%0 Conference Paper %1 9600064 %A Siniosoglou, Ilias %A Sarigiannidis, Panagiotis %A Spyridis, Yannis %A Khadka, Anish %A Efstathopoulos, Georgios %A Lagkas, Thomas %B 2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS) %D 2021 %K cybersecurity %P 302-308 %R 10.1109/DCOSS52077.2021.00056 %T Synthetic Traffic Signs Dataset for Traffic Sign Detection & Recognition In Distributed Smart Systems %U https://ieeexplore.ieee.org/document/9600064/ %X Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures.

@inproceedings{9600064, abstract = {Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures.}, added-at = {2022-08-31T14:14:26.000+0200}, author = {Siniosoglou, Ilias and Sarigiannidis, Panagiotis and Spyridis, Yannis and Khadka, Anish and Efstathopoulos, Georgios and Lagkas, Thomas}, biburl = {https://www.bibsonomy.org/bibtex/280aabeb883cb04f88a44f52225954f77/caramelh2020}, booktitle = {2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS)}, doi = {10.1109/DCOSS52077.2021.00056}, interhash = {67fc85c52c276668420963d00588a17f}, intrahash = {80aabeb883cb04f88a44f52225954f77}, issn = {2325-2944}, keywords = {cybersecurity}, month = {July}, pages = {302-308}, timestamp = {2022-08-31T14:14:26.000+0200}, title = {Synthetic Traffic Signs Dataset for Traffic Sign Detection & Recognition In Distributed Smart Systems}, url = {https://ieeexplore.ieee.org/document/9600064/}, year = 2021 }