Evaluation of Detection and Segmentation Tasks on Driving Datasets

Singh, Deepak; Rahane, Ameet; Mondal, Ajoy; Subramanian, Anbumani; Jawahar, C. V.

doi:10.1007/978-3-031-11346-8_44

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of seamless scene segmentation is better compared with individual models consisting of semantic and instance segmentation with the cost of fractional computation time. Singh et al [34] analyzed four object detection models, three semantic segmentation models, and three instance segmentation models on three datasets, namely, Cityscape, BDD, and IDD. Object detection models perform worse on IDD compared with Cityscape and BDD owing to the unstructured nature of the IDD dataset.…”

Section: Related Workmentioning

confidence: 99%

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

Gite

Pradhan

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%