Enhancing Object Tracking in Smart City Intelligent Transportation Systems: A Track-by-Detection Approach Utilizing Satellite Video Monitoring

Ensuring effective object tracking within Intelligent Transportation Systems (ITS) in smart cities is pivotal for enhancing urban mobility and sustainability. However, challenges arise, particularly in scenarios with occlusions and adverse weather conditions, where traditional methods may fall short in ensuring safety. To address these challenges, a novel track-by-detection approach is introduced aimed at enhancing transportation systems. The approach integrates key components, including the Detection Transformer (DETR) for emphasizing global context, and the You Only Look Once version 7 (YOLOv7) renowned for capturing local context. Additionally, the deep sort tracking filter is incorporated to enhance object tracking accuracy. A pivotal aspect of the approach lies in the utilization of the deep sort of filter for object tracking, preceded by preprocessing with the Principal Component Analysis (PCA) method to refine tracking outcomes. This buffering approach significantly improves tracking quality by reducing noise and enhancing feature representation. Moreover, the approach leverages tracking from satellite videos, enabling comprehensive monitoring of transportation activities across vast regions. The refined tracking outputs, including those from satellite videos, are fused with direct outputs from the trackers obtained from both YOLOv7 and DETR. These integrated fused buffered tracked bounding boxes demonstrate superior performance compared to individual approaches. Validation using simulated imagery under cloudy conditions, incorporating the Motion Evaluation Metric (MOT), showcases enhanced accuracy across various transportation objects. Implementing this approach in ITS promise’s benefits such as enhanced traffic management and increased efficiency in public transportation. This underscores the role of Artificial Intelligence (AI) in revolutionizing smart city mobility.

I. Introduction

Smart city technologies play a crucial role in managing the rapid urbanization witnessed globally, offering solutions to economic and environmental challenges arising from urban population growth. By integrating traditional infrastructure with technology, smart cities aim to create more efficient, sustainable, and accessible urban systems that cater to the needs of residents, thereby revolutionizing traditional city management practices [1]. Among the key components of smart cities, (ITS) are designed to enhance transportation safety and mobility, reduce environmental impact, promote sustainable development, and boost productivity [2]. Leveraging advanced data communication and processing technologies, ITS facilitates real-time data analysis from diverse sources to support informed decision-making, addressing transportation-related issues such as traffic congestion and accidents [3]. The advent of AI technologies has further revolutionized transportation systems, enabling data-driven decision-making and enhancing safety, efficiency, and sustainability across various modes of transportation [4]. Machine learning (ML) methods, a subset of AI, serve as the cognitive backbone of ITS, determining the intelligence and reliability of transportation systems. Particularly, deep learning (DL) methods have emerged as a powerful tool in classification and prediction tasks within ITS, driving advancements in various areas of transportation management [5].