Parking Occupancy Detection through Adaptive Multi-Sensor Camera-CNN Fusion

Lassen V, Lübke M, Franchi N (2025)


Publication Language: English

Publication Type: Journal article, Letter

Publication year: 2025

Journal

DOI: 10.1109/LSENS.2025.3593908

Abstract

A robust multi-camera sensor system for parking-occupancy detection is introduced, combining convolutional neural networks (CNNs) with an adaptive fusion mechanism that leverages angular diversity. The proposed pipeline integrates viewpoint-specific bounding-box components and a distortion-reduction module that compensates for perspective-induced deformations. Under different azimuth angles and illumination conditions, including overcast, sunny, and nighttime scenarios, the fusion approach consistently outperformed single-camera systems. Notably, fusing cameras at 0∘ and 90∘ yielded an Intersection-over-Union (IoU) of 0.898 without correction, while the distortion-reduction module improved IoU from 0.734 to 0.856 in geometrically challenging cases. The method also maintained robust performance in low-light environments, where individual camera views degraded. Designed for scalability and minimal calibration effort, the architecture supports geometry-consistent localization across multiple sensor perspectives. These results demonstrate that combining angular fusion with correction-aware processing offers substantial gains in precision and robustness. The system is particularly suited for real-world deployment in smart parking applications under complex environmental conditions.

Authors with CRIS profile

How to cite

APA:

Lassen, V., Lübke, M., & Franchi, N. (2025). Parking Occupancy Detection through Adaptive Multi-Sensor Camera-CNN Fusion. IEEE Sensors Letters. https://doi.org/10.1109/LSENS.2025.3593908

MLA:

Lassen, Vincent, Maximilian Lübke, and Norman Franchi. "Parking Occupancy Detection through Adaptive Multi-Sensor Camera-CNN Fusion." IEEE Sensors Letters (2025).

BibTeX: Download