nomad86

Thx! Downloading all the photos took the most time. Object detection process took only several days.

At TripOffice, we use simple and widely-used tools: Python, NextJS, and MySQL.

Thx, see here: https://docs.mapbox.com/mapbox-gl-js/example/cluster/

I use MapBox, but similar things can also be done on Google Maps.

It reminded me of how, a long time ago, FPGAs were used in Bitcoin mining.

I haven't checked it, but such data should be easy to get from our database.

We manually labeled almost 1,000 chairs in various photos to train the model.

At first I wanted to use Google's Vertex AI for this purpose, but the costs were too high.

Besides, in this case, we would also have to upload 40 million photos to the cloud for Google to evaluate what’s on them.

YOLO is the best for such tasks; it works locally and is really fast.

This is not scraping. Many hotel sites share photos with their partners, we work with Lexyl (HotelPlanner).

All major booking sites share hotel photos with their partners.

We are in several partner programs, but now we mainly work with HotelPlanner.

I tried to detect models of specific chairs, but it's very difficult. To train the AI model, you need many photos of the same type of chair, and on the internet, you can usually find only one stock photo of each chair.

I created an app similar to Tinder that facilitates manual verification. Around 60 photos can be verified in one minute. The whole process took about a week and didn't cost much.

I don't know, I assigned this task to trusted specialists from India.

In our hotel photo database, we have everything: rooms, lobbies, bathrooms, pools, exterior shots of buildings, etc.

I trained an AI to recognize ergonomic chairs, but sometimes there were errors. For example, a chair in a hotel's SPA was always identified as an ergonomic chair. That's why we manually reviewed all 50k photos to verify them.

I'm building a hotel reservation system on tripoffice.com

Why?

Demo is always better than the real product. We'll soon see how it works...

Yes, Airbnb Killer is registered in Poland, EU

We trained the AI model mainly on Herman Miller and Ergohuman chairs. Unfortunately for AI, a cheap chair on wheels is 95% ergonomic.

Yes, that's why we trained our model only on ergonomic chairs

The map will be ready in a few weeks, now we are manually checking what AI has found and removing all the kitchen tables and chairs.

Our AI (yolo5) can only detect an ergonomic chair. Distinguishing a desk from a kitchen table with AI is probably impossible today.

We can't detect a monitor yet either, because it looks the same as a TV.

AI works great for us only in marketing