Scholarlink

The highest percentage corresponding to people, with visual disabilities, are over 50 years old. In this context, the latest technology development have taken great importance in improving the quality of life of these people. Advanced technologies, like Convolutional Neuronal Network (CNN) and Proxemics Theory, can improve Human-Computer Interaction (HCI) to implement applications that respond to the distance, identity, location, movement, and orientation of objects and people that interact with digital devices. In this work, we demonstrate that the combination of CNN and Proxemics allows developing applications to help people with visual disabilities, estimating the distance and obtaining spatial information of detected objects that are on the path of a person. We implemented a mobile application able to detect objects based on the proposed CNN, as a proof of concept that can be extended to become a real mobile application for detecting obstacles to help people who need it.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Object Detection and Distance Estimation Using CNN and Proxemics: An Application for Visual Impaired People

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Miguel Ruiz-Adarmes,
  • Yudith Cardinale

摘要

The highest percentage corresponding to people, with visual disabilities, are over 50 years old. In this context, the latest technology development have taken great importance in improving the quality of life of these people. Advanced technologies, like Convolutional Neuronal Network (CNN) and Proxemics Theory, can improve Human-Computer Interaction (HCI) to implement applications that respond to the distance, identity, location, movement, and orientation of objects and people that interact with digital devices. In this work, we demonstrate that the combination of CNN and Proxemics allows developing applications to help people with visual disabilities, estimating the distance and obtaining spatial information of detected objects that are on the path of a person. We implemented a mobile application able to detect objects based on the proposed CNN, as a proof of concept that can be extended to become a real mobile application for detecting obstacles to help people who need it.