Photos | Urban Waste

A pile of discarded mattresses and cardboard boxes left on the busy street of San Francisco. Michael Tilson Thomas walks by with a group of people while cars and containers pass through the road.
BLIP-2 Description:
a pile of mattresses and boxes on the sidewalkMetadata
Capture date:
Original Dimensions:
3024w x 4032h - (download 4k)
Usage
Dominant Color:
Location:
continental civic sonson ca urban building fall footwear transportation sidewalk hat walkway trash states road outdoor furniture thai polk container listen francisco city shoe land bag street iphone cardboard listcn hardware no glasses time pc path united massage stopping electronics apple san car vehicle alley garbage screen max accessories monitor pro october laptop st soason civic center center michael tilson thomas california computer handbag symphony box
Detected Text
iso
125
metering mode
5
aperture
f/1.8
focal length
4mm
latitude
37.78
longitude
-122.42
shutter speed
1/120s
camera make
Apple
camera model
date
2019-10-18T17:48:00.258000-07:00
tzoffset
-25200
tzname
GMT-0700
overall
(39.31%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.57%)
failure
(-0.27%)
harmonious color
(1.10%)
immersiveness
(1.71%)
interaction
(1.00%)
interesting subject
(-45.87%)
intrusive object presence
(-2.91%)
lively color
(4.64%)
low light
(4.25%)
noise
(-1.37%)
pleasant camera tilt
(-6.76%)
pleasant composition
(-40.67%)
pleasant lighting
(-4.15%)
pleasant pattern
(12.13%)
pleasant perspective
(9.23%)
pleasant post processing
(0.98%)
pleasant reflection
(-9.16%)
pleasant symmetry
(1.59%)
sharply focused subject
(1.20%)
tastefully blurred
(-4.47%)
well chosen subject
(-22.94%)
well framed subject
(-10.04%)
well timed shot
(-1.47%)
all
(0.37%)
* NOTE: Amazon Rekognition
detected a celebrity in this image using the
Celebrity Recognition API. The API isn't perfect, but it does give you the MatchConfidence which I display
next to the celebrity's name along with links _↗ to their info.
* WARNING: The title and caption of this image were generated by an AI LLM (gpt-3.5-turbo-0301
from
OpenAI)
based on a
BLIP-2 image-to-text labeling, tags,
location,
people
and album metadata from the image and are
potentially inaccurate, often hilariously so. If you'd like me to adjust anything,
just reach out.