Mobile-Le Harmonic Fusion Network for Object Recognition and SiamMoT Based Multi-Object Tracking Using Video Surveillance
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
Video surveillance plays a vital role in applications like crowd control, traffic monitoring, and security, but accurately tracking multiple moving objects remains challenging. Traditional methods often lack reliability in complex scenes. To address this, the Mobile-Le Harmonic Fusion Network (MLeHF-Net) + SiamMoT (MLeHF-Net + SiamMoT) combined with SiamMoT has been introduced, offering improved object detection and tracking performance. The process starts by extracting video from the dataset and breaking it into frames, which are segmented using Entropy Weighting K-Means (EWKM). Objects are then detected via MLeHF-Net a fusion of LeNet, Harmonic analysis, and MobileNet and tracked using the Siamese Multi-Object Tracking network (SiamMoT). This study uses the UCSD Anomaly Detection Dataset to benchmark video surveillance performance. The proposed MLeHF-Net + SiamMOT model is compared with established methods You Only Look Once (YOLOv2) + LuNet, SMSBoxNet, Densely Feature Selection Convolutional Neural Network – Hyper Parameter tuning (DFCN-HP), and Computational Intelligence-based Harmony Search Algorithm for Real-Time Object Detection and Tracking (CIHSA-RTODT). Experimental results show that proposed method achieved high performance with MOTP, TNR, TPR, and overall accuracy of 91.099%, 91.134%, 93.577%, and 92.315%. Compared to existing methods YOLOv2 + LuNet, SMSBoxNet, DFCN-HP, and CIHSA-RTODT it delivered accuracy improvements of up to 13.72%.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it