Failures of the vehicle camera may compromise the correct acquisition of frames, that are subsequently used by autonomous driving tasks. A clear understanding of the behavior of the autonomous driving tasks under such failure conditions, together with strategies to avoid safety is jeopardized, are indeed necessary. This study analyses and improve the performance of Traffic Sign Recognition (TSR) systems for road vehicles under the possible occurrence of camera failures. Our experimental assessment relies on three public datasets, which are commonly used for benchmarking TSR systems. We artificially inject 13 different types of camera failures into the three datasets. Then, we exploit three deep neural networks (DNNs) to classify either a single frame of a traffic sign or a sequence (i.e., a sliding window) of frames. We show that sliding windows significantly improves the robustness of the classifier against altered frames. We confirm our observations through explainable AI, which allows understanding why different classifiers have different performance in case of camera failures

Robust Traffic Sign Recognition Against Camera Failures / MUHAMMAD ATIF , ANDREA CECCARELLI , TOMMASO ZOPPI , MOHAMAD GHARIB , ANDREA BONDAVALLI. - In: IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS. - ISSN 2687-7813. - ELETTRONICO. - 3:(2022), pp. 709-722. [10.1109/OJITS.2022.3213183]

Robust Traffic Sign Recognition Against Camera Failures

MUHAMMAD ATIF;ANDREA CECCARELLI;TOMMASO ZOPPI;ANDREA BONDAVALLI
2022

Abstract

Failures of the vehicle camera may compromise the correct acquisition of frames, that are subsequently used by autonomous driving tasks. A clear understanding of the behavior of the autonomous driving tasks under such failure conditions, together with strategies to avoid safety is jeopardized, are indeed necessary. This study analyses and improve the performance of Traffic Sign Recognition (TSR) systems for road vehicles under the possible occurrence of camera failures. Our experimental assessment relies on three public datasets, which are commonly used for benchmarking TSR systems. We artificially inject 13 different types of camera failures into the three datasets. Then, we exploit three deep neural networks (DNNs) to classify either a single frame of a traffic sign or a sequence (i.e., a sliding window) of frames. We show that sliding windows significantly improves the robustness of the classifier against altered frames. We confirm our observations through explainable AI, which allows understanding why different classifiers have different performance in case of camera failures
2022
3
709
722
MUHAMMAD ATIF , ANDREA CECCARELLI , TOMMASO ZOPPI , MOHAMAD GHARIB , ANDREA BONDAVALLI
File in questo prodotto:
File Dimensione Formato  
Robust_Traffic_Sign_Recognition_Against_Camera_Failures.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Open Access
Dimensione 3.76 MB
Formato Adobe PDF
3.76 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1296085
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact