# Real-Time Segmentation of Tactile Paving and Zebra Crossings for Visually Impaired Assistance Using Embedded Visual Sensors

## TL;DR

This paper presents a real-time system using embedded visual sensors to help visually impaired individuals by accurately identifying tactile paving and zebra crossings.

## Contribution

The novel contribution is an improved G-GhostNet backbone with a Coordinate Attention module and ASPP for efficient and accurate real-time segmentation on embedded devices.

## Key findings

- The proposed model achieves 97% mPA and 94% mIoU for tactile paving segmentation.
- It also achieves 93% mPA and 86% mIoU for zebra crossing segmentation with an inference speed of 59.2 fps.
- The model outperforms mainstream semantic segmentation networks in both accuracy and speed.

## Abstract

This study aims to address the safety and mobility challenges faced by visually impaired individuals. To this end, a lightweight, high-precision semantic segmentation network is proposed for scenes containing tactile paving and zebra crossings. The network is successfully deployed on an intelligent guide robot equipped with a high-definition camera and a Huawei Atlas 310 embedded computing platform. To enhance both real-time performance and segmentation accuracy on resource-constrained devices, an improved G-GhostNet backbone is designed for feature extraction. Specifically, it is combined with a depthwise separable convolution-based Coordinate Attention module and a redesigned Atrous Spatial Pyramid Pooling (ASPP) module to capture multi-scale contextual features. A dedicated decoder efficiently fuses multi-level features to refine segmentation of tactile paving and zebra crossings. Experimental results demonstrate that the proposed model achieves mPA of 97% and 93%, mIoU of 94% and 86% for tactile paving and zebra crossing segmentation, respectively, with an inference speed of 59.2 fps. These results significantly outperform several mainstream semantic segmentation networks, validating the effectiveness and practical value of the proposed method in embedded systems for visually impaired travel assistance.