Skip to main content

Annotates activitiy episodes represented by meshes moving in a 3D environment with the corresponding events, actions and activities.

Project description

EpisodeSegmenter

A python library for segmenting simulation episodes of activities. This is done by detecting physical interactions, and events in the simulation. This library also integrates with NEEMPycramInterface to segment NEEM episodes as a use case.

Installation

pip install episode_segmenter

Example Usage

All below examples assume the neems are located in a 'test' database at 'localhost' which can be accessed by 'newuser' using password 'password'.

Replaying the motions of a NEEM and segmenting it:

This is done by using the PyCRAMNEEMInterface class which provides an easy way to replay the motions of a NEEM, then using the NEEMSegmenter class which implements EpisodeSegmenter to segment the motions into activities, actions, and events.

from neem_pycram_interface import PyCRAMNEEMInterface
from episode_segmenter.neem_segmenter import NEEMSegmenter

from pycram.datastructures.enums import WorldMode
from pycram.worlds.bullet_world import BulletWorld

BulletWorld(WorldMode.GUI)
pni = PyCRAMNEEMInterface('mysql+pymysql://newuser:password@localhost/test')
ns = NEEMSegmenter(pni, annotate_events=True)
ns.run_event_detectors_on_neem([15])

https://github.com/AbdelrhmanBassiouny/EpisodeSegmenter/assets/36744004/186bfd79-f30b-4b4f-ae84-03d2bcce821a

https://github.com/AbdelrhmanBassiouny/EpisodeSegmenter/assets/36744004/bb2e7c65-93cc-4f83-becb-1cb06fcf73ad

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

episode_segmenter-1.0.15.tar.gz (48.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

episode_segmenter-1.0.15-py3-none-any.whl (37.7 kB view details)

Uploaded Python 3

File details

Details for the file episode_segmenter-1.0.15.tar.gz.

File metadata

  • Download URL: episode_segmenter-1.0.15.tar.gz
  • Upload date:
  • Size: 48.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.0 CPython/3.12.5

File hashes

Hashes for episode_segmenter-1.0.15.tar.gz
Algorithm Hash digest
SHA256 ca9ad5f027e2b8e6d2b8a8c5dcb5656e855057332f999f691dfd610eb93aee67
MD5 6443c869c0755a6519e5029d57047ade
BLAKE2b-256 f25d4e5b5273a1077dee483cc143625cb8ebf708e5a5e70186513f1502af1940

See more details on using hashes here.

File details

Details for the file episode_segmenter-1.0.15-py3-none-any.whl.

File metadata

File hashes

Hashes for episode_segmenter-1.0.15-py3-none-any.whl
Algorithm Hash digest
SHA256 8ea1b1c4aaebf06fada84de77bbd151e9ba049331ba3962bec693f3c56fe9ea8
MD5 02187eecbb471e88cd50204702d560a0
BLAKE2b-256 4f2554b45be9eb3524dcf18423c780dc28aca628de93992a1c98617b70a5e2ee

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page