3 - Estimation robuste pour la détection et le suivi par caméra
Bibliographic record
Abstract
When designing a Driving Assistance System based on lane-markings detection, the robustness of the outputs is a crucial issue. Moreover, to be integrated into complex control systems, they must be accompanied with some confidence measure. Formulating road markings detection as the problem of estimating the parameters of a lane model, using features extracted from the image by an original procedure, we can benefit from the robustness of M-estimators and consider as a natural confidence measure the covariance matrix of the estimate. After revisiting M-estimators in an original, Lagrangian formalism, we propose two parametric families of noise models, that allow a continuous transition between Gaussian and non-Gaussian models. Then, we focus on several points of major practical importance, though seldom addressed in computer vision, such as the estimation of noise parameters and the definition of the approximate covariance matrix. We experimentally show that the accuracy of the covariance matrix depends much more on the tuning of parameters than the one of the estimation itself. A new approximation of the covariance matrix, less sensitive to the noise model, is proposed. Finally, we exhibit new matrices, faster to compute, that might be used with advantages in many other applications.
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 | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".