Sustav za detekciju i praćenje ruke pomoću dubinske kamere

undergraduate thesis

• Title (english): System for hand detection and tracking using depth camera
• Author: Ivan Jurin
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru rada izrađen je sustav za daljinsko upravljanje robotskom rukom koristeći pokrete ljudske ruke. U radu su razmatrani pristupi detekciji i praćenju objekata u dubinskim slikama te je implementirana jedinstvena metoda detekcije ruke. Metoda se sastoji od dva koraka, segmentacija ruke iz slike te klasifikacija poze u kojoj se nalazi ruka. Metoda je ispitana i pokazala se uspješnom u primjeni u pogledu točnosti i računske zahtjevnosti. Uz metodu razvijen je i vlastiti mrežni protokol te specifičan način upravljanja kao spoj pozicijskog i brzinskog upravljanja. Upravljanje je također ispitano te radi u stvarnom vremenu.

Abstract (english)

Within this thesis a system was developed for remote robot arm control using human hand movements. Possible approaches to detection and tracking of objects in depth images are discussed. A unique method for hand detection is implemented. The method consists of two steps, initial segmentation of hand from depth image and classification of hand pose. The method is tested and considered succsessful in terms of accuracy and computing complexity. A simple network protocol supporting the method is constructed and a specific way of controling the robotic hand is implemented using both position control and velocity control. The whole system was successfully tested and proven to work in real time.

• Keywords: detekcija ruke; dubinske slike; praćenje pokreta; računalni vid; upravljanje robotskom rukom; morfološke transformacije; klasificiranje objekata
• Keywords (english): hand detection; depth images; real-time hand tracking; computer vision; robotic arm manipulation; morphological transformations; object classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:278190
• Study programme: Title: Computing; 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 09:31:57