Visual pollution real images benchmark dataset on the public roads

Mohammad AlElaiwi; Mugahed A Al-Antari; Hafiz Farooq Ahmad; Areeba Azhar; Badar Almarri; Jamil Hussain

doi:10.1016/j.dib.2023.109491

Visual pollution real images benchmark dataset on the public roads

Data Brief. 2023 Aug 10:50:109491. doi: 10.1016/j.dib.2023.109491. eCollection 2023 Oct.

Authors

Mohammad AlElaiwi¹, Mugahed A Al-Antari², Hafiz Farooq Ahmad¹, Areeba Azhar³, Badar Almarri¹, Jamil Hussain⁴

Affiliations

¹ Computer Science Department, College of Computer Sciences and Information Technology (CCSIT), King Faisal University, P.O. Box 400, Al-Ahsa, 31982, Saudi Arabia.
² Department of Artificial Intelligence, College of Software & Convergence Technology, Daeyang AI Center, Sejong University, Seoul, 05006, Korea.
³ Department of Mathematics, College of Natural & Agricultural Sciences, University of Califor-nia-Riverside (UCR), Riverside, CA, USA.
⁴ Department of Data Science, College of Software & Convergence Technology, Daeyang AI Center, Sejong University, Seoul, 05006, Korea.

Abstract

The term quality of life (QoL) refers to a wide range of multifaceted concepts that often involve subjective assessments of both positive and negative aspects of life. It is difficult to quantify QoL as the word has varied meanings in different academic areas and may have different connotations in different circumstances. The five sectors most commonly associated with QoL, however, are Health, Education, Environmental Quality, Personal Security, Civic Engagement, and Work-Life Balance. An emerging issue that falls under environmental quality is visual pollution (VP) which, as detailed in this study, refers to disruptive presences that limit visual ability in public roads with an emphasis on excavation barriers, potholes, and dilapidated sidewalks. Quantifying VP has always been difficult due to its subjective nature and lack of a consistent set of rules for systematic assessment of visual pollution. This emphasizes the need for research and module development that will allow government agencies to automatically predict and detect VP. Our dataset was collected from different regions in the Kingdom of Saudi Arabia (KSA) via the Ministry of Municipal and Rural Affairs and Housing (MOMRAH) as a part of a VP campaign to improve Saudi Arabia's urban landscape. It consists of 34,460 RGB images separated into three distinct classes: excavation barriers, potholes, and dilapidated sidewalks. To annotate all images for detection (i.e., bounding box) and classification (i.e., classification label) tasks, the deep active learning strategy (DAL) is used where an initial 1,200 VP images (i.e., 400 images per class) are manually annotated by four experts. Images with more than one object increase the number of training object ROIs which are recorded to be 8,417 for excavation barriers, 25,975 for potholes, and 7,412 for dilapidated sidewalks. The MOMRAH dataset is publicly published to enrich the research domain with the new VP image dataset.

Keywords: Active learning; Artificial intelligence; Computer vision; Deep learning; Image classification; Machine learning; Pollution.