Real-time automated concurrent visual tracking of many animals and subsequent behavioural compilation
Bibliographic record
Abstract
One of our major research focus areas is real-time visual tracking and monitoring of moving and static objects in a video sequence. In particular we are interested in (1) object localization (also referred to as the focus of attention) which involves identifying the object of interest, (2) tracking the object using a model of the object which was initiated in step 1, and (3) understanding the accumulation of movements of the object over time (i.e., behavior). The objects of interiest for the purpose of this proposal are pigs. Automatically monitoring pigs via a non-invasively placed camera in their pens is interesting because the pigs are monitored in their natural habitat. Visual tracking involves modelling the object of interest and keeping track of its position and orientation through time. Issues include tracker recovery from error and preventing the tracker from jumping to other pigs. we have been able to demonstrate tracking pigs at about 10-15 Hz, however, the tracker tends to drift off the target eventually. We have only experimented with a single pig but our initial tests indicate that we can probably track at least 10 pigs simultaneously. Some unknowns include determining how quickly the pigs move and the type of motions, including quick jerky movements. Our preliminary investigations revealed that a blob tracker is insufficient for producing accurate traces.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".