Hu, Jia and Luo, Shuyuan and Lai, Jintao and Liu, Chang (2025) Enhanced Infrastructure-Enabled Perception System Based on Edge Computing. IEEE INTERNET OF THINGS JOURNAL, 12 (11). pp. 16493-16510. ISSN 2327-4662 10.1109/JIOT.2025.3532317

Text Hu_16493_36184036_z.pdf Restricted to Registered users only Download (7MB) | Request a copy

Abstract

Perception technology plays a crucial role in vehicle automation, yet traditional approaches solely rely on onboard computing and have inherent limitations in perception range. To improve perception range, edge computing is introduced. Through edge computing, some perception computing tasks can be offloaded from onboard sensors to sensors installed on roadside infrastructures. This infrastructure-enabled perception (IEP) expands perception range beyond what onboard sensors alone can achieve. However, existing IEP systems have limited precision in long-distance perception and require costly sensors for optimal performance. To enhance the performance without significant financial investment, this article proposes an enhanced IEP system. The proposed IEP system adopts a virtual-detector-based perception solution, designing multiple virtual detectors to detect vehicle arrivals. Unlike traditional IEP approaches, the proposed system does not rely on dense data points for estimating vehicle geometry. Instead, it bypasses the geometry-estimation step and only needs sparse data points to detect vehicle arrivals. Consequently, even with sparse data points at long perception distances, our IEP system can achieve high precision in long-distance perception. Due to this enhanced solution, the proposed IEP system has the following features: 1) ensuring wide perception range; 2) enabling cm-level precision perception; 3) maintaining robustness against perception distances, vehicle speeds, and sensor frequencies; 4) compatible with mass-produced and cost-effective sensors; and 5) laying a foundation for infrastructure-enabled cooperative driving. Experimental validation confirms the system's advanced features and demonstrates its superiority over the state-of-the-art IEP system. It achieves a wide perception range up to 150 m and a low localization error down to 6.500 cm. Further investigation suggests that the IEP system should primarily be deployed on expressways and implemented for speed-related cooperative driving applications, such as speed harmonization.

Item Type:	Article
Uncontrolled Keywords:	sensors; TRACKING; vehicles; accuracy; GEOMETRY; Costs; DETECTORS; Robustness; Internet of Things; Sensor systems; Edge Computing; Edge Computing; Engineering, Electrical & Electronic; Computer Science, Information Systems; Vehicle localization; Cooperative driving; Point cloud compression; infrastructure-enabled perception (IEP);
Subjects:	Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Divisions:	Distributed Events Analysis Research Laboratory
SWORD Depositor:	MTMT Injector
Depositing User:	MTMT Injector
Date Deposited:	07 Jul 2025 05:00
Last Modified:	07 Jul 2025 05:00
URI:	https://eprints.sztaki.hu/id/eprint/10932

Update Item