CNN with New Spatial Pyramid Pooling and Advanced Filter-Based Techniques: Revolutionizing Traffic Monitoring via Aerial Images

Irfan Javid, Rozaida Ghazali, Waddah Saeed (), Tuba Batool and Ebrahim Al-Wajih
Additional contact information
Irfan Javid: Department of Computer Science and IT, University of Poonch, Rawalakot 12350, Pakistan
Rozaida Ghazali: Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Batu Pahat 86400, Malaysia
Waddah Saeed: School of Computer Science and Informatics, De Montfort University, Leicester LE1 9BH, UK
Tuba Batool: Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Batu Pahat 86400, Malaysia
Ebrahim Al-Wajih: Society Development & Continuing Education Center, Hodeidah University, Hodeidah P.O. Box 3114, Yemen

Sustainability, 2023, vol. 16, issue 1, 1-13

Abstract: The escalation in vehicular traffic, in conjunction with global population growth, has precipitated heightened road congestion, augmented air pollution, and a rise in vehicular accidents. Over the past decade, the global vehicular count has witnessed a substantial surge. In this context, traffic monitoring emerges as a paramount challenge, especially within developing nations. This research introduces an innovative system for vehicle detection and categorization aimed at intelligent traffic monitoring. The system utilizes a convolutional neural network-based U-Net model for the segmentation of aerial images. After segmentation, the outputs are further analyzed for vehicle identification. This vehicle detection utilizes an advanced spatial pyramid pooling (ASPP) mechanism which refines the spatial partitions of the image and captures intricate details, enhancing the accuracy and precision of the detection process. Detected vehicles are then categorized into distinct subcategories. For the effective management and control of high-density traffic flow, the extended Kalman filter (EKF) technique is employed, thereby reducing the reliance on human oversight. In experimental evaluations, our proposed model exhibits exemplary vehicle detection capabilities across the German Aerospace Center (DLR3K) and the Vehicle Detection in Aerial Imagery (VEDAI) datasets. Potential applications of the system encompass vehicle identification in traffic streams, traffic congestion assessment, intersection traffic density analysis, differentiation of vehicle types, and pedestrian pathway determination.

Keywords: spatial pyramid pooling; U-Net; semantic segmentation; extended Kalman filter; vehicle categorization and recognition (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/16/1/117/pdf (application/pdf)
https://www.mdpi.com/2071-1050/16/1/117/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:16:y:2023:i:1:p:117-:d:1305224

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().