4.8
on G2
Count visits, vehicles, people passing or parts on a line, and see the frame behind every count. Ask for types, colours or behaviour, and get a tally you can check.
Every counted item is a finding with its own timestamp and frame, so the total is never a black box.
Vehicles entering, birds at a feeder, bundles leaving a line. Add attributes like colour, type or direction.
Tell white-tailed deer from fisher, cars from vans, or adult birds from juveniles, with the frame to confirm each.
Counts can be split by camera, and each finding can carry the camera's own date and time.
How it looks
Product captures from Docsie's test environment, October 2026, on CC BY footage and a screen recording generated for testing. No customer footage.
19 white-tailed deer sightings plus fisher, cottontail, opossum and fox, each with the date and time read off the image.
Open the screenshot to inspect the full detail.
Goldfinch visits to a feeder: 4 juvenile and 6 adult, each with its time and frame.
Open the screenshot to inspect the full detail.
Questions to ask
Real questions from our live-examples corpus, each paired with a public video. Results are published as Docsie produces them.
“Count the goldfinches in this feeder-cam video. For each clip, read the burned-in date and time, give the maximum number of birds on the feeder at once with the timestamp of that moment…” Source: Garden Birds Galore, CC BY.
“For each shot of people in this clean room footage of the JPSS-2 satellite solar array deployment, count the people and check whether each wears a full clean room suit: hood, face mask…” Source: NOAASatellites, CC BY.
“This drone footage follows a utility crew stringing three-phase wire along a rural road. In each scene, count the crew members, bucket trucks and wire reel trailers, note whether each crew…” Source: Pilot of the Countryside, CC BY.
“Estimate how many Paramecium cells are in the field of view in this phone-through-the-microscope video. Pick at least three moments, give their timestamps, and for each give a count, or an…” Source: PPT MAN, CC BY.
“In this raw highway dash cam clip, find every commercial vehicle (semi-trailer, cement or bulk trailer, box truck, pickup towing) and every overhead or roadside sign. For each vehicle give…” Source: Tech & Crypto, CC BY.
“Count each admin action in this Moodle walkthrough (navigation clicks, form fields filled, files chosen, buttons pressed, role selections). List each with timestamp, the on-screen label and…” Source: Moodle, CC BY.
From footage to a tally with evidence.
Upload a file or paste a link.
Ask in plain language, or start from this preset.
Open the frame behind each finding, then export the report, frames and CSV.
Join forward-thinking teams using Docsie
_Leader_Small-Business_Leader.svg)
Common questions
Q: How do I count objects in a video?
A: Describe what to count. Docsie logs each occurrence with its timestamp and frame, then gives you the total.
Q: Can it count people or vehicles?
A: Yes, for example people passing an entrance or vehicles entering a lot. It counts what is visible; it does not identify who anyone is.
Q: Can it tell types or species apart?
A: Yes. Ask for the distinction you need, and confirm each one on its frame.
Q: How accurate are the counts?
A: Each count links to its frame, so you can spot-check the result. Busy or low-light scenes need more review.
Q: Does it do face recognition?
A: No. It works with what is visible, such as type, colour and behaviour, never identity.
Q: How long can a video be?
A: Up to 40 minutes per video. Longer recordings are split, and the findings are merged onto one timeline.
Q: Where does my footage go?
A: Use Docsie's cloud, or deploy Docsie on your own infrastructure so footage stays inside your network.
See it on your own footage
Book a DemoEvery number backed by a frame.
Up to 40 minutes per video. Cloud or self-hosted.
