Synthetic to Real Gap Estimation of Autonomous Driving Datasets using Feature Embedding

Gadipudi, Nivesh; Elamvazuthi, Irraivan; Sanmugam, Mahindra; Izhar, Lila Iznita; Prasetyo, Tindyo; Jegadeeshwaran, R.; Ali, Syed Saad Azhar

doi:10.1109/roma55875.2022.9915679

Cited by 4 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [ 17 ] proposes a method for estimating the S2R gap by computing the Euclidean distance between various real and synthetic datasets. Their approach is similar to ours in that it employs feature embedding methods to extract pertinent features.…”

Section: Related Workmentioning

confidence: 99%

“…To achieve this, we propose using three feature-based extraction models and a statistical approach based on [15]. Different feature-based extraction models have already been proposed for different applications, with highly satisfactory results [16][17][18]. In Haralick's work [15], three key elements are identified for image interpretation: spectral, contextual, and textural features.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images

Duminil,

Ieng,

Gruyer

2024

Sensors

View full text Add to dashboard Cite

Generating realistic road scenes is crucial for advanced driving systems, particularly for training deep learning methods and validation. Numerous efforts aim to create larger and more realistic synthetic datasets using graphics engines or synthetic-to-real domain adaptation algorithms. In the realm of computer-generated images (CGIs), assessing fidelity is challenging and involves both objective and subjective aspects. Our study adopts a comprehensive conceptual framework to quantify the fidelity of RGB images, unlike existing methods that are predominantly application-specific. This is probably due to the data complexity and huge range of possible situations and conditions encountered. In this paper, a set of distinct metrics assessing the level of fidelity of virtual RGB images is proposed. For quantifying image fidelity, we analyze both local and global perspectives of texture and the high-frequency information in images. Our focus is on the statistical characteristics of realistic and synthetic road datasets, using over 28,000 images from at least 10 datasets. Through a thorough examination, we aim to reveal insights into texture patterns and high-frequency components contributing to the objective perception of data realism in road scenes. This study, exploring image fidelity in both virtual and real conditions, takes the perspective of an embedded camera rather than the human eye. The results of this work, including a pioneering set of objective scores applied to real, virtual, and improved virtual data, offer crucial insights and are an asset for the scientific community in quantifying fidelity levels.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images

Duminil,

Ieng,

Gruyer

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…For simulation-based testing to be a reliable substitute for real-world testing, previous works effort is directed at validating the sensor models used by quantifying the discrepancy between simulation and reality, such [8] does for radar perception and [9] for camera-based object detection algorithms. Other approaches seek to close the reality gap by applying feature embedding techniques or different levels of domain randomization [10], [11]. In [12] is proposed a method for the real-time generation of realistic images from simulator-rendered images using generative neural networks.…”

Section: Related Workmentioning

confidence: 99%

Insertion of Real Agents Behaviors in CARLA Autonomous Driving Simulator

Serrano

Llorca

Daza

et al. 2022

Proceedings of the 6th International Conference on Computer-Human Interaction Research and Applications

View full text Add to dashboard Cite

The traditional simulation methods present some limitations, such as the reality gap between simulated experiences and real-world performance. In the field of autonomous driving research, we propose the handling of an immersive virtual reality system for pedestrians to include in simulations real behaviors of agents that interact with the simulated environment in real time, to improve the quality of the virtualworld data and reduce the gap.In this paper we employ a digital twin to replicate a study on communication interfaces between autonomous vehicles and pedestrians, generating an equivalent virtual scenario to compare the results and establish qualitative and quantitative measurements of the discrepancy. The goal is to evaluate the effectiveness and acceptability of implicit and explicit forms of communication in both scenarios and to verify that the behavior carried out by the pedestrian inside the simulator through a virtual reality interface is directly comparable with their role performed in a real traffic situation.

show abstract

Behavioural Gap Assessment of Human-Vehicle Interaction in Real and Virtual Reality-Based Scenarios in Autonomous Driving

Martín Serrano,

Izquierdo,

García Daza

et al. 2024

International Journal of Human–Computer Interaction

View full text Add to dashboard Cite

Synthetic to Real Gap Estimation of Autonomous Driving Datasets using Feature Embedding

Cited by 4 publications

References 8 publications

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images

A Comprehensive Exploration of Fidelity Quantification in Computer-Generated Images

Insertion of Real Agents Behaviors in CARLA Autonomous Driving Simulator

Behavioural Gap Assessment of Human-Vehicle Interaction in Real and Virtual Reality-Based Scenarios in Autonomous Driving

Contact Info

Product

Resources

About