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.

OrCam, a company that makes products to aid accessibility for the visually impaired, has won a CES innovation award for its glasses-mounted MyEye Pro device. It aids the blind and visually impaired by reading out printed and digital text, recognizing people, identifying products, and more. OrCam took the prize in both the CES innovation accessibility and health and wellness categories. "We are living in uncertain times, yet... our users' challenges related to access have not stopped during the pandemic. If anything, they have intensified," said OrCam co-founder and co-chairman Prof. Amnon Shashua in OrCam's blog post.

I have been working as a volunteer with visually impaired people for years. On the past new year's eve, I went out with a blind lady familiar enough with her neighborhood after decades of living while she still need a pair of eyes in cases of unexpected obstacles on the sidewalks: abandoned Christmas tree after the festival, illegally parked cars, new worksites, etc. Unfortunately, we have fewer volunteers than needed and some blind people have thus to wait several times to have an accompanied walk. I have been thinking, therefore, how can I suggest a solution to help my visually impaired friends to identify obstacles when they come out alone with machine learning. I will now provide more details for the essential part of this project: the object recognition system with deep learning.

I have been working as a volunteer with visually impaired people for years. On the past new year's eve, I went out with a blind lady familiar enough with her neighborhood after decades of living while she still need a pair of eyes in cases of unexpected obstacles on the sidewalks: abandoned Christmas tree after the festival, illegally parked cars, new worksites, etc. Unfortunately, we have fewer volunteers than needed and some blind people have thus to wait several times to have an accompanied walk. I have been thinking, therefore, how can I suggest a solution to help my visually impaired friends to identify obstacles when they come out alone with machine learning. I will now provide more details for the essential part of this project: the object recognition system with deep learning.

Researchers at Stanford University have developed a robotic'smart' cane that guides people with visual impairments using technology originated for autonomous vehicles. Most sensor canes use ultrasound to notify a user that there's some object directly in front of or above them. But the team at Stanford's Intelligent Systems Laboratory equipped their augmented cane with a LIDAR sensor, a laser-based technology used in some self-driving cars to measure the distance of nearby obstacles. The cane also incorporates smartphone-style GPS, accelerometers, magnetometers, and gyroscopes to monitor a user's position, orientation, speed and direction. A motorized, omnidirectional wheel on the bottom tip maintains contact with the ground and gently tugs and nudges users around impediments.

Google has announced the development of its new Android application'Lookout' with the motive to help blind and visually impaired people, assisting them to learn about their surroundings. The app will be available to the Play Store in the US this year and will aid visually impaired by giving auditory cues as they encounter objects, text, and people around them. After opening the app, and selecting a mode, Lookout processes items of importance in your environment and shares information it believes to be relevant--text from a recipe book, or the location of a bathroom, an exit sign, a chair or a person nearby Lookout delivers spoken notifications, designed to be used with minimal interaction allowing people to stay engaged with their activity. There are over 253 million blind or visually impaired people in the world. To make the world more accessible to them, we need to build tools that can work with the ever-changing environment around us, the company blogged.

"A collection of smart devices may not make you smarter. There seems to be a gap between what technology has to offer and what we are naturally able to do" Suranga Nanayakkara slips a black ring onto his finger and points. This ring, he explains, helps visually impaired people read by converting text into speech. Nanayakkara points at a poster on the wall more than a metre away, clicks a small button on the side of the ring, and almost instantaneously a female voice starts reading out the poster's header through the headphones he's wearing. Such optical character recognition technology, or OCR, already exists but is often locked inside clunky highlighter-style devices that are slow and cumbersome.

Self-driving cars could revolutionize how disabled people get around their communities and even travel far from home. People who can't see well or with physical or mental difficulties that prevent them from driving safely often rely on others – or local government or nonprofit agencies – to help them get around. Autonomous vehicle technology on its own is not enough to help these people become more independent, but simultaneous advances in machine learning and artificial intelligence can enable these vehicles to understand spoken instructions, observe nearby surroundings and communicate with people. An autonomous shuttle by Texas A&M University can create profiles with information on passengers' disabilities and communications preferences, as well as any frequent destinations. An autonomous shuttle, being developed by Texas A&M University, can be a solution for problems associated with access and funding to transportation for disabled people.

When Anne Taylor walks into a room, she wants to know the same things that any person would. Where is there an empty seat? Who is walking up to me, and is that person smiling or frowning? What does that sign say? For Taylor, who is blind, there aren't always easy ways to get this information. Perhaps another person can direct her to her seat, describe her surroundings or make an introduction.

When Anne Taylor walks into a room, she wants to know the same things that any person would. Where is there an empty seat? Who is walking up to me, and is that person smiling or frowning? What does that sign say? For Taylor, who is blind, there aren't always easy ways to get this information. Perhaps another person can direct her to her seat, describe her surroundings or make an introduction.