Enhancing Object Tracking in Smart City Intelligent Transportation Systems: A Track-by-Detection Approach Utilizing Satellite Video Monitoring
Bibliographic record
Abstract
Ensuring effective object tracking within Intelligent Transportation Systems (ITS) in smart cities is pivotal for enhancing urban mobility and sustainability. However, challenges arise, particularly in scenarios with occlusions and adverse weather conditions, where traditional methods may fall short in ensuring safety. To address these challenges, a novel track-by-detection approach is introduced aimed at enhancing transportation systems. The approach integrates key components, including the Detection Transformer (DETR) for emphasizing global context, and the You Only Look Once version 7 (YOLOv7) renowned for capturing local context. Additionally, the deep sort tracking filter is incorporated to enhance object tracking accuracy. A pivotal aspect of the approach lies in the utilization of the deep sort of filter for object tracking, preceded by preprocessing with the Principal Component Analysis (PCA) method to refine tracking outcomes. This buffering approach significantly improves tracking quality by reducing noise and enhancing feature representation. Moreover, the approach leverages tracking from satellite videos, enabling comprehensive monitoring of transportation activities across vast regions. The refined tracking outputs, including those from satellite videos, are fused with direct outputs from the trackers obtained from both YOLOv7 and DETR. These integrated fused buffered tracked bounding boxes demonstrate superior performance compared to individual approaches. Validation using simulated imagery under cloudy conditions, incorporating the Motion Evaluation Metric (MOT), showcases enhanced accuracy across various transportation objects. Implementing this approach in ITS promise’s benefits such as enhanced traffic management and increased efficiency in public transportation. This underscores the role of Artificial Intelligence (AI) in revolutionizing smart city mobility.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".