robert80203/EgoPER_official

The official implementation of Error Detection in Egocentric Procedural Task Videos

31
/ 100
Emerging

This project helps researchers and scientists automatically detect errors in first-person procedural task videos, like someone assembling furniture or performing a lab experiment. It takes in raw video footage and detailed annotations of the task steps and objects, and outputs identified errors in the procedure. This is useful for anyone studying human performance, training, or task analysis in fields like human-computer interaction or cognitive science.

No commits in the last 6 months.

Use this if you are analyzing video recordings of people performing a series of steps and need to automatically flag when a mistake or deviation from the correct procedure occurs.

Not ideal if your videos are not first-person (egocentric) or if you lack detailed annotations describing each step and object involved in the task.

human-computer-interaction task-analysis procedural-training video-analysis egocentric-vision
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

22

Forks

5

Language

Python

License

Last pushed

Sep 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/robert80203/EgoPER_official"

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