamlist = []
for fname in partlist:
if not os.path.isfile(fname):
print("Input file %s does not exist, skipping" % fname)
continue
bname = os.path.basename(fname)[:-4] # drop the suffix
instreamlist.append(scan.NamedVideoStream(db, bname, path=fname))
outfname = 'processed-%s-%s' % (humandate(time.time()), bname)
outstreamlist.append(scan.NamedVideoStream(db, outfname))
input_frames = db.io.Input(instreamlist)
''' Pipeline '''
resized_frames = db.ops.MyResize(frame=input_frames, width=640, height=480)
# face_frames = db.ops.MTCNNDetectFaces(frame=resized_frames)
# boxed_face_frames = db.ops.DrawBboxes(frame=resized_frames, bboxes=face_frames)
run_frames = resized_frames
output = db.io.Output(run_frames, outstreamlist)
db.run(output,
scan.PerfParams.estimate(),
cache_mode=scan.CacheMode.Ignore)
OUTDIR = "."
for output_stream in outstreamlist:
if os.path.isdir(OUTDIR):
sname = os.path.join(OUTDIR, output_stream.name())
print("Saving %s" % sname)
output_stream.save_mp4(sname)
print(db.summarize())
print('Complete!')
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():
# 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():
os.environ['KUBECONFIG'] = cmd0("ls -tr /root/.kube/config")
os.environ['PATH'] = os.environ['PATH'] + ":."
os.environ['AWS_ACCESS_KEY_ID'] = cmd0(
'grep aws_access_key_id /root/.aws/credentials|cut -f2 -d "="')
os.environ['AWS_SECRET_ACCESS_KEY'] = cmd0(
'grep aws_secret_access_key /root/.aws/credentials|cut -f2 -d "="')
example_video_path = '/efsc/star_wars_heros.mp4'
''' Get the media locally '''
if not os.path.isfile(example_video_path):
print("File does not exist: %s" % example_video_path)
retcode = oscmd(
"wget -P /efsc/ https://storage.googleapis.com/scanner-data/tutorial_assets/star_wars_heros.mp4"
)
partlist = [example_video_path]
print('Connecting to Scanner database/client...')
print('Finding master IP...')
ip = cmd0(
"kubectl get services scanner-master --output json | jq -r '.status.loadBalancer.ingress[0].hostname'"
)
port = cmd0(
"kubectl get svc/scanner-master -o json | jq '.spec.ports[0].port' -r")
master = '{}:{}'.format(ip, port)
print('Master ip: {:s}'.format(master))
with open('config.toml', 'w') as f:
config_text = cmds(
"kubectl get configmaps scanner-configmap -o json | jq '.data[\"config.toml\"]' -r"
)
f.write(config_text)
db = scan.Client(master=master,
start_cluster=False,
config_path='./config.toml',
grpc_timeout=60)
print(db.summarize())
db.load_op("/opt/scanner/examples/tutorials/resize_op/libresize_op.so",
"/opt/scanner/examples/tutorials/resize_op/resize_pb2.py")
instreamlist = []
outstreamlist = []
for fname in partlist:
if not os.path.isfile(fname):
print("Input file %s does not exist, skipping" % fname)
continue
bname = os.path.basename(fname)[:-4] # drop the suffix
instreamlist.append(scan.NamedVideoStream(db, bname, path=fname))
outfname = 'processed-%s-%s' % (humandate(time.time()), bname)
outstreamlist.append(scan.NamedVideoStream(db, outfname))
input_frames = db.io.Input(instreamlist)
''' Pipeline '''
resized_frames = db.ops.MyResize(frame=input_frames, width=640, height=480)
# sampled_frames = db.streams.Stride(resized_frames, [3])
# face_frames = db.ops.MTCNNDetectFaces(frame=sampled_frames)
# boxed_face_frames = db.ops.DrawBboxes(frame=sampled_frames, bboxes=face_frames)
run_frames = resized_frames
output = db.io.Output(run_frames, outstreamlist)
db.run(output,
scan.PerfParams.estimate(),
cache_mode=scan.CacheMode.Ignore)
OUTDIR = "."
for output_stream in outstreamlist:
if os.path.isdir(OUTDIR):
sname = os.path.join(OUTDIR, output_stream.name())
print("Saving %s" % sname)
output_stream.save_mp4(sname)
print(db.summarize())
print('Complete!')
