Jolyon Troscianko
banner
jtroscianko.bsky.social
Jolyon Troscianko
@jtroscianko.bsky.social
Visual ecologist at Exeter University. I study how visual information affects the ecology, behaviour, survival and conservation of many different animals. Areas of interest include camouflage, signalling, visual modelling and artificial light at night
This grass moth is often invisible in still frames, but easy to see in motion. BehaveAI can use this motion to track tiny & camouflaged moving objects in complex scenes. Its semi-automated annotation workflow also means this moth-tracker took only an hour to make.

Preprint: tinyurl.com/BehaveAI
November 7, 2025 at 2:06 PM
BehaveAI can tell you who is doing what in each video frame. This example classifies behaviour from movement and sex from static appearance such as wing markings.

Preprint: tinyurl.com/BehaveAI
Git: tinyurl.com/BehaveAIgithub
Video: tinyurl.com/BehaveAIintro

@uniexecec.bsky.social
November 7, 2025 at 12:23 PM
BehaveAI is live!

Our biologically inspired video analysis tool sees motion as colour. Track animals or objects, classify their behaviour, and handle complex natural scenes with ease.

Semi-supervised annotation, no GPUs required, user-friendly, free & open source.

Pre-print tinyurl.com/BehaveAI
November 6, 2025 at 10:09 AM