prikaz prve stranice dokumenta Automatizirano praćenje stanja inventara analizom slike
Access restricted to students and staff of home institution
undergraduate thesis
Automatizirano praćenje stanja inventara analizom slike
Rijeka: University of Rijeka, Faculty of Engineering, 2019. urn:nbn:hr:190:603701
Herak, Simone
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Intelligent Computing Systems

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Herak, S. (2019). Automatizirano praćenje stanja inventara analizom slike (Undergraduate thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:603701

Herak, Simone. "Automatizirano praćenje stanja inventara analizom slike." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:603701

Herak, Simone. "Automatizirano praćenje stanja inventara analizom slike." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:603701

Herak, S. (2019). 'Automatizirano praćenje stanja inventara analizom slike', Undergraduate thesis, University of Rijeka, Faculty of Engineering, accessed 02 May 2024, https://urn.nsk.hr/urn:nbn:hr:190:603701

Herak S. Automatizirano praćenje stanja inventara analizom slike [Undergraduate thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2019 [cited 2024 May 02] Available at: https://urn.nsk.hr/urn:nbn:hr:190:603701

S. Herak, "Automatizirano praćenje stanja inventara analizom slike", Undergraduate thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:190:603701

Metadata
TitleAutomatizirano praćenje stanja inventara analizom slike
Title (english)Automated Image-Guided Inventory Management System
AuthorSimone Herak
MentorIvan Štajduhar (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Intelligent Computing Systems)
Rijeka
Defense date and country2019-07-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu je opisan problem automatiziranog praćenja stanja inventara konačne veličine u kućanstvu (hladnjaka) analizom slike i predloženo je prikladno rješenje istog. U uvodnom dijelu argumentirana je osnovna ideja, a dan je i pregled korištenih tehnologija i alata u razvoju sustava. Glavni dio odnosi se na postavljanje eksperimenta i odredivanja modaliteta akvizicije podataka (videa ili slikovnih zapisa). Razmotreni su različiti scenariji i osigurana je zadovoljavajuća količina podataka, radi osiguravanja razumne varijacije u podacima za potrebe učenja kvalitetnog prediktivnog modela. Razmotren je problem prepoznavanja pojedinih artikala sa slike iz konačnog, unaprijed zadanog, skupa artikala. Dodatno, razmotren je problem prepoznavanja aktivnosti dodavanja, odnosno oduzimanja sa stanja skladišta. Razvijen je prototip sustava koji omogućava automatizirano dodavanje, odnosno oduzimanje artikala sa stanja skladišta u realnom vremenu. U završnom dijelu je prikazana komparativna analiza s postojećim srodnim sustavima za problem automatiziranog praćenja stanja inventara te doneseni su zaključci za poboljšanje odnosnog sustava u svrhu uvodenja istog u fazu produkcije.
Abstract (english)
This paper describes the problem of automated inventory management in the household (refrigerator) by analyzing images and proposing the appropriate solution. The basic idea was argued in the introductory part and an overview of the technologies and tools used in the development of the system is given. The main part refers to setting up an experiment and determining the data acquisition mode (video or image). Different scenarios were considered and a sufficient amount of data was provided to ensure a reasonable variation in the data for learning the quality predictive model. The issue of recognizing individual items from images from a final set of articles was considered. Additionally, the problem of recognizing additions or withdrawals from the storage is considered. A prototype system has been developed that allows automated addition or subtraction of items with real-time warehouse conditions. The final section presents a comparative analysis of existing related automated inventory management systems and conclusions are made to improve the current model precision.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:603701
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2019-09-02 08:06:52