aisingapore/PeekingDuck

A modular framework built to simplify Computer Vision inference workloads.

58
/ 100
Established

This tool helps Computer Vision engineers and data scientists quickly build and deploy real-time video analysis applications. You can feed it live camera footage or video files, and it outputs analyzed video streams with detections like objects, people's poses, or privacy-protected faces. It simplifies the setup of complex computer vision pipelines, allowing practitioners to focus on the insights rather than the infrastructure.

176 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to rapidly prototype or deploy computer vision solutions for tasks like security monitoring, retail analytics, or social distancing compliance, especially with live video feeds.

Not ideal if your primary goal is offline batch processing of images or if you require extremely fine-grained, low-level control over every aspect of a deep learning model's training and inference lifecycle.

video-analytics real-time-monitoring object-detection pose-estimation crowd-counting
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

176

Forks

44

Language

Python

License

Apache-2.0

Last pushed

Sep 04, 2025

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/aisingapore/PeekingDuck"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.