https://github.com/sarvesh30112002/gridhtm---anomaly-detection
This project explores the potential of the Hierarchical Temporal Memory (HTM) algorithm for this purpose, aiming to address challenges such as noise, concept drift, and unknown anomalies. We propose a specialized variant, "Grid HTM," designed to enhance video anomaly detection, making it more adaptive and reliable.
https://github.com/sarvesh30112002/gridhtm---anomaly-detection
grid gridhtm htm
Last synced: 2 months ago
JSON representation
This project explores the potential of the Hierarchical Temporal Memory (HTM) algorithm for this purpose, aiming to address challenges such as noise, concept drift, and unknown anomalies. We propose a specialized variant, "Grid HTM," designed to enhance video anomaly detection, making it more adaptive and reliable.
- Host: GitHub
- URL: https://github.com/sarvesh30112002/gridhtm---anomaly-detection
- Owner: Sarvesh30112002
- License: mit
- Created: 2023-11-24T15:40:51.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-11-24T15:57:26.000Z (over 2 years ago)
- Last Synced: 2025-01-20T00:53:43.245Z (over 1 year ago)
- Topics: grid, gridhtm, htm
- Language: Python
- Homepage:
- Size: 16.6 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# GridHTM---Anomaly-Detection
# Grid HTM - Used VIRAT Dataset
This repo depends on htm.core (https://github.com/htm-community/htm.core)
###Setup
To clone the repo and htm.core:
```commandline
git submodule update --init --recursive
```
To build and install htm.core, which requires cmake and more (see https://github.com/htm-community/htm.core):
(default)
```commandline
cd htm.core/
python setup.py install --user --force
```
(Anaconda)
```commandline
cd htm.core/
python setup.py install
```
### Running
To run:
```commandline
python main.py segmentedVideoFile settingsFile -o outputName
```
Where `segmentedVideoFile` is the path to a segmented video file (unless code is modified, it can only contain one class of objects) and
`settingsFile` is the path to a settings json file, see `surveillance_experiment_params.json` for an example.
`outputName` is the name of the resulting output files that are generated.
Help:
```commandline
python main.py -h
```