WHF‐YOLOv11: Traffic Cone Detection Algorithm in Complex Scenes Based on Wavelet Convolution and Hierarchical Feature Attention
Bibliographic record
Abstract
Aiming to address the issues of missed detection and low accuracy in detecting small, dense traffic cones in complex traffic scenarios, this study proposes an improved traffic small target detection method based on YOLOv11, referred to as WHF‐YOLOv11. In terms of network structure, large receptive field wavelet convolution is introduced into the YOLOv11 network (WTConv). By decomposing and reconstructing the image at different scales, the model can capture the local and global features of the image more accurately, so as to effectively extract the key details such as texture and edge. At the level of feature map extraction, the hierarchical multiscale feature fusion network (HiFuse) was introduced into the neck network. By utilizing a three‐branch HiFuse, the local perception capabilities of CNNs and the global modeling strengths of transformers were combined to enhance the image classification accuracy. In terms of loss function, Focaler‐IoU is used as the bounding box loss function to improve the detection ability of small target difficult cases. The experimental results show that for the traffic cone dataset obtained on the Roboflow platform, compared to the benchmark model YOLOv11 n, the improved model improves the accuracy rate P and recall rate R by 2.8% and 1.7%, respectively, and mAP50 and mAP50∼95 by 1.6% and 3.3%, which verifies the effectiveness of the model and provides technical support for the intelligent detection of small targets in traffic scenes.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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".