Details

Ocenjevanje zasedenosti zaprtih prostorov s pasivnim zaznavanjem oglaševalnih paketov BLE
ID Markizeti, Matic (Author), ID Kos, Andrej (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,26 MB)
MD5: 47946E6FAAA44A2621550666A2E09AAB

Abstract
Magistrsko delo obravnava merjenje zasedenosti zaprtih prostorov s pasivnim zaznavanjem oglaševalnih paketov BLE. Izhodišče je opažanje, da skoraj vsaka mobilna naprava neprestano oddaja oglaševalne pakete BLE, ne glede na to, ali jo uporabnik uporablja, kar omogoča posredno sklepanje o prisotnosti oseb brez kamer in brez kakršnekoli interakcije z opazovanimi napravami. V okviru naloge je bil zasnovan in izdelan celoten sistem: senzorska vozlišča na osnovi mikrokrmilnika ESP32-C3, ki pasivno skenirajo pakete BLE, posredniška plast MQTT, zaledni sistem v ogrodju FastAPI s časovno-vrstno podatkovno bazo InfluxDB in spletna nadzorna plošča z upravljanjem vozlišč ter posodabljanjem programske opreme po zraku. Zbiranje podatkov je zasnovano minimalistično: ocena zasedenosti je v celoti izpeljana iz agregiranega števila zaznanih naprav, naslovi MAC pa so za delovanje potrebni le v kratkem drsečem oknu v pomnilniku. Naključna rotacija naslovov MAC je zasebnostni mehanizem, zaradi katerega se ista fizična naprava skozi čas pojavlja kot več različnih naprav. V podobnih sistemih je ta pojav pogosto omenjen le mimogrede, v tem delu pa je obravnavan kot osrednji izziv metode. Naloga ga ne rešuje z algoritmičnim razreševanjem naslovov, temveč z empirično kalibracijo inflacijskega faktorja za posamezen prostor. Sistem je bil preizkušen v dejanskem pisarniškem okolju z večtedenskim neprekinjenim zajemom podatkov. Meritve pokažejo stabilno bazno vrednost zaznanih naprav, izrazito razliko med delovnimi dnevi in vikendi ter ponovljiv dnevni potek z jutranjim vrhom. Sočasni ročni popisi potrdijo sorazmerje med številom zaznanih naprav in številom prisotnih oseb, ki pa med posameznimi popisi opazno niha. Rezultati potrjujejo, da je pasivno zaznavanje BLE dobra osnova za kategorično oceno zasedenosti, natančno štetje posameznih oseb pa z njim ni dosegljivo.

Language:Slovenian
Keywords:BLE, zasedenost, pasivno skeniranje, RSSI, MQTT, ESP32, zasebnost
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FE - Faculty of Electrical Engineering
Year:2026
PID:20.500.12556/RUL-188342 This link opens in a new window
COBISS.SI-ID:302292995 This link opens in a new window
Publication date in RUL:21.09.2026
Views:229
Downloads:64
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Indoor Occupancy Estimation with Passive Detection of BLE Advertisement Packets
Abstract:
This thesis addresses the measurement of indoor space occupancy through passive detection of BLE advertising packets. The starting point is the observation that almost every mobile device continuously broadcasts BLE advertising packets regardless of whether it is actively being used, which allows the presence of people to be inferred indirectly -- without cameras and without any interaction with the observed devices. A complete system was designed and built: sensor nodes based on the ESP32-C3 microcontroller that passively scan for BLE packets, an MQTT messaging layer, a FastAPI backend with an InfluxDB time-series database, and a web dashboard providing node management and over-the-air firmware updates. Data collection is deliberately minimal: the occupancy estimate is derived entirely from the aggregate device count, and MAC addresses are needed only within a short in-memory sliding window. Random MAC address rotation is a privacy mechanism that causes a single physical device to appear as several distinct devices over time. Related systems often mention this effect only in passing, whereas this work treats it as the central challenge of the method. Rather than resolving rotated addresses algorithmically, the problem is addressed through empirical calibration of an inflation factor for a given space. The system was evaluated in a real office environment through several weeks of continuous data collection. The measurements show a stable baseline device count, a pronounced difference between weekdays and weekends, and a repeatable daily pattern with a morning peak. Concurrent manual headcounts confirm a proportional relationship between the number of detected devices and the number of people present, although that ratio varies noticeably between individual counts. The results confirm that passive BLE sensing is a reliable basis for a categorical occupancy estimate, while exact counting of individual people is not attainable with it.

Keywords:BLE, occupancy, passive scanning, RSSI, MQTT, ESP32, privacy

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back