Mitigating Port-Induced Traffic Congestion in Chattogram: A Theoretical SUMO Simulation Framework for the Agrabad–Freeport Corridor

Wed, 23 Sep 2026 00:00:00 +0000

Port-related freight activity, heterogeneous traffic, weak lane discipline, and roadside friction contribute to persistent congestion along major urban corridors in Chattogram, Bangladesh. This study develops an evidence-informed microscopic traffic simulation framework using the Simulation of Urban Mobility (SUMO) platform for the Agrabad–Freeport corridor, with particular focus on the Barik Building–Saltgola section. Five scenarios are considered: the existing-condition baseline, adaptive signal control, lane channelization, a dedicated Non-Motorized Transport (NMT) lane, and a combined strategy. Because corridor-specific traffic counts, signal timings, trajectory data, and validated travel-time observations were unavailable, the study is structured as a theoretical framework rather than a locally calibrated simulation. Published intervention effects were transferred only where sufficiently comparable evidence existed, while unsupported outcomes were retained as theoretical or sensitivity-based projections. Adaptive signal control showed the most comprehensive evidence base, with reported reductions of 13.6% in travel time, 14.3% in intersection delay, 8.9% in queue length, and approximately 9% in both CO₂ emissions and fuel consumption, together with a 47.9% increase in mean network speed. Lane channelization indicated a 10%–30% travel-time reduction based on Bangladesh-specific evidence. In contrast, the dedicated NMT lane revealed a context-dependent safety–capacity trade-off, while the combined strategy was treated as non-additive because the interventions influence overlapping network processes. The framework provides a transparent basis for prioritizing future field data collection, calibration, validation, and integrated scenario testing in a freight-intensive urban corridor.

TrafficVisionAI: A Real-Time Deep Learning Framework for Automated Vehicle Counting and Speed Estimation using YOLOv8 and ByteTrack

Maloani Saidi Georges — Fri, 25 Sep 2026 00:00:00 +0000

Rapid urbanization has escalated the urgent need for intelligent transportation systems capable of alleviating traffic congestion, enhancing road safety, and enabling data-driven urban planning. Traditional manual surveillance methods are notoriously prone to human error, labor-intensive, and incapable of delivering real-time analytics at scale. This paper presents the design, implementation, and evaluation of TrafficVisionAI, a lightweight and cost-effective deep learning framework for automated vehicle detection, tracking, and speed estimation. The system leverages the YOLOv8n model to perform object detection across four specific COCO classes: Cars, Motorcycles, Buses, and Trucks. To ensure consistent identity preservation in complex, occluded traffic environments, the ByteTrack algorithm is integrated to assign persistent IDs to moving vehicles. The core novelty of this work lies in the seamless integration of a custom pixel-to-meter scaling factor for real-time speed estimation (in km/h), coupled with a professional, feature-rich Heads-Up Display (HUD) that provides live traffic statistics and system status (FPS, timestamp). Additionally, automated video archiving via OpenCV ensures high-volume annotated data is retained for post-hoc analysis. Experimental results demonstrate the system's robust capability to classify and count vehicles, while preliminary testing highlights a performance trade-off of 4 FPS on standard CPU hardware. The findings confirm that deep learning provides a scalable, accessible, and highly efficient solution for modern intelligent transportation systems.

International Journal of Traffic Management in Transportation Network (p: 3107-9504)

Mitigating Port-Induced Traffic Congestion in Chattogram: A Theoretical SUMO Simulation Framework for the Agrabad–Freeport Corridor

TrafficVisionAI: A Real-Time Deep Learning Framework for Automated Vehicle Counting and Speed Estimation using YOLOv8 and ByteTrack