AI for Home-Cage Behaviour Analysis
Industrial & Inspection Life Sciences

AI for Home-Cage Behaviour Analysis

Turning side-view video into per-minute behavioural readouts for preclinical research.

0.91

Mouse detection AP50
on 100 held-out frames

3×

Detection AP50 gain
over the off-the-shelf model

5–7 s

Detection, pose and tracking
per minute of video on a single GPU

Customer Story

iMouse offers a retrofit observation system for standard laboratory home cages. Blackthorn AI is building a computer vision pipeline for the system that converts side-view recordings into behavioural analytics.

Detection, pose estimation and activity readouts are in use in the research pipeline.

Computer Vision

Services

Germany

Location

Applied AI research · ongoing

Engagement

Challenge

From hours of home-cage video to consistent behavioural measurements

Researchers need to compare behaviour over time without relying on isolated manual observations. Side-view recordings capture posture and vertical movement, but overlapping animals, cage furniture, infrared lighting and camera angle make automated analysis difficult. iMouse needed models adapted to its own recordings, agreed behaviour definitions and outputs in the format its scientists use.

Solution

One pipeline from video to research readouts

Blackthorn AI has built a pipeline that detects mice, tracks them and estimates their pose, with models trained on hand-labelled iMouse footage. Behavioral readouts are aggregated per cage and minute, exported as CSV and paired with overlay videos.

Detection overlay on an iMouse side-view home-cage recording: one mouse rearing.
Rearing detection
Detection overlay on an iMouse side-view home-cage recording: one mouse climbing, one resting.
Climbing and resting detections
Infrared home-cage recording with two resting mice outlined.
Resting detections
Tech Stack

Built with Python, PyTorch and OpenCV, with CVAT for box and keypoint labelling.

Python
PyTorch
OpenCV
CVAT
Roadmap

Project duration

Initial engagement: October 2026–January 2027.

Oct 2026 Data foundation

Completed

Audited recordings, timestamps and camera-to-cage mappings. Established box and keypoint labelling protocols and prepared held-out evaluation data.

Oct–Nov Perception & activity

In use in research

Mouse detection and pose estimation on iMouse recordings. Added false-box filtering, activity readouts and per-minute exports.

Nov–Jan Behaviour models & batch run

Ongoing

Annotating behaviour, evaluating and retraining classifiers, and preparing a pipeline run across all recording rounds.

Team Size

4 Qualified Specialists
1 × Senior AI Engineer
2 × Annotators
1 × Senior AI Architect

Results to Date

Research benchmarks as of 13 November 2026. Accuracy varies with camera view, occlusion and lighting. Resting is currently estimated from periods of low movement and can include grooming or eating.

0.91

Detection AP50

Mouse detection AP50 on 100 held-out, human-labelled frames.

3×

Gain over off-the-shelf

Fine-tuning on hand-labelled iMouse frames lifted mouse detection AP50 from 0.30 (zero-shot) to 0.91.

5–7 s

Processing per video minute

Detection, pose estimation and tracking process one minute of video in about 5–7 seconds on a single GPU.

Discover More Related Customer Stories