# njvisionpower/Safety-Helmet-Wearing-Dataset

Safety helmet wearing detect dataset, with pretrained model

Repository: https://github.com/njvisionpower/Safety-Helmet-Wearing-Dataset
Canonical: https://ross.abutalabs.com/products/safety-helmet-wearing-dataset
Language: Python
License: MIT
License Family: permissive
Topics: helmet, hardhat, dataset, detection, gluoncv
Last push: 2019-12-17T12:39:51+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2575, "days_push": 2451, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1720, forks 421 (observed 2026-08-28T04:05:26.709823+00:00)

## What it is
A labeled dataset (SHWD) of 7,581 images for detecting safety helmet (hardhat) wearing and human heads, annotated in Pascal VOC format. It also ships pretrained YOLO models (darknet, mobile1.0, mobile0.25) built with MXNet GluonCV for inference and training.

## Use cases
- detect whether workers are wearing safety helmets in images
- train an object detection model for hardhat and head detection
- get a Pascal VOC formatted dataset for head/helmet detection
- use pretrained YOLO models for construction site safety monitoring
- benchmark lightweight YOLO models on helmet detection
- fine-tune a detector on workplace safety compliance images

## When to choose
- you need labeled images of people with and without hardhats
- you want a quick pretrained model for helmet-wearing detection
- you work in the MXNet/GluonCV ecosystem and want VOC-format data
- you need a baseline dataset for construction or industrial safety vision tasks

## When to avoid
- you need video or real-time streaming safety monitoring out of the box
- you require a maintained project with active updates and support
- you work exclusively in PyTorch or TensorFlow and cannot use MXNet models
- you need large-scale or diverse datasets beyond ~7.5k images

## Facets
- artifact type: dataset
- maturity: maintenance
- function: computer-vision, machine-learning, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: object-detection, safety-helmet, pascal-voc, yolo, gluoncv, mxnet, pretrained-models, workplace-safety, gpu

## Member repositories
- njvisionpower/Safety-Helmet-Wearing-Dataset (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:26.709823+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:34:05.210597+00:00, confidence not recorded.
  - readme: https://github.com/njvisionpower/Safety-Helmet-Wearing-Dataset (fetched 2026-08-28T04:05:26.709823+00:00, sha b6cbe279450f)
- Data as of 2026-08-30T08:39:29.467469+00:00.