PPE-Detection / README.md
qc903113684's picture
Update README.md
55aacaa verified
metadata
license: other
license_name: aplux-model-farm-license
license_link: https://aiot.aidlux.com/api/v1/files/license/model_farm_license_en.pdf
pipeline_tag: object-detection
tags:
  - AIoT
  - QNN

PPE-Detection: Object Detection

PPE-Detection (Personal Protective Equipment Detection) is a computer vision-based technology designed to automatically identify whether personnel are wearing essential safety gear, such as helmets, reflective vests, goggles, masks, and gloves. Using deep learning algorithms (e.g., YOLO, Faster R-CNN), this technology enables real-time detection and classification of safety equipment in high-risk environments like construction sites, factories, and healthcare facilities, significantly reducing occupational hazards. The system analyzes data from cameras or drones, integrating object detection and semantic segmentation to pinpoint non-compliant behaviors and trigger immediate alerts. Key challenges include handling occlusions in complex scenarios, multi-scale object recognition, and optimizing cross-device deployment. With advancements in edge computing and lightweight models, PPE-Detection is evolving toward cost-effective, intelligent safety management solutions, enhancing compliance and operational safety standards globally.

Source model

  • Input shape: 1x3x320x192
  • Number of parameters: 5.92M
  • Model size: 23.64M
  • Output shape: [1x21x40x24],[1x21x20x12],[1x21x10x6]

The source model can be found here

Performance Reference

Please search model by model name in Model Farm

Inference & Model Conversion

Please search model by model name in Model Farm

License