sayyedabrarakhtar.com.np
theme
~/portfolio

// THESIS GUIDANCE PORTAL · Engineering

Smart Traffic Management System for Kathmandu

Level: MasterDifficulty: Advanced

1. Introduction & Problem Statement

Overview: Design an AI-based adaptive traffic signal control system for Kathmandu's major intersections. Uses real-time vehicle counting via YOLO object detection to optimize signal timing.

Background Context (Nepal): Kathmandu's traffic congestion causes an estimated NPR 28 billion annual economic loss. Traditional fixed-time signals are inefficient. Computer vision-based adaptive systems can reduce congestion by 20-40%.

2. Research Objectives

  • Implement real-time vehicle detection using YOLOv8
  • Design adaptive signal timing algorithm
  • Simulate system on Kathmandu intersection data
  • Build control dashboard for traffic police
  • Measure congestion reduction vs fixed-time baseline

3. Proposed Methodology

  1. Video data collection from Kathmandu intersections
  2. YOLOv8 model training for Nepali traffic conditions
  3. Adaptive algorithm design — reinforcement learning
  4. SUMO traffic simulation for evaluation
  5. Dashboard development for deployment

4. Thesis Chapter-by-Chapter Outline

Chapter 1: IntroductionTU/KU standard

Kathmandu traffic problem, existing systems, research scope

Chapter 2: Literature ReviewTU/KU standard

Adaptive traffic systems, computer vision, RL in traffic control

Chapter 3: System ArchitectureTU/KU standard

Camera setup, detection pipeline, adaptive algorithm, dashboard

Chapter 4: ImplementationTU/KU standard

YOLO training, algorithm coding, simulation setup

Chapter 5: Simulation & ResultsTU/KU standard

SUMO simulation results, comparison analysis

Chapter 6: ConclusionTU/KU standard

Findings, deployment recommendations, future work

5. Recommended Tools & Technologies

To implement the practical, technical, or analytical portions of this thesis topic, the following software tools, libraries, or APIs are recommended:

PythonYOLOv8SUMOOpenCVPyTorchReactFastAPI

6. Core References & Citations

  • [1]DoR Nepal — Road Transport Statistics
  • [2]Redmon, J. et al. (2016). You Only Look Once: Unified, Real-Time Object Detection.
available for workKathmandu, Nepal 🇳🇵contact@sayyedabrarakhtar.com.np