Anomaly Detection in Surveillance Videos Using Regression With Recurrent Neural Networks
Bibliographic record
Abstract
Security cameras are widely used to detect and prevent crimes, but the number of surveillance videos has increased due to this prevalence. By processing these videos with the help of a suitable machine learning algorithm, unfavorable events can be brought to the attention of expert to manually monitor. Since these unfavorable events are of various types and few in number, this problem can be addressed in the anomaly detection structure. In this study, an anomaly detection algorithm has been developed using the UCF-Crime dataset consisting of 1900 surveillance videos of various lengths. First of all, features were extracted from these videos with the help of a pre-trained artificial neural network (ANN), the size of these features was reduced with another ANN, and the anomaly detection was performed using two different recurrent neural networks, one based on classification and the other based on future feature estimation by regression. Area under receiver operating characteristic (ROC) curve (AUC) was used as the evaluation criterion. At video level, regression method gives a better performance with 88.71% AUC than the classification method which only gives 85.82% AUC, while at video frame level, both methods perform similarly with 73.64% and 73.71%, but there are true positive rate ranges where they perform better than each other.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 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".