arXiv:2510.22390v1 Announce Type: new 
Abstract: We present a fully interpretable and flexible statistical method for background subtraction in roadside LiDAR data, aimed at enhancing infrastructure-based perception in automated driving. Our approach introduces both a Gaussian distribution grid (GDG), which models the spatial statistics of the background using background-only scans, and a filtering algorithm that uses this representation to classify LiDAR points as foreground or background. The method supports diverse LiDAR types, including multiline 360 degree and micro-electro-mechanical systems (MEMS) sensors, and adapts to various configurations. Evaluated on the publicly available RCooper dataset, it outperforms state-of-the-art techniques in accuracy and flexibility, even with minimal background data. Its efficient implementation ensures reliable performance on low-resource hardware, enabling scalable real-world deployment.

تم تقديم طريقة إحصائية جديدة لطرح الخلفية في بيانات LiDAR على جانب الطريق، والتي يمكن أن تحسن بشكل كبير أنظمة القيادة الآلية. تستخدم هذه الطريقة شبكة توزيع غاوسي لنمذجة إحصائيات الخلفية، مما يسمح بتصنيف أكثر دقة لنقاط LiDAR. هذه الابتكار مهم لأنه يعزز قدرات الإدراك للبنية التحتية، مما قد يؤدي إلى سيارات ذاتية القيادة أكثر أمانًا وكفاءة.

Se ha presentado un nuevo método estadístico para la sustracción de fondo en datos LiDAR de carretera, que podría mejorar significativamente los sistemas de conducción automatizada. Este enfoque utiliza una cuadrícula de distribución gaussiana para modelar las estadísticas de fondo, lo que permite una clasificación más precisa de los puntos LiDAR. Esta innovación es importante ya que mejora las capacidades de percepción de la infraestructura, lo que podría llevar a vehículos autónomos más seguros y eficientes.

Une nouvelle méthode statistique pour la soustraction de fond dans les données LiDAR routières a été introduite, ce qui pourrait améliorer considérablement les systèmes de conduite automatisée. Cette approche utilise une grille de distribution gaussienne pour modéliser les statistiques de fond, permettant une classification plus précise des points LiDAR. Cette innovation est importante car elle améliore les capacités de perception de l'infrastructure, ce qui pourrait conduire à des véhicules autonomes plus sûrs et plus efficaces.

A new statistical method for background subtraction in roadside LiDAR data has been introduced, which could significantly improve automated driving systems. This approach utilizes a Gaussian distribution grid to model background statistics, allowing for more accurate classification of LiDAR points. This innovation is important as it enhances the perception capabilities of infrastructure, potentially leading to safer and more efficient autonomous vehicles.

A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction

arXiv:2512.02062v1 Announce Type: cross 
Abstract: Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small perturbations that can lead to misclassifications. More powerful black-box adversarial attacks are required to develop more effective defenses. A promising approach to black-box adversarial attacks is to repeat the process of extracting a specific image area and changing the perturbations added to it. Existing attacks adopt simple rectangles as the areas where perturbations are changed in a single iteration. We propose applying superpixels instead, which achieve a good balance between color variance and compactness. We also propose a new search method, versatile search, and a novel attack method, Superpixel Attack, which applies superpixels and performs versatile search. Superpixel Attack improves attack success rates by an average of 2.10% compared with existing attacks. Most models used in this study are robust against adversarial attacks, and this improvement is significant for black-box adversarial attacks. The code is avilable at https://github.com/oe1307/SuperpixelAttack.git.

تم اقتراح طريقة جديدة تُدعى Superpixel Attack لتعزيز الهجمات العدائية في نماذج التعلم العميق، خاصة في التطبيقات الحرجة للسلامة مثل القيادة الآلية والتعرف على الوجه. تستخدم هذه الطريقة وحدات بكسل فائقة بدلاً من المستطيلات البسيطة لتطبيق الاضطرابات، مما يحسن فعالية الهجمات العدائية والدفاعات.

Se ha propuesto un nuevo método llamado Superpixel Attack para mejorar los ataques adversariales de caja negra en modelos de aprendizaje profundo, especialmente en aplicaciones críticas para la seguridad como la conducción automatizada y el reconocimiento facial. Este enfoque utiliza superpíxeles en lugar de rectángulos simples para aplicar perturbaciones, mejorando la efectividad de los ataques adversariales y las defensas.

Une nouvelle méthode appelée Superpixel Attack a été proposée pour améliorer les attaques adversariales en boîte noire dans les modèles d'apprentissage profond, en particulier dans des applications critiques pour la sécurité comme la conduite automatisée et la reconnaissance faciale. Cette approche utilise des superpixels au lieu de simples rectangles pour appliquer des perturbations, améliorant ainsi l'efficacité des attaques adversariales et des défenses.

A new method called Superpixel Attack has been proposed to enhance black-box adversarial attacks in deep learning models, particularly in safety-critical applications like automated driving and face recognition. This approach utilizes superpixels instead of simple rectangles to apply perturbations, improving the effectiveness of adversarial attacks and defenses.

A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction

Was this article worth reading? Share it

AIPortalX

Open Source Surveillance

Attentive AI