Tracktor: Image‐based automated tracking of animal movement and behaviour
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Automated movement tracking is essential for high‐throughput quantitative analyses of the behaviour and kinematics of organisms. Automated tracking also improves replicability by avoiding observer bias and allowing reproducible workflows. However, few automated tracking programs exist that are open access, open source and capable of tracking unmarked organisms in noisy environments. Tracktor is an image‐based tracking freeware designed to perform single‐object tracking in noisy environments, or multi‐object tracking in uniform environments while maintaining individual identities. Tracktor is code‐based but requires no coding skills other than the user being able to specify tracking parameters in a designated location, much like in a graphical user interface. The installation and use of the software is fully detailed in a user manual. Through four examples of common tracking problems, we show that Tracktor is able to track a variety of animals in diverse conditions. The main strengths of Tracktor lie in its ability to track single individuals under noisy conditions (e.g. when the object shape is distorted), its robustness to perturbations (e.g. changes in lighting conditions during the experiment), and its capacity to track multiple unmarked individuals while maintaining their identities. Additionally, summary statistics and plots allow measuring and visualising common metrics used in the analysis of animal movement (e.g. cumulative distance, speed, acceleration, activity, time spent in specific areas and distance to conspecific, etc.). Tracktor is a versatile, reliable and easy‐to‐use automated tracking software that is compatible with all operating systems and provides many features not available in other existing freeware. Access Tracktor and the complete user manual here: https://github.com/vivekhsridhar/tracktor
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it