[HN Gopher] Show HN: Weather Watching
       ___________________________________________________________________
        
       Show HN: Weather Watching
        
       I was walking around New York last month during some light rain and
       noticed about half the people had umbrellas open. When the rain
       picked up a few minutes later, that number jumped closer to 80%.
       It got me thinking it'd be cool to track this somehow, so I built a
       website! I am taking a sidewalk livestream, feeding it into a YOLO
       model for people tracking, then sending a frame of each detected
       person to Gemini 2.0 Flash, which returns structured JSON about
       each person's clothing and if they're holding an umbrella. I also
       had fun making the site look like a TV weather channel.  I showed
       some friends this project and someone mentioned how the legendary
       Tasks xkcd comic (https://xkcd.com/1425) is out of date now. If you
       want to check whether a photo has birds in it (or if someone is
       holding an umbrella), you can just ask an inexpensive vision model
       for JSON.
        
       Author : walz
       Score  : 80 points
       Date   : 2025-06-23 16:25 UTC (1 days ago)
        
 (HTM) web link (walzr.com)
 (TXT) w3m dump (walzr.com)
        
       | cgsmith wrote:
       | Pretty neat test of image recognition. I don't know why but it
       | bothers me to know that everyone everywhere is being watched by
       | something.
        
       | roxolotl wrote:
       | Wild that less than 15 years after Person of Interest it's so
       | cheap to build such a system we're using it to decide how to
       | dress for the day.
        
       | jackthetab wrote:
       | Cool. Do you have write-up of the technical details or a tutorial
       | on how you did this? I'm not familiar with the tech you mentioned
       | but it'd be interesting to see how it's done and so...easily?
       | cheaply? by non-mega-organizations?
        
         | scottmcdot wrote:
         | Yes please, would love this. Feel free to email me from
         | profile. Thanks
        
       | keyle wrote:
       | This is cute, I saw someone walk past and the information showed
       | what they were wearing correctly, or as correctly as can be.
       | 
       | For a while there I thought about recording cars driving in my
       | quiet street, by colour, make, try to categorise them... Never
       | got around to setting up the length needed for the camera cable
       | and a good weather proofing solution.
       | 
       | I didn't realise you could get Gemini to respond that fast. We
       | live in the science-fiction times.
       | 
       | What's amusing to me is that if a mugger was going to mug someone
       | in front of the camera, your system would happily report what
       | they're wearing, blissfully ignorant of the situation.
       | 
       | Consider open sourcing this mangled up solution!
        
       | okokwhatever wrote:
       | Who cares about privacy anymore, it's a lost battle this days.
        
         | 1970-01-01 wrote:
         | Filming a public street in NYC isn't pushing any limits.
        
         | tantalor wrote:
         | Say more about that.
         | 
         | What privacy standard is being broken here?
        
       | eber wrote:
       | I've kinda always wanted this.
       | 
       | I now luckily have a window that looks out into the city and I
       | use what other people are wearing as an indicator for what to
       | wear that day. Definitely helpful on the marginal days where it's
       | maybe shorts, maybe pants, maybe light jacket, maybe sweater-
       | weather. Temperature/wind/humidity tell most of the story, but
       | there's cloud cover, wind direction, morning-to-night temperature
       | swings, etc, that make the decision a bit more iffy.
       | 
       | Cool project! I may need to look into doing something similar.
        
       | dylan604 wrote:
       | Based on the position of the camera and current time of day, the
       | sun is over powering and the camera's exposure adjustment washes
       | out so much detail. If the system is able to determine the
       | information it is trying to discern from that image, I'm
       | impressed. You can't even tell what the sky looks like from this
       | image. I'd try hooding the lens to see if you could get a better
       | image when the sun is shining directly into the lens like this.
       | 
       | What would happen if someone geolocates your camera and just
       | plants a bunch of umbrellas in the frame? Does the counter
       | require the umbrella to be held by a human? What if the same
       | person walks past the camera multiple times? Are they considered
       | unique counts, or are you recognizing people and logging that?
       | 
       | TL;DR how robust is your system against mischievousness?
        
       | wiether wrote:
       | Love the idea and made me thought immediately of the song Coton
       | ouate from Bleu Jeans Bleu!
       | 
       | The song: https://www.youtube.com/watch?v=_whvVXX0hCk A
       | translation of the lyrics: https://lyricstranslate.com/en/coton-
       | ouate-sweater.html
        
       | ravdar wrote:
       | this is actually a brilliant idea. I can see it being available
       | in every city around the world in a couple of years
        
       | cryptozeus wrote:
       | Love the idea
        
       | icameron wrote:
       | Just shows what our assumptions are about attire and culture.
       | Short sleeves 75% and shorts are 62% currently, yet it's a record
       | high temperatures in NYC. (I know it's hotter in Saudi Arabia and
       | almost nobody wears shorts there.) The 2% umbrellas must be
       | misidentified parasols.
        
       | heeton wrote:
       | I tuned in, and immediately watched a guy wait for his dog to
       | shit, and then pick it up. The internet is a wonder.
        
       ___________________________________________________________________
       (page generated 2025-06-24 23:02 UTC)