Implementation of visual people counting algorithms in embedded systems
| dc.contributor.author | Rudolf, O. | |
| dc.contributor.author | Hecker, R. | |
| dc.contributor.author | Thißen, M. | |
| dc.contributor.author | Sillekens, L. | |
| dc.contributor.author | Penner, I. | |
| dc.contributor.author | Seyfarth, S. | |
| dc.contributor.author | Akelbein, J.-P. | |
| dc.contributor.author | Hergenröther, E. | |
| dc.contributor.editor | Skala, Václav | |
| dc.date.accessioned | 2025-07-30T08:54:07Z | |
| dc.date.available | 2025-07-30T08:54:07Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract-translated | Optimising the efficiency of HVAC systems represents a significant opportunity to reduce energy consumption in buildings and mitigate greenhouse gas emissions. This research evaluates low-resolution computer vision algorithms for occupancy detection on resource-constrained embedded systems. Our evaluation focuses specifically on the feasibility of deploying advanced AI object detection models on low-cost hardware platforms (under =C10) with varying computational capabilities. We systematically compared 45 different pre-trained object detection models using the COCO dataset. Among the models evaluated, those with the YOLO backbone proved to be the most suitable for this task. Quantitative analysis showed that YOLOv5n achieved a favourable balance between accuracy (AP50 = 0.944; AP50-95 = 0.584), model size (2.6 MB in RKNN format) and inference time. Performance tests on three embedded platforms - ESP32-CAM (microcontroller), Raspberry Pi Zero 2 W and Luckfox Pico Mini A (single-board computer) - revealed significant differences in inference speed, with hardware-accelerated solutions up to 10,000 times faster than software-only implementations. We have verified real-world applicability using our own ceiling-mounted wide-angle camera dataset. Future work will focus on developing a full hardware prototype, optimising the training dataset with AI-generated synthetic data, and implementing sensor fusion with audio signals for a multimodal approach. | en |
| dc.description.sponsorship | The authors thank the Federal Ministry for Economic Affairs and Climate Action (BMWK, Germany) for financial support of this research project. | |
| dc.format | 8 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.doi | http://www.doi.org/10.24132/CSRN.2025-4 | |
| dc.identifier.issn | 2464-4617 (Print) | |
| dc.identifier.issn | 2464-4625 (online) | |
| dc.identifier.uri | http://hdl.handle.net/11025/62210 | |
| dc.language.iso | en | en |
| dc.publisher | Vaclav Skala - UNION Agency | en |
| dc.rights | © Vaclav Skala - UNION Agency | en |
| dc.rights.access | openAccess | en |
| dc.subject | detekce obsazenosti | cs |
| dc.subject | počítačové vidění | cs |
| dc.subject | YOLO | cs |
| dc.subject | vestavěné systémy | cs |
| dc.subject.translated | occupancy detection | en |
| dc.subject.translated | computer vision | en |
| dc.subject.translated | YOLO | en |
| dc.subject.translated | embedded systems | en |
| dc.title | Implementation of visual people counting algorithms in embedded systems | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | conferenceObject | en |
| dc.type.status | Peer reviewed | en |
| dc.type.version | publishedVersion | en |
| local.files.count | 1 | * |
| local.files.size | 2267404 | * |
| local.has.files | yes | * |