Improved Deep Learning-Based Vehicle Detection for Urban Applications Using Remote Sensing Imagery

Abstract

Remote sensing (RS) data can be attained from different sources, such as drones, satellites, aerial platforms, or street-level cameras. Each source has its own characteristics, including the spectral bands, spatial resolution, and temporal coverage, which may affect the performance of the vehicle detection algorithm. Vehicle detection for urban applications using remote sensing imagery (RSI) is a difficult but significant task with many real-time applications. Due to its potential in different sectors, including traffic management, urban planning, environmental monitoring, and defense, the detection of vehicles from RS data, such as aerial or satellite imagery, has received greater emphasis. Machine learning (ML), especially deep learning (DL), has proven to be effective in vehicle detection tasks. A convolutional neural network (CNN) is widely utilized to detect vehicles and automatically learn features from the input images. This study develops the Improved Deep Learning-Based Vehicle Detection for Urban Applications using Remote Sensing Imagery (IDLVD-UARSI) technique. The major aim of the IDLVD-UARSI method emphasizes the recognition and classification of vehicle targets on RSI using a hyperparameter-tuned DL model. To achieve this, the IDLVD-UARSI algorithm utilizes an improved RefineDet model for the vehicle detection and classification process. Once the vehicles are detected, the classification process takes place using the convolutional autoencoder (CAE) model. Finally, a Quantum-Based Dwarf Mongoose Optimization (QDMO) algorithm is applied to ensure an optimal hyperparameter tuning process, demonstrating the novelty of the work. The simulation results of the IDLVD-UARSI technique are obtained on a benchmark vehicle database. The simulation values indicate that the IDLVD-UARSI technique outperforms the other recent DL models, with maximum accuracy of 97.89% and 98.69% on the VEDAI and ISPRS Potsdam databases, respectively.

A Vehicle-Edge-Cloud Framework for Computational Analysis of a Fine-Tuned Deep Learning Model

“…The TF-YOLO detector [22] enhanced pedestrian detection with a novel transformer-fusion module. The IDLVD-UARSI technique [23] achieved high accuracy in vehicle detection using remote sensing imagery. In [24], the authors proposed a DL-based system for face recognition in CCTV images, aiming for high accuracy with minimal human oversight.…”

Monitoring the Distribution of Mangrove Area using Synthetic Aperture Radar (SAR) and Optic Remote Sensing Data Fusion based on Deep Learning in Kotabaru Regency, Indonesia

“…Remote sensing analyses are less expensive in labor and time than field surveys and aerial photography, and they can be readily expanded to larger scales 16) . Remote Sensing techniques are widely used to monitor the environment and natural resources over extended periods 17,18) , for purposes such as land cover classification 19,20) , urban planning 21,22) , traffic monitoring 23,24) , and land cover change detection 25,26) . In many tropical regions, remote sensing is crucial to coastal monitoring because detailed estimates of changes in forest cover are necessary due to the effects these changes have on the environment and on sustainable development 27) .…”