Small Object Detection for Indoor Assistance to the Blind using YOLO NAS Small and Super Gradients

TL;DR

This paper introduces a lightweight, real-time small object detection model optimized for indoor assistance to the blind, improving navigation by accurately identifying furniture and household items.

Contribution

It presents YOLO NAS Small, a novel small object detection architecture optimized with Super Gradients, tailored for assistive indoor navigation for the visually impaired.

Findings

Achieves high accuracy in small object detection

Enables real-time indoor navigation assistance

Demonstrates low latency suitable for assistive devices

Abstract

Advancements in object detection algorithms have opened new avenues for assistive technologies that cater to the needs of visually impaired individuals. This paper presents a novel approach for indoor assistance to the blind by addressing the challenge of small object detection. We propose a technique YOLO NAS Small architecture, a lightweight and efficient object detection model, optimized using the Super Gradients training framework. This combination enables real-time detection of small objects crucial for assisting the blind in navigating indoor environments, such as furniture, appliances, and household items. Proposed method emphasizes low latency and high accuracy, enabling timely and informative voice-based guidance to enhance the user's spatial awareness and interaction with their surroundings. The paper details the implementation, experimental results, and discusses the system's effectiveness in providing a practical solution for indoor assistance to the visually impaired.