AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Motion-Based Compression and Tracking System for Video Camera Trap-Based Insect Behaviour Studies

Malika Nisal Ratnayake, Lex Gallon, Adel N. Toosi, Alan Dorin

IJCV 2026 · Video › Video segmentation and tracking · approach: Learned video compression · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use pixel-wise motion analysis instead of frame-level discarding onlyEcoMotionZip · Dataset 3 (strawberry farm, continuous)size reduction vs frame reduction: 93.03 -> 97.56Improved
use pixel-wise motion analysis instead of frame-level discarding onlyEcoMotionZip · Dataset 4 (orchid, motion-triggered)size reduction vs frame reduction: 1.90 -> 89.53Improved
use pixel-wise motion analysis instead of frame-level discarding onlyEcoMotionZip · Dataset 1 (motion-triggered/time-lapse)size reduction vs frame reduction: 23.49 -> 78.44Improved
view compressed instead of raw video for manual insect countinghuman observers · Dataset 3 manual counts (Syrphidae)insect count: 6 -> 9Improved
view compressed instead of raw video for manual insect countinghuman observers · Dataset 3 manual counts (Vespidae)insect count: 10 -> 13Improved
view compressed instead of raw video for manual insect countinghuman observers · Dataset 3 manual counts (Lepidoptera)insect count: 4 -> 5Improved
view compressed instead of raw video for manual insect countinghuman observers · Dataset 3 manual counts (Honeybee)insect count: 20 -> 20No clear effect
discard no-motion frames, losing hovering honeybee framesEcoMotionZip · Dataset 3 manual flower visits (Honeybee)flower visits: 67 -> 67 with 2 visits missedHurt
upgrade hardware from Raspberry Pi 4 to Raspberry Pi 5EcoMotionZip · Dataset 3 (strawberry farm)processing speed (fps): 60.9 -> 88.5Improved
run on Jetson Nano instead of Raspberry Pi 5EcoMotionZip · Dataset 6 (semi-controlled)processing speed (fps): 32.1 -> 37.0Improved
run on Jetson Nano instead of Raspberry Pi 5EcoMotionZip · Dataset 2 (Scaevola)processing speed (fps): 37.4 -> 39.5Mixed
use Polytrack on compressed rather than raw videosPolytrack with pre-processing · automated trackingflower visit countsMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy