Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles

Ibrahim F.J. Ghalyan, Vikram Kapila

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper considers the problem of modeling the surrounding environment of a driven car by using the images captured by a dash cam during the driving process. Inspired from a human driver's interpretation of the car's surrounding environment, an abstract representation of the environment is developed that can facilitate in decision-making to prevent the car's collisions with surrounding objects. The proposed technique for modeling the car's surrounding environment utilizes the dash cam to capture images as the car is driven facing multiple situations and obstacles. By relying on the human driver's interpretation of various driving scenarios, the images of the car's surrounding environment are manually grouped into classes that reflect the driver's abstract knowledge. Grouping the images allows the formulation of knowledge transfer process from the human driver to an autonomous vehicle as a classification problem, producing a meaningful and efficient representation of models arising from real-world scenarios. The framework of convolutional neural networks (CNN) is employed to model the surrounding environment of the driven car, encapsulating the abstract knowledge of the human driver. The proposed modeling approach is applied to determine its efficacy in two experimental scenarios. In the first experiment, a highway driving scenario is considered with three classes. Alternatively, in the second experiment, a scenario of driving in a residential area is addressed with six classes. Excellent modeling performance is reported for both experiments. Comparisons conducted with alternative image classification techniques reveal the superiority of the CNN for modeling the considered driving scenarios.

Original languageEnglish (US)
Title of host publication2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538693063
DOIs
StatePublished - May 6 2019
Event2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018 - Washington, United States
Duration: Oct 9 2018Oct 11 2018

Publication series

NameProceedings - Applied Imagery Pattern Recognition Workshop
Volume2018-October
ISSN (Print)2164-2516

Conference

Conference2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018
CountryUnited States
CityWashington
Period10/9/1810/11/18

Fingerprint

Railroad cars
Cams
Neural networks
Image classification
Experiments
Decision making

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ghalyan, I. F. J., & Kapila, V. (2019). Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles. In 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018 [8707386] (Proceedings - Applied Imagery Pattern Recognition Workshop; Vol. 2018-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIPR.2018.8707386

Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles. / Ghalyan, Ibrahim F.J.; Kapila, Vikram.

2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. 8707386 (Proceedings - Applied Imagery Pattern Recognition Workshop; Vol. 2018-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ghalyan, IFJ & Kapila, V 2019, Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles. in 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018., 8707386, Proceedings - Applied Imagery Pattern Recognition Workshop, vol. 2018-October, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018, Washington, United States, 10/9/18. https://doi.org/10.1109/AIPR.2018.8707386
Ghalyan IFJ, Kapila V. Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles. In 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018. Institute of Electrical and Electronics Engineers Inc. 2019. 8707386. (Proceedings - Applied Imagery Pattern Recognition Workshop). https://doi.org/10.1109/AIPR.2018.8707386
Ghalyan, Ibrahim F.J. ; Kapila, Vikram. / Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles. 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - Applied Imagery Pattern Recognition Workshop).
@inproceedings{a877e94d03cf4739a25c9d679c4ddada,
title = "Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles",
abstract = "This paper considers the problem of modeling the surrounding environment of a driven car by using the images captured by a dash cam during the driving process. Inspired from a human driver's interpretation of the car's surrounding environment, an abstract representation of the environment is developed that can facilitate in decision-making to prevent the car's collisions with surrounding objects. The proposed technique for modeling the car's surrounding environment utilizes the dash cam to capture images as the car is driven facing multiple situations and obstacles. By relying on the human driver's interpretation of various driving scenarios, the images of the car's surrounding environment are manually grouped into classes that reflect the driver's abstract knowledge. Grouping the images allows the formulation of knowledge transfer process from the human driver to an autonomous vehicle as a classification problem, producing a meaningful and efficient representation of models arising from real-world scenarios. The framework of convolutional neural networks (CNN) is employed to model the surrounding environment of the driven car, encapsulating the abstract knowledge of the human driver. The proposed modeling approach is applied to determine its efficacy in two experimental scenarios. In the first experiment, a highway driving scenario is considered with three classes. Alternatively, in the second experiment, a scenario of driving in a residential area is addressed with six classes. Excellent modeling performance is reported for both experiments. Comparisons conducted with alternative image classification techniques reveal the superiority of the CNN for modeling the considered driving scenarios.",
author = "Ghalyan, {Ibrahim F.J.} and Vikram Kapila",
year = "2019",
month = "5",
day = "6",
doi = "10.1109/AIPR.2018.8707386",
language = "English (US)",
series = "Proceedings - Applied Imagery Pattern Recognition Workshop",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018",

}

TY - GEN

T1 - Acquiring Abstract Visual Knowledge of the Real-World Environment for Autonomous Vehicles

AU - Ghalyan, Ibrahim F.J.

AU - Kapila, Vikram

PY - 2019/5/6

Y1 - 2019/5/6

N2 - This paper considers the problem of modeling the surrounding environment of a driven car by using the images captured by a dash cam during the driving process. Inspired from a human driver's interpretation of the car's surrounding environment, an abstract representation of the environment is developed that can facilitate in decision-making to prevent the car's collisions with surrounding objects. The proposed technique for modeling the car's surrounding environment utilizes the dash cam to capture images as the car is driven facing multiple situations and obstacles. By relying on the human driver's interpretation of various driving scenarios, the images of the car's surrounding environment are manually grouped into classes that reflect the driver's abstract knowledge. Grouping the images allows the formulation of knowledge transfer process from the human driver to an autonomous vehicle as a classification problem, producing a meaningful and efficient representation of models arising from real-world scenarios. The framework of convolutional neural networks (CNN) is employed to model the surrounding environment of the driven car, encapsulating the abstract knowledge of the human driver. The proposed modeling approach is applied to determine its efficacy in two experimental scenarios. In the first experiment, a highway driving scenario is considered with three classes. Alternatively, in the second experiment, a scenario of driving in a residential area is addressed with six classes. Excellent modeling performance is reported for both experiments. Comparisons conducted with alternative image classification techniques reveal the superiority of the CNN for modeling the considered driving scenarios.

AB - This paper considers the problem of modeling the surrounding environment of a driven car by using the images captured by a dash cam during the driving process. Inspired from a human driver's interpretation of the car's surrounding environment, an abstract representation of the environment is developed that can facilitate in decision-making to prevent the car's collisions with surrounding objects. The proposed technique for modeling the car's surrounding environment utilizes the dash cam to capture images as the car is driven facing multiple situations and obstacles. By relying on the human driver's interpretation of various driving scenarios, the images of the car's surrounding environment are manually grouped into classes that reflect the driver's abstract knowledge. Grouping the images allows the formulation of knowledge transfer process from the human driver to an autonomous vehicle as a classification problem, producing a meaningful and efficient representation of models arising from real-world scenarios. The framework of convolutional neural networks (CNN) is employed to model the surrounding environment of the driven car, encapsulating the abstract knowledge of the human driver. The proposed modeling approach is applied to determine its efficacy in two experimental scenarios. In the first experiment, a highway driving scenario is considered with three classes. Alternatively, in the second experiment, a scenario of driving in a residential area is addressed with six classes. Excellent modeling performance is reported for both experiments. Comparisons conducted with alternative image classification techniques reveal the superiority of the CNN for modeling the considered driving scenarios.

UR - http://www.scopus.com/inward/record.url?scp=85065989602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065989602&partnerID=8YFLogxK

U2 - 10.1109/AIPR.2018.8707386

DO - 10.1109/AIPR.2018.8707386

M3 - Conference contribution

T3 - Proceedings - Applied Imagery Pattern Recognition Workshop

BT - 2018 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -