Object Detection in Real-Time Surveillance Using Deep Learning-Based YOLO Framework
Bibliographic record
Abstract
The continual growth of the computer vision and artificial intelligence fields overtime have provided the basis for more efficient and accurate surveillance. This paper examines the use of YOLO, a deep learning model that is used in the detection of objects, for use in real-time surveillance systems. The added benefits of identifying and labeling multiple objects in a single pass forward makes YOLO ideal for real-time surveillance. Unlike other approaches to object detection such as region-based methods or methods with multiple stages of detection, YOLO cast object detection as a regression problem where boxes and class probabilities are predicted jointly. This leads to a far improved performance when compared with their slower counterparts without the sacrifice of precision. In this work, the YOLO model is finetuned on a large database of surveillance videos to improve object detection at low lighting and in the presence of occlusion and crowding. The developed system has a high detection speed and accuracy; the application areas will include uses such as security inspection, traffic regulation, and anomaly detection. This is done to affirm that using YOLO is more efficient and faster than the other object detection algorithms in real-time surveillance tasks. The results indicate directions for further improvements to guarantee public safety and improve efficient surveillance systems.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".