Object Detection using Oriented Window Learning Vi-sion Transformer: Roadway Assets Recognition

TL;DR

This paper introduces OWL-ViT, a novel vision transformer model with oriented window learning, tailored for roadway asset detection in transportation systems, demonstrating high efficiency and robustness across diverse scenarios.

Contribution

It presents a new method integrating OWL-ViT within a one-shot learning framework for effective roadway asset recognition, addressing challenges of data variability and object diversity.

Findings

High detection accuracy across multiple roadway assets

Robust performance under varying resolutions and contexts

Enhanced detection consistency and reliability

Abstract

Object detection is a critical component of transportation systems, particularly for applications such as autonomous driving, traffic monitoring, and infrastructure maintenance. Traditional object detection methods often struggle with limited data and variability in object appearance. The Oriented Window Learning Vision Transformer (OWL-ViT) offers a novel approach by adapting window orientations to the geometry and existence of objects, making it highly suitable for detecting diverse roadway assets. This study leverages OWL-ViT within a one-shot learning framework to recognize transportation infrastructure components, such as traffic signs, poles, pavement, and cracks. This study presents a novel method for roadway asset detection using OWL-ViT. We conducted a series of experiments to evaluate the performance of the model in terms of detection consistency, semantic flexibility, visual context adaptability, resolution robustness, and impact of non-max suppression. The results demonstrate the high efficiency and reliability of the OWL-ViT across various scenarios, underscoring its potential to enhance the safety and efficiency of intelligent transportation systems.