About SightSpace and how to take part

This page is written in text only, with no images or tables, so that it can be read aloud by a screen reader. You can move through it heading by heading.

1. Who we are

SightSpace is a non-profit organization that helps blind and low-vision people get around in everyday life, with AI glasses.

We build software that confirms, in Korean, whether the entrance, sign or bus the glasses see matches where you are going. We also teach people how to use the glasses. It is run by co-founders Jinseorang Madison Chung and Juyeon Lee, who both studied architecture at Hongik University.

Built with blind people

Sido, a blind creator (@hello_sido_), continuously contributes feature feedback and co-creates content with us, and about 10 other blind people cooperate in development. We have conducted more than 60 interviews to date.

Accessibility research staff at the National Museum of Modern and Contemporary Art, Korea told us that blind visitors need both a way to get to the museum and guidance within indoor spaces.

So our first tasks are doors and buses — detecting and guiding the moments of leaving where you are, travelling, and entering your destination.

Awards and selections

• Top Award, University IR Challenge — 2026 Innovative Small Business Final Audition, Minister of SMEs and Startups Award
• Selected, 2026 Challenge Track — Asan Nonprofit Startup, Asan Nanum Foundation
• Selected, CES 2027 Eureka Park, Changwon National University pavilion
• Top Award, Hongik Startup Festival 2026, Startup Idea category
• Selected, U300+ Promising Student Startup Teams
• Top 40, Student Startup Festa
• First-round finalist, AI ROOKIE 2026, National AI Competition
• Exhibitor, AI FESTA 2026, Oct 6–8, COEX Seoul
• Feasibility Award, APEC Sustainable Social Entrepreneurship Training 2026, Co-founder Jinseorang Madison Chung · Aug 25–27, 2026, Seoul

2. Why we do this

Map apps tell you where to go, and the white cane handles how to walk safely. In between, the last few metres where map apps stop are left empty.

Is this door the place I was looking for? Is the bus pulling in the one I need? Today that check is made by asking whoever is nearby. We are building AI glasses that take on that moment.

3. What we are building

First, finding doors. Once you reach a building, it checks whether the entrance, sign or marker in front of you matches the place you were looking for.

Second, catching buses. It checks whether the bus pulling into the stop is the one you need. Our first task is detecting and guiding the moments of leaving where you are, travelling, and entering your destination.

The work comes in three steps. Confirm: check it matches the destination. Align: if it does, turn you toward it. Hand off: when the AI is not sure, or a person's help is needed, connect you to a place or a person who can help. When it is not certain, it holds and looks again rather than saying something wrong.

Why glasses: one hand holds a white cane and the other rests on a wall or a companion, so there is no hand left for a phone. Glasses need no hands, and they work together with AI.

An ophthalmologist reviews our work so that we make no unsound medical assumptions, and a professor of architecture and a practicing architect review it so that our judgements about space hold up on site.

How we build it

An ordinary scene-description app looks at one photograph and writes a sentence. We do four more things.

We read space, not scenes. It is closer to drawing a map of the space than to turning a photograph into prose.

The path you walked stays. Come back to the same space a second time, and it does not behave as if it were the first.

The same fact, differently for each person. The same fact can be information to one person and noise to another.

It learns when not to speak. In a 300-second clip, 601 moments could have been spoken. Fourteen were.

It also runs on the device with no internet connection. It works in underground passages and inside buildings where the signal is weak, and the recorded video never leaves the device.

4. How to take part

What matters most is not the technology, but what the people who will actually use it have to say.

Who we are looking for

Totally blind, low vision, late blindness, congenital blindness. Any of these is welcome. It is fine if you have never worn AI glasses. Where catching a bus alone, or finding the entrance of a building you have never been to, gets hard: that is what we most want to hear.

5. Apply and enquire

Reach us by phone, text message, or email, whichever is easiest. Leave your name, a contact, and a time that suits you, and we will get back to you.

Our phone number is +82 10-4345-6603.

Our email address is jsrjung@g.hongik.ac.kr. That is j s r j u n g, at, g, dot, hongik, dot, a c, dot, k r.

If anything here is wrong or awkwardly put, please tell us. Fixing things is what we do best.

Jinseorang Madison Chung and Juyeon Lee, Co-founders, SightSpace