Hazard Detection in Supermarkets using Deep Learning on the Edge
This addresses the need for real-time hazard detection in supermarkets to enhance safety for shoppers and employees, though it appears incremental as it builds on existing object detection methods with optimizations for edge deployment.
The paper tackled the problem of detecting hazardous conditions like spills or fallen items on supermarket floors to prevent injuries, and presented EdgeLite, a lightweight deep learning model that outperformed six state-of-the-art object detection models in accuracy on a custom dataset while maintaining comparable memory usage and inference time on edge devices.
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.