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

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

Author : Mr. Sittinun Thongbai Dr. Weerachai Wongweeranimit and Mr.Kittiwan Suphan

This study proposes a Transformer-Based YOLOX with a Feature Pyramid Network (FPN) Decoder for detecting road assets of different sizes in Thai highway panorama images. The study focuses on road asset detection, including kilometer signs and kilometer stones. Experimental results on the Thailand highway corpus achieved 61.5 AP, outperforming YOLOv5L by 2.56% AP on the test-dev dataset.