SocialDistance
Keep safe social distance is considered as an effective way of avoiding spreading of coronavirus. Our SocialDistance module SDD is a lightweight package which provides an implementation of utlizing deep learning models for monitoring safe social distance.
Demo
Dataset
We use the video clip collected from OXFORD TOWN CENTRE dataset and made the above demo video.
Supported Models
We have tested our model using YOLO-v3 and SSD, based on the performance of each model, we have chosen YOLO-v3 as our default model
All our pretrained models are selected from Gluno CV Tookit
Installation
You may be able to obtain the latest version our model from:
pip install SDD
How to Use
After Successfully installed SocialDistance, you can use it for detection by:
import SDD
import mxnet as mx
from SDD.utils.Run import Detect
detect = Detect(pretrained_models = 'yolo_v3')
detector = detect(save_path = output_path_image, video = False, device = mx.cpu())
_ = detector(file_path)
Parameters
- pretrained_models: str, Currently, we provided two pretrained models: 'yolo_v3' and 'ssd'
- save_path: str, Path where you want to save the output video/ images
- video: boolean, If your input is a video, set this parameter as True, if your input is a set of images, set this parameter as False
- device: mx.cpu() or mx.gpu()
- file_path: str, Input path of your video or image folder
Reference
- Landing AI 16 April 2020, Landing AI Creates an AI Tool to Help Customers Monitor Social Distancing in the Workplace, accessed 19 April 2020, https://landing.ai/landing-ai-creates-an-ai-tool-to-help-customers-monitor-social-distancing-in-the-workplace/
Metadata
Release files for SDD 0.2.2.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| SDD-0.2.2.7.tar.gz | 17.1 kB | Without provenance | Details for SDD-0.2.2.7.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| SDD-0.2.2.7-py3-none-any.whl | Python 3 | none | any | Details for SDD-0.2.2.7-py3-none-any.whl |
Total release size: 41.0 kB
Release files / SDD-0.2.2.7.tar.gz
| Download URL | SDD-0.2.2.7.tar.gz |
|---|---|
| Size | 17.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
500bafda67bb5127a5c15abe109d0bf3aedec3cc1fbfa7efd98bea071ecd110c
|
|
BLAKE2b-256 checksum How to use checksums |
ef0a8887c06c8a4720bdf562c09d16e0d54857721e73e338a12aa763882c0178
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.4.2 requests/2.22.0 setuptools/50.2.0 requests-toolbelt/0.9.1 tqdm/4.42.0 CPython/3.7.1
|
Release files / SDD-0.2.2.7-py3-none-any.whl
| Download URL | SDD-0.2.2.7-py3-none-any.whl |
|---|---|
| Size | 23.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c87a532015d8532e3d559157148abb95e15b7dc92509b13b8de4de3c418a4111
|
|
BLAKE2b-256 checksum How to use checksums |
95156a22ced6dc5fa6f561e9c11d25466bfaf9a36089790cf268f93c690e4f45
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.4.2 requests/2.22.0 setuptools/50.2.0 requests-toolbelt/0.9.1 tqdm/4.42.0 CPython/3.7.1
|
Security for SDD 0.2.2.7
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.