pip install pixeltable label-studio label-studio-sdk torch transformers

import pixeltable as pxt
from pixeltable.iterators import FrameIterator
from pixeltable.functions.huggingface import detr_for_object_detection, detr_to_coco
from datetime import datetime

# Initialize app structure
pxt.drop_dir('annotation', force=True)
pxt.create_dir('annotation')

# Create base video table
videos = pxt.create_table(
    'annotation.videos',
    {
        'video': pxt.Video,
        'date': pxt.Timestamp
    },
    if_exists="ignore"
)

# Create frame extraction view
frames = pxt.create_view(
    'annotation.frames',
    videos,
    iterator=FrameIterator.create(
        video=videos.video,
        fps=0.25  # Extract 1 frame every 4 seconds
    )
)

# Add object detection for pre-annotations
frames.add_computed_column(
    detections=detr_for_object_detection(
        frames.frame,
        model_id='facebook/detr-resnet-50',
        threshold=0.95
    )
)

# Convert detections to COCO format for Label Studio
frames.add_computed_column(
    preannotations=detr_to_coco(frames.frame, frames.detections)
)

# Define Label Studio configurations
video_config = '''
<View>
  <Video name="video" value="$video"/>
  <Choices name="video-category" toName="video" showInLine="true">
    <Choice value="city"/>
    <Choice value="food"/>
    <Choice value="sports"/>
  </Choices>
</View>
'''

frame_config = '''
<View>
  <Image name="frame" value="$frame"/>
  <RectangleLabels name="preannotations" toName="frame">
    <Label value="car" background="blue"/>
    <Label value="person" background="red"/>
    <Label value="train" background="green"/>
  </RectangleLabels>
</View>
'''

# Create Label Studio projects
pxt.io.create_label_studio_project(
    videos,
    video_config,
    media_import_method='url'  # Recommended for production
)

pxt.io.create_label_studio_project(
    frames,
    frame_config,
    media_import_method='url'
)

import pixeltable as pxt
import os

# Set up Label Studio connection
if 'LABEL_STUDIO_URL' not in os.environ:
    os.environ['LABEL_STUDIO_URL'] = 'http://localhost:8080/'

# Connect to your tables
videos = pxt.get_table("annotation.videos")
frames = pxt.get_view("annotation.frames")

# Insert videos
url_prefix = 'http://multimedia-commons.s3-website-us-west-2.amazonaws.com/data/videos/mp4/'
video_files = [
    '122/8ff/1228ff94bf742242ee7c88e4769ad5d5.mp4',
    '2cf/a20/2cfa205eae979b31b1144abd9fa4e521.mp4'
]

videos.insert([{
    'video': url_prefix + file,
    'date': datetime.now()
} for file in video_files])

# Sync with Label Studio
videos.sync()
frames.sync()

# After annotation, retrieve results
results = videos.select(
    videos.video,
    videos.annotations,
    category=videos.annotations[0].result[0].value.choices[0]
).collect()

frame_results = frames.select(
    frames.frame,
    frames.annotations,
    frames.preannotations
).collect()