Enhancing the application of signal light recognition for the YOLOv8 model in complex traffic scenarios
Bibliographic record
Abstract
In intricate traffic environments, traffic lights, as pivotal signaling tools, are influenced by factors such as observational distance and lighting conditions. This article proposes an enhanced YOLOv8 model that integrates a hybrid attention mechanism to adapt signal light recognition to complex traffic scenarios. Particularly, the introduction of the Global Attention Mechanism (GAM) within the YOLOv8 model is highlighted. GAM leverages a three-dimensional arrangement and dual-layer MLPs (Multilayer Perceptrons) to emphasize and strengthen channel features that are advantageous for the task of traffic light detection, while also maintaining cross-dimensional channel-spatial dependencies. It concentrates and merges spatial information with channel information through convolutional layers, enabling interaction and avoiding information loss by excluding max-pooling operations. Experimental results demonstrate the exceptional signal light recognition capabilities of the YOLOv8 model enhanced by the GAM attention mechanism in complex traffic scenes, fulfilling practical application requirements across all metrics. Post enhancement, the average recognition rate (Map@50) reaches as high as 93%, demonstrating the model's stability and efficiency in complex environments. The proposed method, based on the improved YOLOv8 model combined with the GAM attention mechanism for signal light recognition, effectively enhances the accuracy and robustness of traffic light detection in complex traffic environments, offering valuable research findings for the advancement and implementation of intelligent transportation 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 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) | 0.002 | 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".