AI Video Copyright Detection

pip install videodb

import videodb

# Connect to VideoDB
api_key = "your_api_key"
conn = videodb.connect(api_key=api_key)
coll = conn.get_collection()

from videodb import SceneExtractionType, IndexType

# Upload your original videos
portfolio_videos = []
portfolio_videos.append(coll.upload(url="https://example.com/original-video-1.mp4"))
portfolio_videos.append(coll.upload(url="https://example.com/original-video-2.mp4"))

# Create scene indexes for all portfolio videos
portfolio_indexes = {}
for video in portfolio_videos:
    index_id = video.index_scenes(
        extraction_type=SceneExtractionType.shot_based,
        extraction_config={"threshold": 20}
    )
    portfolio_indexes[video.id] = index_id

# Upload the video you suspect is plagiarized
suspect_video = coll.upload(url="https://example.com/suspect-video.mp4")

# Create scene index for suspect video (shot-based for better detection)
suspect_index_id = suspect_video.index_scenes(
    extraction_type=SceneExtractionType.shot_based,
    extraction_config={"threshold": 20}
)

from videodb import IndexType

matches = []
similarity_threshold = 0.70

# Get suspect video scenes
suspect_scenes = suspect_video.get_scene_index(suspect_index_id)

for portfolio_vid_id, portfolio_index_id in portfolio_indexes.items():
    portfolio_video = coll.get_video(portfolio_vid_id)

    # Compare each suspect scene against portfolio
    for suspect_scene in suspect_scenes:
        # Use VideoDB's semantic search
        results = portfolio_video.search(
            query=suspect_scene['description'],
            search_type="semantic",
            index_type=IndexType.scene,
            index_id=portfolio_index_id
        )

        # Process results
        for shot in results.shots:
            if shot.search_score > similarity_threshold:
                matches.append({
                    "suspect_time": suspect_scene['start'],
                    "portfolio_video": portfolio_vid_id,
                    "portfolio_time": shot.start,
                    "similarity": shot.search_score
                })

# Sort by highest similarity
matches = sorted(matches, key=lambda x: x["similarity"], reverse=True)

# Check for sequential matching (stronger evidence)
sequential_matches = []
consecutive_count = 0
last_similarity = 0

for match in matches:
    if match["similarity"] > 0.80 and consecutive_count < 5:
        consecutive_count += 1
        sequential_matches.append(match)
    else:
        if consecutive_count >= 3:  # 3+ consecutive = strong evidence
            sequential_matches.extend(sequential_matches[-consecutive_count:])
        consecutive_count = 0

plagiarism_confidence = min(1.0, len(sequential_matches) / 10)

from videodb.editor import Timeline, Track, Clip, VideoAsset, Position, Fit

# Create side-by-side comparison timeline
timeline = Timeline(conn)

# Add matching segments side-by-side
for match in matches[:5]:  # Top 5 matches as evidence
    track = Track()

    # Portfolio video (left side)
    portfolio_asset = VideoAsset(
        id=match["portfolio_video"],
        start=match["portfolio_time"]
    )
    portfolio_clip = Clip(
        asset=portfolio_asset,
        duration=5,
        position=Position.left,
        fit=Fit.crop,
        scale=0.5
    )
    track.add_clip(0, portfolio_clip)

    # Suspect video (right side)
    suspect_asset = VideoAsset(
        id=suspect_video.id,
        start=match["suspect_time"]
    )
    suspect_clip = Clip(
        asset=suspect_asset,
        duration=5,
        position=Position.right,
        fit=Fit.crop,
        scale=0.5
    )
    track.add_clip(0, suspect_clip)

    timeline.add_track(track)

# Generate evidence video
evidence_stream_url = timeline.generate_stream()

# Create comprehensive report
report = {
    "suspect_video_id": suspect_video.id,
    "total_matches": len(matches),
    "sequential_matches": len(sequential_matches),
    "plagiarism_confidence": plagiarism_confidence,
    "high_confidence_matches": len([m for m in matches if m["similarity"] > 0.95]),
    "medium_confidence_matches": len([m for m in matches if 0.85 < m["similarity"] <= 0.95]),
    "evidence_video_url": evidence_stream_url,
    "timestamp": "2025-01-20T12:00:00Z"
}

# If confidence > 0.80, recommend DMCA takedown
if plagiarism_confidence > 0.80:
    report["recommendation"] = "STRONG PLAGIARISM DETECTED - Ready for DMCA takedown"
    report["action"] = "prepare_dmca_evidence"