Contrastive Learning-Based Haze Visibility Enhancement in Intelligent Maritime Transportation System
Bibliographic record
Abstract
With the rapid development of artificial intelligence and big traffic data, the data-driven intelligent maritime transportation has received significant attention in both industry and academia. It is capable of improving traffic efficiency and reducing traffic accidents in maritime applications. However, video cameras often suffer from severe haze weather, leading to degraded visual data and ineffective maritime surveillance. It is thus necessary to restore the visually degraded images and to guarantee maritime transportation efficiency and safety under hazy imaging conditions. In this work, a contrastive learning framework is proposed for haze visibility enhancement in intelligent maritime transportation systems. In particular, the proposed learning method could fully learn both local and global image features, which are beneficial for visual quality improvement. A total of 100 clean images containing water traffic scenes were selected as the synthetic test dataset, and good dehazing results were achieved on both visual and indexing results (e.g., peak signal to noise ratio (PSNR): 23.95 ± 3.48 and structural similarity index (SSIM): 0.924 ± 0.065 for different transmittance and atmospheric light values). In addition, extensive experiments on real-world 100 water hazy images demonstrate the effectiveness of the proposed method (e.g., natural image quality evaluator (NIQE): 4.800 ± 0.634 and perception-based image quality evaluator (PIQE): 46.320 ± 10.253 ). The enhanced images could be effectively exploited for promoting the accuracy and robustness of ship detection. The maritime traffic supervision and management could be accordingly improved in the intelligent transportation system.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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".