Parkur: Digital Twin Parking System with Nearest-Slot Allocation and Edge AI-Based Occupancy Monitoring

Conventional parking management still relies on manual observation or fragmented dashboards, so field conditions are difficult to monitor quickly and comprehensively. Existing digital parking systems typically display numbers, sensor statuses, or CCTV feeds separately, forcing operators to fuse information mentally; the result is low visibility of slot occupancy, limited monitoring parameters, and no interactive centralized visualization. This paper presents Parkur, a digital twin parking system that unifies the physical parking area, IoT data streams, and an interactive virtual environment in a plug-and-play architecture. The system is organized into eight layers: physical devices, device connectivity and integration, edge intelligence, data platform, digital twin core, analytics and decision, experience dashboard, and a closed feedback loop. Vehicle detection uses the YOLO family of detectors, multi-object tracking uses ByteTrack, and automatic number plate recognition combines YOLO-based plate detection with PaddleOCR, all executed on edge devices such as the NVIDIA Jetson Orin Nano. Slot occupancy is derived from a rule engine with geofencing, and a rule-based alert engine issues real-time notifications. A key innovation is the nearest-slot allocation algorithm, which assigns each entering vehicle the closest available slot to reduce cruising and disorder. The dashboard integrates a 3D visualization area, live CCTV preview, occupancy statistics, and a tap-to-inspect slot inspector. Compared with previous fragmented monitoring approaches, Parkur provides centralized interactive visibility purpose-built for parking operators. The paper details the layered architecture, the edge AI perception pipeline, and the allocation algorithm, and presents the implemented 3D dashboard of the prototype. The main contribution is a complete plug-and-play digital twin architecture for parking management that couples edge AI perception with nearest-slot allocation in one interactive environment.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-06
DOI
https://doi.org/10.5281/zenodo.24011020
Primary Topic
Smart Parking Systems Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Parkur: Digital Twin Parking System with Nearest-Slot Allocation and Edge AI-Based Occupancy Monitoring

Muhammad Rizqi Syahal Maulana, Brieva Ommr
3 links
Zenodo (CERN European Organization for Nuclear Research)
Smart Parking Systems Research
article

Parkur: Digital Twin Parking System with Nearest-Slot Allocation and Edge AI-Based Occupancy Monitoring

Muhammad Rizqi Syahal Maulana, Brieva Ommr
article en

Abstract

Conventional parking management still relies on manual observation or fragmented dashboards, so field conditions are difficult to monitor quickly and comprehensively. Existing digital parking systems typically display numbers, sensor statuses, or CCTV feeds separately, forcing operators to fuse information mentally; the result is low visibility of slot occupancy, limited monitoring parameters, and no interactive centralized visualization. This paper presents Parkur, a digital twin parking system that unifies the physical parking area, IoT data streams, and an interactive virtual environment in a plug-and-play architecture. The system is organized into eight layers: physical devices, device connectivity and integration, edge intelligence, data platform, digital twin core, analytics and decision, experience dashboard, and a closed feedback loop. Vehicle detection uses the YOLO family of detectors, multi-object tracking uses ByteTrack, and automatic number plate recognition combines YOLO-based plate detection with PaddleOCR, all executed on edge devices such as the NVIDIA Jetson Orin Nano. Slot occupancy is derived from a rule engine with geofencing, and a rule-based alert engine issues real-time notifications. A key innovation is the nearest-slot allocation algorithm, which assigns each entering vehicle the closest available slot to reduce cruising and disorder. The dashboard integrates a 3D visualization area, live CCTV preview, occupancy statistics, and a tap-to-inspect slot inspector. Compared with previous fragmented monitoring approaches, Parkur provides centralized interactive visibility purpose-built for parking operators. The paper details the layered architecture, the edge AI perception pipeline, and the allocation algorithm, and presents the implemented 3D dashboard of the prototype. The main contribution is a complete plug-and-play digital twin architecture for parking management that couples edge AI perception with nearest-slot allocation in one interactive environment.

Zenodo (CERN European Organization for Nuclear Research)
Industry, innovation and infrastructure, Sustainable cities and communities
Openalex Percentile: Top 17%
Smart Parking Systems Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon