Real Time Classification of Retail Theft Utilizing YOLO Algorithm
Bibliographic record
Abstract
With the rapid advancement of computer vision technologies, human behavior detection systems in surveillance environments have become a vital research area, especially in security applications such as shoplifting surveillance.This study aims to develop a classification model based on still images to detect suspicious behavior in a shopping environment.Current theft detection systems struggle with real-time processing; our YOLOv8-based framework addresses this by achieving 95% accuracy with low latency (12 ms per frame).This makes our approach suitable for being integrated in real-time monitoring systems where it guarantees an early and robust detection of abnormal behavior.Comprehensive comparison with other state-of-the-arts also confirms the superiority of the proposed method in terms of speed and detection accuracy.The model was trained using the UCF Crime dataset, as well as manually collected suspicious images from multiple sources.The categories comprised (normal behavior) and (suspicious behavior).The model was trained for 150 epochs and the model parameters were fine-tuned to obtain the best performance.Different performance metrics including precision, recall, F1-score, confusion matrix analysis, and visual results of the output of the model, were assessed.This paper is a first step in the development of an intelligent system for detecting suspicious instore behavior.This system will be extended to analyze temporal behavior with video sequences, with a view to providing a richer and more accurate understanding of theft pattern in its temporal context.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".