> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Detect scene changes in videos
> Detect scene cuts and shot boundaries in videos using Pixeltable to split footage into segments for indexing, summarization, and editing.
This documentation page is also available as an interactive notebook. You can launch the notebook in
Kaggle or Colab, or download it for use with an IDE or local Jupyter installation, by clicking one of the
above links.
export const quartoRawHtml = [`
| Use case |
Goal |
| Video editing |
Find cut points automatically |
| Content analysis |
Segment videos into scenes |
| Thumbnail generation |
Extract one frame per scene |
| Clip extraction |
Split videos at scene boundaries |
| Ad detection |
Find commercial breaks |
`, `
| title |
scenes_content |
| Sample video 1 |
[{"duration": 25.692, "start_pts": 0, "start_time": 0.}] |
`, `
| title |
scenes_fade |
| Sample video 1 |
[{"duration": 25.692, "start_pts": 0, "start_time": 0.}] |
`, `
| title |
scenes_adaptive |
| Sample video 1 |
[{"duration": 25.526, "start_pts": 0, "start_time": 0.}] |
`, `
| Method |
Best for |
Key parameter |
scene_detect_content() |
Hard cuts |
threshold (27 default) |
scene_detect_threshold() |
Fades |
threshold (12 default) |
scene_detect_adaptive() |
Mixed content |
adaptive_threshold (3 default) |
`, `
| Goal |
Adjustment |
| More scenes |
Lower threshold values |
| Fewer scenes |
Higher threshold values |
| Faster processing |
Set fps=1.0 or fps=2.0 |
| Ignore quick cuts |
Increase min_scene_len |
`];
Automatically find scene cuts, transitions, and fades in video files.
## Problem
You have video files and need to identify scene boundaries for:
## Solution
**What’s in this recipe:**
* Detect hard cuts with `scene_detect_content()`
* Find fade transitions with `scene_detect_threshold()`
* Use adaptive detection with `scene_detect_adaptive()`
Three built-in detection methods handle different transition types using
PySceneDetect.
### Setup
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
%pip install -qU pixeltable scenedetect opencv-python
```
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import pixeltable as pxt
# Create a fresh directory
pxt.drop_dir('scene_demo', force=True)
pxt.create_dir('scene_demo')
```
Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/pjlb/.pixeltable/pgdata
Created directory 'scene\_demo'.
\
### Load sample videos
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Create a video table
videos = pxt.create_table(
'scene_demo/videos', {'video': pxt.Video, 'title': pxt.String}
)
# Insert sample videos from S3
videos.insert(
[
{
'video': 's3://multimedia-commons/data/videos/mp4/ffe/ffb/ffeffbef41bbc269810b2a1a888de.mp4',
'title': 'Sample video 1',
}
]
)
```
Created table 'videos'.
Inserting rows into \`videos\`: 1 rows \[00:00, 200.53 rows/s]
Inserted 1 row with 0 errors.
1 row inserted, 3 values computed.
### Detect scenes with content-based detection
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Detect scenes using content-based detection (best for hard cuts)
videos.add_computed_column(
scenes_content=videos.video.scene_detect_content(
threshold=27.0, # Lower = more sensitive
min_scene_len=15, # Minimum frames between cuts
)
)
# View detected scenes
videos.select(videos.title, videos.scenes_content).collect()
```
Added 1 column value with 0 errors.
### Detect fade transitions
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Detect fade-to-black/white transitions
videos.add_computed_column(
scenes_fade=videos.video.scene_detect_threshold(
threshold=12.0, # Brightness threshold for fades
min_scene_len=15,
)
)
# View fade-detected scenes
videos.select(videos.title, videos.scenes_fade).collect()
```
Added 1 column value with 0 errors.
### Adaptive detection for complex videos
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Adaptive detection adjusts to video content dynamically
videos.add_computed_column(
scenes_adaptive=videos.video.scene_detect_adaptive(
adaptive_threshold=3.0, # Lower = more scenes detected
min_scene_len=15,
fps=2.0, # Analyze at 2 FPS for speed
)
)
# View adaptively-detected scenes
videos.select(videos.title, videos.scenes_adaptive).collect()
```
Added 1 column value with 0 errors.
## Explanation
**Detection methods:**
**Output format:**
Each method returns a list of scene dictionaries:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
{
'start_time': 5.2, # Scene start in seconds
'start_pts': 156, # Presentation timestamp
'duration': 3.8 # Scene duration in seconds
}
```
**Tuning tips:**
## See also
* [Extract frames from
videos](/howto/cookbooks/video/video-extract-frames) -
Get frames at scene boundaries
* [Generate
thumbnails](/howto/cookbooks/video/video-generate-thumbnails) -
Create preview images