Hazard Detection in Supermarkets using Deep Learning on the Edge

Supermarkets need to ensure clean and safe environments for both shoppers and employees. Slips, trips, and falls can result in injuries that have a physical as well as financial cost. Timely detection of hazardous conditions such as spilled liquids or fallen items on supermarket floors can reduce th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-02
Main Authors: Sarwar Murshed, M G, Verenich, Edward, Carroll, James J, Khan, Nazar, Hussain, Faraz
Format: Article
Language:English
Subjects:
Deep learning
Floors
Inference
Injury prevention
Machine learning
Model accuracy
Object recognition
Supermarkets
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Supermarkets need to ensure clean and safe environments for both shoppers and employees. Slips, trips, and falls can result in injuries that have a physical as well as financial cost. Timely detection of hazardous conditions such as spilled liquids or fallen items on supermarket floors can reduce the chances of serious injuries. This paper presents EdgeLite, a novel, lightweight deep learning model for easy deployment and inference on resource-constrained devices. We describe the use of EdgeLite on two edge devices for detecting supermarket floor hazards. On a hazard detection dataset that we developed, EdgeLite, when deployed on edge devices, outperformed six state-of-the-art object detection models in terms of accuracy while having comparable memory usage and inference time.
ISSN:2331-8422