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)))
def main():
if len(sys.argv) <= 1:
print('Usage: {:s} path/to/your/video/file.mp4'.format(sys.argv[0]))
sys.exit(1)
movie_path = sys.argv[1]
print('Detecting objects in movie {}'.format(movie_path))
movie_name = os.path.splitext(os.path.basename(movie_path))[0]
sc = sp.Client()
stride = 1
input_stream = sp.NamedVideoStream(sc, movie_name, path=movie_path)
frame = sc.io.Input([input_stream])
strided_frame = sc.streams.Stride(frame, [stride])
model_name = 'ssd_mobilenet_v1_coco_2017_11_17'
model_url = MODEL_TEMPLATE_URL.format(model_name)
objdet_frame = sc.ops.ObjDetect(
frame=strided_frame,
dnn_url=model_url,
device=sp.DeviceType.GPU if sc.has_gpu() else sp.DeviceType.CPU,
batch=2)
detect_stream = sp.NamedVideoStream(sc, movie_name + '_detect')
output_op = sc.io.Output(objdet_frame, [detect_stream])
sc.run(output_op,
sp.PerfParams.estimate(),
cache_mode=sp.CacheMode.Overwrite)
print('Extracting data from Scanner output...')
# bundled_data_list is a list of bundled_data
# bundled data format: [box position(x1 y1 x2 y2), box class, box score]
bundled_data_list = list(tqdm(detect_stream.load()))
print('Successfully extracted data from Scanner output!')
# run non-maximum suppression
bundled_np_list = kernels.nms_bulk(bundled_data_list)
bundled_np_list = kernels.smooth_box(bundled_np_list, min_score_thresh=0.5)
print('Writing frames to {:s}_obj_detect.mp4'.format(movie_name))
frame = sc.io.Input([input_stream])
bundled_data = sc.io.Input([PythonStream(bundled_np_list)])
strided_frame = sc.streams.Stride(frame, [stride])
drawn_frame = sc.ops.TFDrawBoxes(frame=strided_frame,
bundled_data=bundled_data,
min_score_thresh=0.5)
drawn_stream = sp.NamedVideoStream(sc, movie_name + '_drawn_frames')
output_op = sc.io.Output(drawn_frame, [drawn_stream])
sc.run(output_op,
sp.PerfParams.estimate(),
cache_mode=sp.CacheMode.Overwrite)
drawn_stream.save_mp4(movie_name + '_obj_detect')
input_stream.delete(sc)
detect_stream.delete(sc)
drawn_stream.delete(sc)
print('Successfully generated {:s}_obj_detect.mp4'.format(movie_name))
def main():
videos = []
# Keep track of the streams so we can delete them at the end
streams = []
sc = sp.Client()
example_video_path = util.download_video()
video_stream = sp.NamedVideoStream(sc, 'example', path=example_video_path)
streams.append(video_stream)
# 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.
@sp.register_python_op(device_type=sp.DeviceType.CPU)
def device_resize(config, frame: sp.FrameType) -> sp.FrameType:
return cv2.resize(frame, (config.args['width'], config.args['height']))
frames = sc.io.Input([video_stream])
resized_frames = sc.ops.device_resize(frame=frames, width=640, height=480)
stream = sp.NamedVideoStream(sc, 'example_resize')
streams.append(stream)
output = sc.io.Output(resized_frames, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.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.
@sp.register_python_op(batch=10)
def batch_resize(config,
frame: Sequence[sp.FrameType]) -> Sequence[sp.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 = sc.io.Input([video_stream])
resized_frame = sc.ops.batch_resize(frame=frame,
width=640,
height=480,
batch=10)
stream = sp.NamedVideoStream(sc, 'example_batch_resize')
streams.append(stream)
output = sc.io.Output(resized_frame, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.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.
@sp.register_python_op(stencil=[0, 1])
def optical_flow(config, frame: Sequence[sp.FrameType]) -> sp.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
@sp.register_python_op()
def visualize_flow(config, flow: sp.FrameType) -> sp.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
frames = sc.io.Input([video_stream])
# 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_frames = sc.streams.Range(frames, [(0, 30)])
flows = sc.ops.optical_flow(frame=range_frames, stencil=[0, 1])
flow_viz_frames = sc.ops.visualize_flow(flow=flows)
stream = sp.NamedVideoStream(sc, 'example_flow')
streams.append(stream)
output = sc.io.Output(flow_viz_frames, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.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
@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
# 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: 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
# 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.
frames = sc.io.Input([video_stream])
# We perform background subtraction and indicate we need 60 prior
# frames to produce correct output
masked_frames = sc.ops.BackgroundSubtraction(frame=frames,
alpha=0.05,
threshold=0.05,
bounded_state=60)
# Here, we say that we only want the outputs for this range of frames
sampled_frames = sc.streams.Range(masked_frames, [(0, 120)])
stream = sp.NamedVideoStream(sc, 'masked_video')
streams.append(stream)
output = sc.io.Output(sampled_frames, [stream])
sc.run(output, sp.PerfParams.estimate())
stream.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.
@sp.register_python_op(unbounded_state=True)
class Example(sp.Kernel):
def __init__(self, config):
pass
def reset(self):
pass
def execute(self, frame: sp.FrameType) -> bytes:
pass
for stream in streams:
stream.delete(sc)
print('Finished! The following videos were written: {:s}'.format(
', '.join(videos)))