Removing Snowfall Noise From Point Clouds Without Considering the Nearest Neighbors
Bibliographic record
Abstract
Light detection and ranging (LiDAR) is crucial for recognizing the surrounding environment in autonomous driving. However, snowfall can generate noise in the reflected laser beam of LiDAR, affecting downstream tasks such as object detection in autonomous driving systems. The accuracy and processing speed of existing methods for removing snowfall noise, which primarily adopt approaches based on the nearest neighbors, do not meet the requirements for autonomous driving systems. Considerably, we propose a novel method for snowfall noise removal that does not consider the nearest neighbors; instead, our method establishes threshold values for intensity, distance, and height from the LiDAR by analyzing snowfall noise characteristics. Thus, our method differs from the existing methods. We evaluated the removal accuracy and processing time of our method using the winter adverse driving dataset (WADS). Compared to the existing methods, our method achieves a similar recall but higher precision (by approximately 13.7%) and F-measure (by approximately 7.4%). Furthermore, our method significantly reduces processing time by approximately 93.7%, indicating a substantial improvement in processing speed. Furthermore, to validate its effectiveness, our method was adopted as a preprocessing step for object detection under snowfall conditions, and the Canadian adverse driving conditions (CADC) dataset was employed for evaluation. Results demonstrate that adopting our method led to an approximately 7.6% improvement in the object detection rates (ODRs) compared to detection without our method.
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) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| 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) | 0.001 | 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".