| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document

Title:Energy efficient system for detection of elephants with Machine Learning : master's thesis
Authors:ID Sagadin, Marko (Author)
ID Kramberger, Iztok (Mentor) More about this mentor... New window
ID Milivojević, Vojislav Dragan (Co-mentor)
Files:.pdf MAG_Sagadin_Marko_2020.pdf (13,35 MB)
MD5: 8BBC42EDCE94958427525B2225CAA32F
 
Language:English
Work type:Master's thesis/paper (mb22)
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Human-Elephant Conflicts are a major problem in terms of elephant conservation. According to WILDLABS, an average of 400 people and 100 elephants are killed every year in India alone because of them. Early warning systems replace the role of human watchers and warn local communities of nearby, potentially life threatening, elephants, thus minimising the Human-Elephant Conflicts. In this Master's thesis we present the structure of an early warning system, which consists of several low-power embedded systems equipped with thermal cameras and a single gateway. To detect elephants from captured thermal images we used Machine Learning methods, specifically Convolutional Neural Networks. The main focus of this thesis was the design, implementation and evaluation of Machine Learning models running on microcontrollers under low-power conditions. We designed and trained several accurate image classification models, optimised them for on-device deployment and compared them against models trained with commercial software in terms of accuracy, inference speed and size. While writing firmware, we ported a part of the TensorFlow library and created our own build system, suitable for the libopencm3 platform. We also implemented reporting of inference results over the LoRaWAN network and described a possible server-size solution. We finally a constructed fully functional embedded system from various development and evaluation boards, and evaluated its performance in terms of power consumption. We show that embedded systems with Machine Learning capabilities are a viable solution to many real life problems.
Keywords:machine learning, microcontroller, on-device inference, thermal camera, low-power system
Year of publishing:2020
Place of performance:Maribor
Publisher:[M. Sagadin]
Number of pages:XVIII, 112 f.
Source:Maribor
UDC:004.85:004.932(043.2)
COBISS.SI-ID:47742723 New window
NUK URN:URN:SI:UM:DK:MDOPEXOF
Publication date in DKUM:06.01.2021
Views:445
Downloads:88
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FERI
:
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-SA 4.0, Creative Commons Attribution-ShareAlike 4.0 International
Link:http://creativecommons.org/licenses/by-sa/4.0/
Description:This Creative Commons license is very similar to the regular Attribution license, but requires the release of all derivative works under this same license.
Licensing start date:08.12.2020

Secondary language

Language:Slovenian
Title:Energetsko učinkovit sistem za detekcijo slonov s pomočjo strojnega učenja
Abstract:Konflikti med ljudmi in sloni predstavljajo velik problem ohranjanja populacije slonov. Zaradi fragmentacije in pomanjkanja habitata sloni, v iskanju hrane, pogosto zaidejo na riževa polja in plantaže, kjer pridejo v stik s človekom. Po podatkih skupnosti WILDLABS, zaradi konfliktov, samo v Indiji, letno umre povprečno 400 ljudi in 100 slonov. Sistemi zgodnje opozoritve nadomeščajo vlogo človeških stražarjev in opozarjajo bližnjo skupnost o bližini, potencialno nevarnih, slonov in tako pripomorejo k zmanjševanju konfliktov med ljudmi in sloni. V tem magistrskem delu predstavljamo strukturo sistema zgodnje opozoritve, ki je sestavljen iz večih, nizko porabnih, vgrajenih sistemov, ki so opremljeni s termalnimi kamerami in ene dostopne točke oz. prehoda (gateway). Vgrajeni sistemi so postavljeni na terenu, ob zaznavi slona pošljejo opozorilo preko brezžičnega omrežja do dostopne točke, ki nato lahko opozori lokalno skupnost. Za prepoznavo slonov iz zajetih termalnih slik smo uporabili metode strojnega učenja, bolj specifično konvolucijske nevronske mreže. Glavni cilji tega magistrskega dela so bili zasnova, izvedba in ovrednotenje modelov strojnega učenja, ki jih je možno poganjati na mikrokrmilnkih pod pogoji nizke porabe.
Keywords:strojno učenje, mikrokrmilnik, inferenca na napravi, termalna kamera, sistem z majhno porabo


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica