Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments
Traffic Sign Recognition (TSR) is one of the many utilities made possible by embedded systems with internet connections. Through the usage of vehicular cameras, it’s possible to capture and classify traffic signs in real time with Artificial Intelligence (AI), more specifically, Convolutional Neural...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/5919 |
| _version_ | 1797590831749660672 |
|---|---|
| author | Vanessa Dalborgo Thiago B. Murari Vinicius S. Madureira João Gabriel L. Moraes Vitor Magno O. S. Bezerra Filipe Q. Santos Alexandre Silva Roberto L. S. Monteiro |
| author_facet | Vanessa Dalborgo Thiago B. Murari Vinicius S. Madureira João Gabriel L. Moraes Vitor Magno O. S. Bezerra Filipe Q. Santos Alexandre Silva Roberto L. S. Monteiro |
| author_sort | Vanessa Dalborgo |
| collection | DOAJ |
| description | Traffic Sign Recognition (TSR) is one of the many utilities made possible by embedded systems with internet connections. Through the usage of vehicular cameras, it’s possible to capture and classify traffic signs in real time with Artificial Intelligence (AI), more specifically, Convolutional Neural Networks (CNNs) based techniques. This article discusses the implementation of such TSR systems, and the building process of datasets for AI training. Such datasets include a brand new class to be used in TSR, vegetation occlusion. The results show that this approach is useful in making traffic sign maintenance faster since this application turns vehicles into moving sensors in that context. Leaning on the proposed technique, identified irregularities in traffic signs can be reported to a responsible body so they will eventually be fixed, contributing to a safer traffic environment. This paper also discusses the usage and performance of different YOLO models according to our case studies. |
| first_indexed | 2024-03-11T01:29:03Z |
| format | Article |
| id | doaj.art-12eb554a2f8643a79a573bfff8952c73 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:03Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-12eb554a2f8643a79a573bfff8952c732023-11-18T17:28:46ZengMDPI AGSensors1424-82202023-06-012313591910.3390/s23135919Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian EnvironmentsVanessa Dalborgo0Thiago B. Murari1Vinicius S. Madureira2João Gabriel L. Moraes3Vitor Magno O. S. Bezerra4Filipe Q. Santos5Alexandre Silva6Roberto L. S. Monteiro7Computational Modeling and Industrial Technology Program, SENAI CIMATEC, Salvador 41650-010, BrazilComputational Modeling and Industrial Technology Program, SENAI CIMATEC, Salvador 41650-010, BrazilElectrical Engineering Program, College of Ilhéus, Ilhéus 45655-120, BrazilComputational Modeling and Industrial Technology Program, SENAI CIMATEC, Salvador 41650-010, BrazilElectrical Engineering Department, Federal University of Sergipe, São Cristovão 49100-000, BrazilDepartment of Engineering and Computing, State University of Santa Cruz, Ilhéus 45662-900, BrazilComputational Modeling and Industrial Technology Program, SENAI CIMATEC, Salvador 41650-010, BrazilComputational Modeling and Industrial Technology Program, SENAI CIMATEC, Salvador 41650-010, BrazilTraffic Sign Recognition (TSR) is one of the many utilities made possible by embedded systems with internet connections. Through the usage of vehicular cameras, it’s possible to capture and classify traffic signs in real time with Artificial Intelligence (AI), more specifically, Convolutional Neural Networks (CNNs) based techniques. This article discusses the implementation of such TSR systems, and the building process of datasets for AI training. Such datasets include a brand new class to be used in TSR, vegetation occlusion. The results show that this approach is useful in making traffic sign maintenance faster since this application turns vehicles into moving sensors in that context. Leaning on the proposed technique, identified irregularities in traffic signs can be reported to a responsible body so they will eventually be fixed, contributing to a safer traffic environment. This paper also discusses the usage and performance of different YOLO models according to our case studies.https://www.mdpi.com/1424-8220/23/13/5919object recognitionNeural NetworksYOLO |
| spellingShingle | Vanessa Dalborgo Thiago B. Murari Vinicius S. Madureira João Gabriel L. Moraes Vitor Magno O. S. Bezerra Filipe Q. Santos Alexandre Silva Roberto L. S. Monteiro Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments Sensors object recognition Neural Networks YOLO |
| title | Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments |
| title_full | Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments |
| title_fullStr | Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments |
| title_full_unstemmed | Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments |
| title_short | Traffic Sign Recognition with Deep Learning: Vegetation Occlusion Detection in Brazilian Environments |
| title_sort | traffic sign recognition with deep learning vegetation occlusion detection in brazilian environments |
| topic | object recognition Neural Networks YOLO |
| url | https://www.mdpi.com/1424-8220/23/13/5919 |
| work_keys_str_mv | AT vanessadalborgo trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT thiagobmurari trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT viniciussmadureira trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT joaogabriellmoraes trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT vitormagnoosbezerra trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT filipeqsantos trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT alexandresilva trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments AT robertolsmonteiro trafficsignrecognitionwithdeeplearningvegetationocclusiondetectioninbrazilianenvironments |