An Investigation of ADAS Camera Performance Degradation Using a Realistic Rain Simulation System in Wind Tunnel
Bibliographic record
Abstract
Modern advances in the technical developments of Advanced Driver Assistance Systems (ADAS) have elevated autonomous vehicle (AV) operations to a new height. Vehicles equipped with sensor based ADAS have been positively contributing to safer roads. As the automotive industry strives for SAE Level 5 full driving autonomy, challenges inevitably arise to ensure ADAS performance and reliability in all driving scenarios, especially in adverse weather conditions, during which ADAS sensors such as optical cameras and LiDARs suffer performance degradation, leading to inaccuracy and inability to provide crucial environmental information for object detection. Currently, the difficulty to simulate realistic and dynamic adverse weather scenarios experienced by vehicles in a controlled environment becomes one of the challenges that hinders further ADAS development. While outdoor testing encounters unpredictable environmental variables, indoor testing methods, such as using spray nozzles in a wind tunnel, are often unrealistic due to the atomization of the spray droplets, causing the droplet size distributions to deviate from real-life conditions. A novel full-scale rain simulation system is developed and implemented into the ACE Climatic Aerodynamic Wind Tunnel at Ontario Tech University with the goal of quantifying ADAS sensor performance when driving in rain. The designed system is capable of recreating a wide range of dynamic rain intensity experienced by the vehicle at different driving speeds, along with the corresponding droplet size distributions. Proposed methods to evaluate optical cameras are discussed, with sample results of object detection performance and image evaluation metrics presented. Additionally, the rain simulation system showcases repeatable testing environments for soiling mitigation developments. It also demonstrates the potential to further broaden the scope of testing, such as training object detection datasets, as well as exploring the possibilities of using artificial intelligence to expand and predict the rain system control strategies and target rain 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 | 0.001 |
| 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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".