KCS-YOLO: An Improved Algorithm for Traffic Light Detection under Low Visibility Conditions
Bibliographic record
Abstract
Autonomous vehicles face challenges in small-target detection and, in particular, in accurately identifying traffic lights under low visibility conditions, e.g., fog, rain, and blurred night-time lighting. To address these issues, this paper proposes an improved algorithm, namely KCS-YOLO (you only look once), to increase the accuracy of detecting and recognizing traffic lights under low visibility conditions. First, a comparison was made to assess different YOLO algorithms. The benchmark indicates that the YOLOv5n algorithm achieves the highest mean average precision (mAP) with fewer parameters. To enhance the capability for detecting small targets, the algorithm built upon YOLOv5n, namely KCS-YOLO, was developed using the K-means++ algorithm for clustering marked multi-dimensional target frames, embedding the convolutional block attention module (CBAM) attention mechanism, and constructing a small-target detection layer. Second, an image dataset of traffic lights was generated, which was preprocessed using the dark channel prior dehazing algorithm to enhance the proposed algorithm’s recognition capability and robustness. Finally, KCS-YOLO was evaluated through comparison and ablation experiments. The experimental results showed that the mAP of KCS-YOLO reaches 98.87%, an increase of 5.03% over its counterpart of YOLOv5n. This indicates that KCS-YOLO features high accuracy in object detection and recognition, thereby enhancing the capability of traffic light detection and recognition for autonomous vehicles in low visibility conditions.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 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".