Zubin Bhuyan
Postdoctoral Research, UMass Lowell
Intelligent Transportation Systems |
Deep Learning | Computer Vision

Zubin Bhuyan is an AI researcher at the University of Massachusetts Lowell, specializing in deep learning and computer vision algorithms for Intelligent Transportation Systems. He holds a PhD in Computer Science. His research focuses on:

• Improving detection and analytics algorithms for vehicle and pedestrian safety
• Developing vehicle tracking systems using thermal and RGB cameras from drones and ground-level setups
• Conducting LiDAR data analysis for semantic segmentation, object detection, and scene understanding
• Creating multimodal datasets to analyze highway traffic in work zones

• Bhuyan, Z., Wu, L., Xie, Y., Cao, Y., & Liu, B. (2024)."Using Nighttime Thermal UAV Videos and Deep Learning To Analyze Highway Work Zone Traffic Dynamics". 27th IEEE International Conference on Intelligent Transportation Systems (ITSC).  Github
• Bhuyan, Z., Xie, Y., Angkea Reach Rith (2024)."AI Framework for Midblock Crosswalk Detection Across Massachusetts", 2024 MassDOT Transportation Innovation Conference. [POSTER]     Github
• Bhuyan, Z., Xie, Y., Liu, R., Cao, Y., & Liu, B. (2024)."Towards Safer Highway Work Zones: Insights from Deep Learning Analysis of Thermal Footage". 17th IFAC Symposium on Control in Transportation Systems.    Github  
• Liu, R., Xie, Y., Bhuyan, Z. (2024). "Assessing the Impacts of Merge and Speed Control Strategies on Highway Work Zone Safety and Operations Using Artificial Intelligence and Advanced Sensors". 17th IFAC Symposium on Control in Transportation Systems.    
• Bhuyan, Z., Chen, Q., Xie, Y., Cao, Y., & Liu, B. (2023). "Modeling the Risk of Truck Rollover Crashes on Highway Ramps Using Drone Video Data and Mask-RCNN". 26th IEEE International Conference on Intelligent Transportation Systems (ITSC).       Github  

Recent Projects

CrosswalkNet: A deep learning framework for pedestrian crosswalk detection Github  

CrosswalkNet is a deep learning framework optimized for detecting crosswalks in aerial images across over 10,000 square miles. It utilizes high-resolution aerial imagery from MassGIS (2019, 2021) captured with an UltraCam Eagle M3 camera.

Smart Work Zone Control and Performance Evaluation Based on Trajectory Data - Thermal UAV Video Data Github  

Thermal imaging analysis solution aimed at vehicle tracking in drone-captured videos, incorporating oriented bounding boxes and SHAI for superior detection capabilities.

Towards Safer Highway Work Zones: Insights from Deep Learning Analysis of Thermal Footage Github  

This research project aims to develop methods to extract vehicle trajectories, use the trajectories to analyze driver behavior, particularly lane-changing behavior under different conditions, and identify safety hazards and opportunities to improve work zone safety and operations. (MassDOT Research Program with funding from FHWA SPR funds.) Research in Progress-Record

Transportation Data Analytics and Pilot Case Studies Using Deep Learning Github  

Current Status of Transportation Data Analytics and Pilot Case Studies Using Artificial Intelligence." sponsored by the New England Transportation Consortium (NETC) Project Webpage

Uncovering the Root Causes of Truck Rollover Crashes on Highway Ramps Github  

Vehicle detection using modified Mask-RCNN: Oriented Bounding Box (OBB) + instance segmentation. Download Technical Report

Massachusetts-Specific Trip Generation Models for Land Use Projects Github  

The primary focus is on utilizing location-based service (LBS) data to create accurate and efficient trip generation models, particularly for urban sites that benefit from proximity to public transportation. Download Technical Report

Advisor and Committee

Contact