A Large Vision-Language Model based Environment Perception System for Visually Impaired People
This addresses the problem of limited personal and social activities for visually impaired people by enhancing their ability to perceive complex natural scenes, though it appears incremental as it builds on existing LVLM and segmentation methods.
The paper tackles the challenge of environment perception for visually impaired people by introducing a Large Vision-Language Model (LVLM) based system that uses a wearable device to capture scenes and provide descriptions, with technical experiments showing it provides more accurate scene descriptions compared to Qwen-VL-Chat.
It is a challenging task for visually impaired people to perceive their surrounding environment due to the complexity of the natural scenes. Their personal and social activities are thus highly limited. This paper introduces a Large Vision-Language Model(LVLM) based environment perception system which helps them to better understand the surrounding environment, by capturing the current scene they face with a wearable device, and then letting them retrieve the analysis results through the device. The visually impaired people could acquire a global description of the scene by long pressing the screen to activate the LVLM output, retrieve the categories of the objects in the scene resulting from a segmentation model by tapping or swiping the screen, and get a detailed description of the objects they are interested in by double-tapping the screen. To help visually impaired people more accurately perceive the world, this paper proposes incorporating the segmentation result of the RGB image as external knowledge into the input of LVLM to reduce the LVLM's hallucination. Technical experiments on POPE, MME and LLaVA-QA90 show that the system could provide a more accurate description of the scene compared to Qwen-VL-Chat, exploratory experiments show that the system helps visually impaired people to perceive the surrounding environment effectively.