This is pretty cool; however this account has been repeatedly posting this same story since 2023 and never anything else... weird
Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
61–70 of 129 posts
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#62Earlier quoted context omitted.
Perceptual hashes are very good for that, maybe with some adjustments for mirrored images and some crops
Can use dhash that is more robusts to compression, crops and color changes. Mainly look at the features in the image.
The README explicitly says it's not good for crops, and from the algorithm description it can't be. Or is there another thing called dhash with a different algorithm? https://github.com/benhoyt/dhash. https://github.com/Rayraegah/dhash is similar but horizontal only.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#63You posted this in 2023 too. Thought it sounded familiar!
All 8 of their submissions are versions of it: https://news.ycombinator.com/submitted?id=nomad86
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#64From a few minutes of clicking around, most of these "office chairs" look entirely unsuitable for longer periods of work. I've also never seen a hotel room without at least a basic "school chair" and those are far more comfortable than a lot of the plastic slab or designer clamshell things I see in these photos.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#65How much did you end up spending?
They did it on their own computer. https://github.com/ultralytics/ultralytics
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#66Earlier quoted context omitted.
I don't know, I assigned this task to trusted specialists from India.
Wow, manually reviewing 50k photos is a lot! Would you be willing to share what the cost of that was?
Doesn't sound that much. When I was playing with datasets, for simple tasks I only took around 3 seconds to classify an image. That's 1200/hour or on the order of 40 hours of work. That can't cost much when outsourced.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#67Earlier quoted context omitted.
They know what they’re doing. Most hotels ‘are’ built for work, but they’re built for what most workers use them for: work travel . Though probably common for developers, I’ll bet it’s pretty unusual for the other like 96% of people to want to do deep work in a hotel room. Especially if you’re on the road for work, you’re probably the sort of worker that needs to physically be somewhere remote to accomplish a goal, w…
Hanlon's Razor I think there's a simpler explanation: most people don't do work when they go to hotels, they do the work like you are discussing. Doesn't mean they are intentionally being hostile to remote workers. One thing I've realized about the world is that a lot of people do things just because others are. "Momentum is a bitch." I will bet you very few people are thinking this way, at least very few that make d…
> There was a LTT video where they mentioned how WiFi used to be better in some locations so those rooms were more desirable and the hotel's solution was to make it standard for everyone. They seemed to be suggesting that they brought down the quality rather than balanced.
This was from their podcast 'WAN Show' a week or two back, specifically about hotels in Las Vegas.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#68Why stop at just office chairs? Why not detect all categorizable objects in every photo and rank based on that? Could also crop just the object detection regions of each image, run those cropped images through CLIP/SigLIP, then UMAP and HDBSCAN to view a 2 or 3 dimensional latent space clustering of office chair types.. might reveal some info as to what kinds of chairs exist in what geographical regions. Could use a…
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.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#69I've checked locally. Most of these aren't really hotels, but short term rentals.
I don't have an huge issue with short term rentals per si. They are an important niche for tourism when you take the whole family, whereas most (esp. city) hotels are not really appropriate for a family of 4 or 5.
OTOH, (esp. city) hotels are usually fine for the business trips they were designed to cater too.
This leaves us with “digital nomads.” Helping these find ways to put additional pressure on the housing market through short term rentals will only cause locals to get politicians to further restrict them.
Re: Show HN: Using YOLO to Detect Office Chairs in 40M Hotel Photos
#70What I'm most curious about is how does one get 40 million hotel photos? Is this offered through some Booking.com API etc.?
I was also wondering this. The hardest part about this would be scraping 40m photos.
All major booking sites share hotel photos with their partners.
We are in several partner programs, but now we mainly work with HotelPlanner.