Evaluating Artificial Vision in AI Systems : The Case of Autonomous Driving : 43rd European Conference on Visual Perception (ECVP 2021), (Online conference), August 22-27, 2021
(2021) In Perception 50(1 Suppl.). p.221-222- Abstract
- We develop a cognitive evaluation schema for analysing the diversity and nuances of visuospatial complexity and multimodal interactions encountered in naturalistic everyday driving conditions. The proposed schema is based on a finegrained empirical analysis of real-world everyday driving situations involving stakeholders such as drivers, pedestrians, cyclists. Our method involves a semantic analysis of egocentric POVs of stakeholders, focusing on the sequence and duration of events (e.g. velocity or direction change), the combination of modalities used (e.g., gestures, gaze, head-movements), audio, quantity and variety of moving and static objects in the scene e.g., (cars, signs), behavioural metrics from the stakeholders (e.g. gaze... (More)
- We develop a cognitive evaluation schema for analysing the diversity and nuances of visuospatial complexity and multimodal interactions encountered in naturalistic everyday driving conditions. The proposed schema is based on a finegrained empirical analysis of real-world everyday driving situations involving stakeholders such as drivers, pedestrians, cyclists. Our method involves a semantic analysis of egocentric POVs of stakeholders, focusing on the sequence and duration of events (e.g. velocity or direction change), the combination of modalities used (e.g., gestures, gaze, head-movements), audio, quantity and variety of moving and static objects in the scene e.g., (cars, signs), behavioural metrics from the stakeholders (e.g. gaze allocation, steering), etc. The proposed cognitive evaluation schema consists of three key aspects: (1) Scene characteristics consisting of a combination of quantitative (e.g., clutter, size), structural (e.g. symmetry), and dynamic attributes (e.g. motion), (2) Multimodal interactions consisting of the mode and method of interaction, as well as the level of joint attention achieved, (3) Recipient effects characterising subject’s behaviour and driving performance through physiological measurements (e.g. eye-tracking, head rotation) in a series of virtual reality (VR) environments replicating a number of naturalistic scenarios (and variations therefrom). Driven by behavioural methods in visual perception, we aim to open-up an interdisciplinary frontier for the human-centred design, evaluation / testing of artificial vision modules within AI-technologies for autonomous driving, cognitive robotics etc., where embodied, multimodal human-machine interaction is of the essence. We also demonstrate the practical application of basic visual perception research towards technology-centric settings of social significance. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/9effc8f2-bde7-43e8-b436-62ad434d7fe7
- author
- Kondyli, Vasiliki LU and Bhatt, Mehul
- publishing date
- 2021
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Embodied Interaction, Human Factors, Visual Perception, Naturalistic Studies, Multimodality, Autonomous Driving, Psychology (excluding Applied Psychology), Psykologi (exklusive tillämpad psykologi), Computer Systems, Datorsystem
- in
- Perception
- volume
- 50
- issue
- 1 Suppl.
- pages
- 2 pages
- publisher
- SAGE Publications
- external identifiers
-
- scopus:85123393878
- ISSN
- 0301-0066
- DOI
- 10.1177/03010066211059887
- language
- English
- LU publication?
- no
- additional info
- 2023-05-11T10:42:07.906+02:00
- id
- 9effc8f2-bde7-43e8-b436-62ad434d7fe7
- date added to LUP
- 2024-12-18 15:12:23
- date last changed
- 2025-04-04 14:31:07
@article{9effc8f2-bde7-43e8-b436-62ad434d7fe7,
abstract = {{We develop a cognitive evaluation schema for analysing the diversity and nuances of visuospatial complexity and multimodal interactions encountered in naturalistic everyday driving conditions. The proposed schema is based on a finegrained empirical analysis of real-world everyday driving situations involving stakeholders such as drivers, pedestrians, cyclists. Our method involves a semantic analysis of egocentric POVs of stakeholders, focusing on the sequence and duration of events (e.g. velocity or direction change), the combination of modalities used (e.g., gestures, gaze, head-movements), audio, quantity and variety of moving and static objects in the scene e.g., (cars, signs), behavioural metrics from the stakeholders (e.g. gaze allocation, steering), etc. The proposed cognitive evaluation schema consists of three key aspects: (1) Scene characteristics consisting of a combination of quantitative (e.g., clutter, size), structural (e.g. symmetry), and dynamic attributes (e.g. motion), (2) Multimodal interactions consisting of the mode and method of interaction, as well as the level of joint attention achieved, (3) Recipient effects characterising subject’s behaviour and driving performance through physiological measurements (e.g. eye-tracking, head rotation) in a series of virtual reality (VR) environments replicating a number of naturalistic scenarios (and variations therefrom). Driven by behavioural methods in visual perception, we aim to open-up an interdisciplinary frontier for the human-centred design, evaluation / testing of artificial vision modules within AI-technologies for autonomous driving, cognitive robotics etc., where embodied, multimodal human-machine interaction is of the essence. We also demonstrate the practical application of basic visual perception research towards technology-centric settings of social significance.}},
author = {{Kondyli, Vasiliki and Bhatt, Mehul}},
issn = {{0301-0066}},
keywords = {{Embodied Interaction; Human Factors; Visual Perception; Naturalistic Studies; Multimodality; Autonomous Driving; Psychology (excluding Applied Psychology); Psykologi (exklusive tillämpad psykologi); Computer Systems; Datorsystem}},
language = {{eng}},
number = {{1 Suppl.}},
pages = {{221--222}},
publisher = {{SAGE Publications}},
series = {{Perception}},
title = {{Evaluating Artificial Vision in AI Systems : The Case of Autonomous Driving : 43rd European Conference on Visual Perception (ECVP 2021), (Online conference), August 22-27, 2021}},
url = {{http://dx.doi.org/10.1177/03010066211059887}},
doi = {{10.1177/03010066211059887}},
volume = {{50}},
year = {{2021}},
}