Urban Intersection Classification: A Comparative Analysis
Understanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/18/6269 |
| _version_ | 1797517212927393792 |
|---|---|
| author | Augusto Luis Ballardini Álvaro Hernández Saz Sandra Carrasco Limeros Javier Lorenzo Ignacio Parra Alonso Noelia Hernández Parra Iván García Daza Miguel Ángel Sotelo |
| author_facet | Augusto Luis Ballardini Álvaro Hernández Saz Sandra Carrasco Limeros Javier Lorenzo Ignacio Parra Alonso Noelia Hernández Parra Iván García Daza Miguel Ángel Sotelo |
| author_sort | Augusto Luis Ballardini |
| collection | DOAJ |
| description | Understanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on the detection and classification of urban intersections as seen from onboard front-facing cameras. Different methodologies aimed at classifying intersection geometries have been assessed to provide a comprehensive evaluation of state-of-the-art techniques based on Deep Neural Network (DNN) approaches, including single-frame approaches and temporal integration schemes. A detailed analysis of most popular datasets previously used for the application together with a comparison with ad hoc recorded sequences revealed that the performances strongly depend on the field of view of the camera rather than other characteristics or temporal-integrating techniques. Due to the scarcity of training data, a new dataset is created by performing data augmentation from real-world data through a Generative Adversarial Network (GAN) to increase generalizability as well as to test the influence of data quality. Despite being in the relatively early stages, mainly due to the lack of intersection datasets oriented to the problem, an extensive experimental activity has been performed to analyze the individual performance of each proposed systems. |
| first_indexed | 2024-03-10T07:13:35Z |
| format | Article |
| id | doaj.art-86dacad74277490cb716e609b9e0d9e6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T07:13:35Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-86dacad74277490cb716e609b9e0d9e62023-11-22T15:14:20ZengMDPI AGSensors1424-82202021-09-012118626910.3390/s21186269Urban Intersection Classification: A Comparative AnalysisAugusto Luis Ballardini0Álvaro Hernández Saz1Sandra Carrasco Limeros2Javier Lorenzo3Ignacio Parra Alonso4Noelia Hernández Parra5Iván García Daza6Miguel Ángel Sotelo7Computer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainComputer Engineering Department, Universidad de Alcalá, 28805 Alcalá de Henares, SpainUnderstanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on the detection and classification of urban intersections as seen from onboard front-facing cameras. Different methodologies aimed at classifying intersection geometries have been assessed to provide a comprehensive evaluation of state-of-the-art techniques based on Deep Neural Network (DNN) approaches, including single-frame approaches and temporal integration schemes. A detailed analysis of most popular datasets previously used for the application together with a comparison with ad hoc recorded sequences revealed that the performances strongly depend on the field of view of the camera rather than other characteristics or temporal-integrating techniques. Due to the scarcity of training data, a new dataset is created by performing data augmentation from real-world data through a Generative Adversarial Network (GAN) to increase generalizability as well as to test the influence of data quality. Despite being in the relatively early stages, mainly due to the lack of intersection datasets oriented to the problem, an extensive experimental activity has been performed to analyze the individual performance of each proposed systems.https://www.mdpi.com/1424-8220/21/18/6269intersection classificationscene understandingself drivingintelligent transportation systemsCNNGAN |
| spellingShingle | Augusto Luis Ballardini Álvaro Hernández Saz Sandra Carrasco Limeros Javier Lorenzo Ignacio Parra Alonso Noelia Hernández Parra Iván García Daza Miguel Ángel Sotelo Urban Intersection Classification: A Comparative Analysis Sensors intersection classification scene understanding self driving intelligent transportation systems CNN GAN |
| title | Urban Intersection Classification: A Comparative Analysis |
| title_full | Urban Intersection Classification: A Comparative Analysis |
| title_fullStr | Urban Intersection Classification: A Comparative Analysis |
| title_full_unstemmed | Urban Intersection Classification: A Comparative Analysis |
| title_short | Urban Intersection Classification: A Comparative Analysis |
| title_sort | urban intersection classification a comparative analysis |
| topic | intersection classification scene understanding self driving intelligent transportation systems CNN GAN |
| url | https://www.mdpi.com/1424-8220/21/18/6269 |
| work_keys_str_mv | AT augustoluisballardini urbanintersectionclassificationacomparativeanalysis AT alvarohernandezsaz urbanintersectionclassificationacomparativeanalysis AT sandracarrascolimeros urbanintersectionclassificationacomparativeanalysis AT javierlorenzo urbanintersectionclassificationacomparativeanalysis AT ignacioparraalonso urbanintersectionclassificationacomparativeanalysis AT noeliahernandezparra urbanintersectionclassificationacomparativeanalysis AT ivangarciadaza urbanintersectionclassificationacomparativeanalysis AT miguelangelsotelo urbanintersectionclassificationacomparativeanalysis |