Cargando…

Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization

The intelligent transportation system, especially autonomous vehicles, has seen a lot of interest among researchers owing to the tremendous work in modern artificial intelligence (AI) techniques, especially deep neural learning. As a result of increased road accidents over the last few decades, sign...

Descripción completa

Detalles Bibliográficos
Autores principales: Kolekar, Suresh, Gite, Shilpa, Pradhan, Biswajeet, Alamri, Abdullah
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9785663/
https://www.ncbi.nlm.nih.gov/pubmed/36560047
http://dx.doi.org/10.3390/s22249677
_version_ 1784858103442833408
author Kolekar, Suresh
Gite, Shilpa
Pradhan, Biswajeet
Alamri, Abdullah
author_facet Kolekar, Suresh
Gite, Shilpa
Pradhan, Biswajeet
Alamri, Abdullah
author_sort Kolekar, Suresh
collection PubMed
description The intelligent transportation system, especially autonomous vehicles, has seen a lot of interest among researchers owing to the tremendous work in modern artificial intelligence (AI) techniques, especially deep neural learning. As a result of increased road accidents over the last few decades, significant industries are moving to design and develop autonomous vehicles. Understanding the surrounding environment is essential for understanding the behavior of nearby vehicles to enable the safe navigation of autonomous vehicles in crowded traffic environments. Several datasets are available for autonomous vehicles focusing only on structured driving environments. To develop an intelligent vehicle that drives in real-world traffic environments, which are unstructured by nature, there should be an availability of a dataset for an autonomous vehicle that focuses on unstructured traffic environments. Indian Driving Lite dataset (IDD-Lite), focused on an unstructured driving environment, was released as an online competition in NCPPRIPG 2019. This study proposed an explainable inception-based U-Net model with Grad-CAM visualization for semantic segmentation that combines an inception-based module as an encoder for automatic extraction of features and passes to a decoder for the reconstruction of the segmentation feature map. The black-box nature of deep neural networks failed to build trust within consumers. Grad-CAM is used to interpret the deep-learning-based inception U-Net model to increase consumer trust. The proposed inception U-net with Grad-CAM model achieves 0.622 intersection over union (IoU) on the Indian Driving Dataset (IDD-Lite), outperforming the state-of-the-art (SOTA) deep neural-network-based segmentation models.
format Online
Article
Text
id pubmed-9785663
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97856632022-12-24 Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization Kolekar, Suresh Gite, Shilpa Pradhan, Biswajeet Alamri, Abdullah Sensors (Basel) Article The intelligent transportation system, especially autonomous vehicles, has seen a lot of interest among researchers owing to the tremendous work in modern artificial intelligence (AI) techniques, especially deep neural learning. As a result of increased road accidents over the last few decades, significant industries are moving to design and develop autonomous vehicles. Understanding the surrounding environment is essential for understanding the behavior of nearby vehicles to enable the safe navigation of autonomous vehicles in crowded traffic environments. Several datasets are available for autonomous vehicles focusing only on structured driving environments. To develop an intelligent vehicle that drives in real-world traffic environments, which are unstructured by nature, there should be an availability of a dataset for an autonomous vehicle that focuses on unstructured traffic environments. Indian Driving Lite dataset (IDD-Lite), focused on an unstructured driving environment, was released as an online competition in NCPPRIPG 2019. This study proposed an explainable inception-based U-Net model with Grad-CAM visualization for semantic segmentation that combines an inception-based module as an encoder for automatic extraction of features and passes to a decoder for the reconstruction of the segmentation feature map. The black-box nature of deep neural networks failed to build trust within consumers. Grad-CAM is used to interpret the deep-learning-based inception U-Net model to increase consumer trust. The proposed inception U-net with Grad-CAM model achieves 0.622 intersection over union (IoU) on the Indian Driving Dataset (IDD-Lite), outperforming the state-of-the-art (SOTA) deep neural-network-based segmentation models. MDPI 2022-12-10 /pmc/articles/PMC9785663/ /pubmed/36560047 http://dx.doi.org/10.3390/s22249677 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kolekar, Suresh
Gite, Shilpa
Pradhan, Biswajeet
Alamri, Abdullah
Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title_full Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title_fullStr Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title_full_unstemmed Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title_short Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization
title_sort explainable ai in scene understanding for autonomous vehicles in unstructured traffic environments on indian roads using the inception u-net model with grad-cam visualization
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9785663/
https://www.ncbi.nlm.nih.gov/pubmed/36560047
http://dx.doi.org/10.3390/s22249677
work_keys_str_mv AT kolekarsuresh explainableaiinsceneunderstandingforautonomousvehiclesinunstructuredtrafficenvironmentsonindianroadsusingtheinceptionunetmodelwithgradcamvisualization
AT giteshilpa explainableaiinsceneunderstandingforautonomousvehiclesinunstructuredtrafficenvironmentsonindianroadsusingtheinceptionunetmodelwithgradcamvisualization
AT pradhanbiswajeet explainableaiinsceneunderstandingforautonomousvehiclesinunstructuredtrafficenvironmentsonindianroadsusingtheinceptionunetmodelwithgradcamvisualization
AT alamriabdullah explainableaiinsceneunderstandingforautonomousvehiclesinunstructuredtrafficenvironmentsonindianroadsusingtheinceptionunetmodelwithgradcamvisualization