One Convolutional Layer Model for Parking Occupancy Detection

Soumia Goumiri; Dalila Benboudjema; Wojciech Pieczynski

doi:10.1109/ISC253183.2021.9562946

One Convolutional Layer Model for Parking Occupancy Detection

Soumia Goumiri
, Dalila Benboudjema
, Wojciech Pieczynski

Natl. Institute of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

Convolutional Neural Networks (CNN) have recently performed wonders in image recognition tasks. In this paper, we propose a new CNN model composed of one convolutional layer, which we called 1Conv. We apply 1Conv for the problem of parking space detection. We used the most popular datasets to evaluate the performance of our model that are: National Research Council Park (CNRPark), National Research Council Park Extension (\mathbf{CNRPark}+\mathbf{EXT}), and Parking Lot (PKLot). We compared the results with mAlexNet, a CNN model similar to 1Conv. The results show that our model outperforms mAlexNet in terms of accuracy, Area Under the Curve (AUC), and execution time. The better accuracy of 1 Conv compared to mAlexNet was 99.06% against 90.71 % using CNRPark dataset. Which means that our model outperforms mAlexNet by 9% in term of accuracy. Execution time of mAlexNet is double compared to 1Conv.

Original language	English
Title of host publication	2021 IEEE International Smart Cities Conference, ISC2 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665449199
DOIs	https://doi.org/10.1109/ISC253183.2021.9562946
Publication status	Published - 7 Sept 2021
Event	2021 IEEE International Smart Cities Conference, ISC2 2021 - Manchester, United Kingdom Duration: 7 Sept 2021 → 10 Sept 2021

Publication series

Name	2021 IEEE International Smart Cities Conference, ISC2 2021

Conference

Conference	2021 IEEE International Smart Cities Conference, ISC2 2021
Country/Territory	United Kingdom
City	Manchester
Period	7/09/21 → 10/09/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy
SDG 11 Sustainable Cities and Communities

Keywords

Convolutional Neural Networks (CNN) model
deep learning
parking space detection

Access to Document

10.1109/ISC253183.2021.9562946

Cite this

@inproceedings{42a19f211e344845992520b122dbbea5,

title = "One Convolutional Layer Model for Parking Occupancy Detection",

abstract = "Convolutional Neural Networks (CNN) have recently performed wonders in image recognition tasks. In this paper, we propose a new CNN model composed of one convolutional layer, which we called 1Conv. We apply 1Conv for the problem of parking space detection. We used the most popular datasets to evaluate the performance of our model that are: National Research Council Park (CNRPark), National Research Council Park Extension (\textbackslash{}mathbf\{CNRPark\}+\textbackslash{}mathbf\{EXT\}), and Parking Lot (PKLot). We compared the results with mAlexNet, a CNN model similar to 1Conv. The results show that our model outperforms mAlexNet in terms of accuracy, Area Under the Curve (AUC), and execution time. The better accuracy of 1 Conv compared to mAlexNet was 99.06\% against 90.71 \% using CNRPark dataset. Which means that our model outperforms mAlexNet by 9\% in term of accuracy. Execution time of mAlexNet is double compared to 1Conv.",

keywords = "Convolutional Neural Networks (CNN) model, deep learning, parking space detection",

author = "Soumia Goumiri and Dalila Benboudjema and Wojciech Pieczynski",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Smart Cities Conference, ISC2 2021 ; Conference date: 07-09-2021 Through 10-09-2021",

year = "2021",

month = sep,

day = "7",

doi = "10.1109/ISC253183.2021.9562946",

language = "English",

series = "2021 IEEE International Smart Cities Conference, ISC2 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 IEEE International Smart Cities Conference, ISC2 2021",

}

Goumiri, S, Benboudjema, D & Pieczynski, W 2021, One Convolutional Layer Model for Parking Occupancy Detection. in 2021 IEEE International Smart Cities Conference, ISC2 2021. 2021 IEEE International Smart Cities Conference, ISC2 2021, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE International Smart Cities Conference, ISC2 2021, Manchester, United Kingdom, 7/09/21. https://doi.org/10.1109/ISC253183.2021.9562946

One Convolutional Layer Model for Parking Occupancy Detection. / Goumiri, Soumia; Benboudjema, Dalila; Pieczynski, Wojciech.
2021 IEEE International Smart Cities Conference, ISC2 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE International Smart Cities Conference, ISC2 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - One Convolutional Layer Model for Parking Occupancy Detection

AU - Goumiri, Soumia

AU - Benboudjema, Dalila

AU - Pieczynski, Wojciech

PY - 2021/9/7

Y1 - 2021/9/7

N2 - Convolutional Neural Networks (CNN) have recently performed wonders in image recognition tasks. In this paper, we propose a new CNN model composed of one convolutional layer, which we called 1Conv. We apply 1Conv for the problem of parking space detection. We used the most popular datasets to evaluate the performance of our model that are: National Research Council Park (CNRPark), National Research Council Park Extension (\mathbf{CNRPark}+\mathbf{EXT}), and Parking Lot (PKLot). We compared the results with mAlexNet, a CNN model similar to 1Conv. The results show that our model outperforms mAlexNet in terms of accuracy, Area Under the Curve (AUC), and execution time. The better accuracy of 1 Conv compared to mAlexNet was 99.06% against 90.71 % using CNRPark dataset. Which means that our model outperforms mAlexNet by 9% in term of accuracy. Execution time of mAlexNet is double compared to 1Conv.

AB - Convolutional Neural Networks (CNN) have recently performed wonders in image recognition tasks. In this paper, we propose a new CNN model composed of one convolutional layer, which we called 1Conv. We apply 1Conv for the problem of parking space detection. We used the most popular datasets to evaluate the performance of our model that are: National Research Council Park (CNRPark), National Research Council Park Extension (\mathbf{CNRPark}+\mathbf{EXT}), and Parking Lot (PKLot). We compared the results with mAlexNet, a CNN model similar to 1Conv. The results show that our model outperforms mAlexNet in terms of accuracy, Area Under the Curve (AUC), and execution time. The better accuracy of 1 Conv compared to mAlexNet was 99.06% against 90.71 % using CNRPark dataset. Which means that our model outperforms mAlexNet by 9% in term of accuracy. Execution time of mAlexNet is double compared to 1Conv.

KW - Convolutional Neural Networks (CNN) model

KW - deep learning

KW - parking space detection

U2 - 10.1109/ISC253183.2021.9562946

DO - 10.1109/ISC253183.2021.9562946

M3 - Conference contribution

AN - SCOPUS:85118153579

T3 - 2021 IEEE International Smart Cities Conference, ISC2 2021

BT - 2021 IEEE International Smart Cities Conference, ISC2 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Smart Cities Conference, ISC2 2021

Y2 - 7 September 2021 through 10 September 2021

ER -

One Convolutional Layer Model for Parking Occupancy Detection

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this