• About us
  • Product & Services

Research & Videos

หมวดหมู่บทความ

Diffusion-Based Synthetic Augmentation for Vehicle Detection

This study investigates diffusion-based synthetic data augmentation to improve vehicle detection under adverse weather and lighting conditions. It examines reference image quality and mAP-guided data allocation to address class imbalance and improve detection robustness.
  • 1
See more

Comparative Performance of Conventional and Plastic Waste-Modified Hot Mix Asphalt Concrete

This study investigates the use of recycled plastic waste as an additive in hot mix asphalt concrete for road construction. The research team developed mixture proportions and conducted comprehensive laboratory and field performance evaluations in accordance with the standards of the Department of Highways, Thailand.
  • 3
See more

Study and Development of Prototype to Explore and Evaluate the Pavement Friction for Safety

This research studies and develops a prototype device for measuring Mean Profile Depth (MPD), representing pavement macro-texture, as supporting data for pavement friction evaluation and road safety management.
  • 4
See more

Optimizing Budget Allocation for Low-Volume Roads Through the AHP-TOPSIS Approach

This study develops and evaluates an AHP-TOPSIS framework for prioritizing low-volume road maintenance under budget constraints. The approach integrates multiple criteria, including pavement performance, accessibility, and regional distribution, to support more balanced budget allocation.
  • 3
See more

Study and Development of Prototype to Explore and Evaluate the Pavement Friction for Safety

This research studies and develops a prototype device for measuring Mean Profile Depth (MPD), representing pavement macro-texture, as supporting data for pavement friction evaluation and road safety management.
  • 2
See more

Precision Road Infrastructure Management: Monocular Vision-Based 3D Damage Detection and Assessment

This research presents a computer vision-based approach for road pavement damage detection and assessment using a monocular camera mounted on a vehicle. The proposed system integrates the YOLO9tr object detection model with image-based depth estimation to detect damage types and estimate their dimensions in 3D.
  • 4
See more

Assessing the Potential and Strength of Local Administrative Organization in Local Roadway Field

This research examines the potential and strength of local administrative organizations in the local roadway field, focusing on their capacity to undertake local roadway-related operations.
  • 4
See more

YOL026-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling

This research presents YOL026-RD, a network for detecting road surface damage from survey imagery. It incorporates Learnable Contrast Enhancement and Edge-Guided Downsampling to improve the detection of small-scale damage and preserve image details during processing.
  • 4
See more

Object Detection of Road Assets Using Transformer-Based YOLOX with Feature Pyramid Decoder on Thai Highway Panorama

This study presents road asset detection in Thai highway panorama images using Transformer-Based YOLOX with a Feature Pyramid Network (FPN) Decoder, focusing on kilometer signs and kilometer stones. The model achieved 61.5 AP, outperforming YOLOv5L by 2.56% AP on the test-dev dataset.
  • 4
See more

iNFRA’s Work Featured in the Civil Insight Series

iNFRA Co., Ltd. is proud to announce that its article, “A New Era of Traffic Data Collection with Artificial Intelligence,” has been featured in Civil Insight Series Content (Ep.46 DIT-CACE/004) by the Civil Engineering Committee of the Engineering Institute of Thailand under H.M. The King’s Patronage (EIT). This recognition reflects the company’s expertise in applying Artificial Intelligence (AI) to support traffic engineering and infrastructure development.
  • 3
See more

Tags

Our Social