A Multi-Scene Roadside Lidar Benchmark towards Digital Twins of Road Intersections

Abstract

In recent years, the evolution of digital twin technology has paved the way for the construction of intelligent holographic intersections. This can be facilitated by utilizing precise point clouds from roadside lidar. With its capability of real-time monitoring, lidar plays a crucial role in enhancing intersection perception, enabling precise detection and tracking of road objects, as well as providing accurate speed estimates. Despite the introduction of few roadside lidar datasets aimed at enhancing supervised learning algorithms, their applicability to intelligent intersection monitoring remains limited. To address this, this paper presents an Intelligent Intersections (Int2sec) dataset, which exhibits several salient features: 1) it encompasses a broad array of urban intersection scenarios accompanied by a substantial quantity of object annotations; 2) the deployment of dual lidar stations facilitates a thorough scanning of scenes, thereby ensuring expansive scene coverage and mitigating the mutual occlusion phenomenon amongst objects; and 3) the dataset not only catalogues the coordinates, dimensions, and orientations of objects but also encompasses additional attributes such as tracking IDs and real-time motion statuses. Furthermore, the paper evaluates the efficacy of various prominent benchmarking networks, providing a critical analysis and prospective for future research.