Uočavanje strukturalnih pravilnosti u prometnom okruženju iz oblaka točaka laserskog senzora udaljenosti

master's thesis

• Title (english): Detection of structural regularities in traffic environments from laser range sensor point clouds
• Author: Tibor Bataljak Savić
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Petrović (član povjerenstva)
• Committee member: Marija Seder (član povjerenstva)
• Committee member: Juraj Peršić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Za autonomiju mobilnih platformi poželjno je iskoristiti pravilnosti struktura koje
se nalaze u ljudskim okruženjima, kao što su prometnice. Primjeri takvih pravilnosti
su prometni znakovi, linije koje označavaju rubove traka te cestovni rubnik koji odvaja
prostor za automobile od prostora za pješake. Laserski senzor udaljenosti je često korišten
senzor u mobilnim platformama za autonomnu vožnju zbog velike točnosti pri
mjerenju udaljenosti u odnosu da druge senzore. U ovom diplomskom radu razvijen je
algoritam za uočavanje objekata sa strukturalnim pravilnostima, poput rubnika ceste,
iz oblaka točaka snimljenih laserskim senzorom udaljenosti te analizirane su njegove
karakteristike. Algoritam se temelji na računanju geometrijskih karakteristika za detekciju
rubnika i čestičnog filtera za filtriranje rezultata detekcije.

Abstract (english)

For mobile platform autonomy, it is opportune to use the regularity of structures
that appear in human environments, for example the traffic. Examples of such regularities
are traffic signs, traffic lanes and road curbs that separate the automobile from
the pedestrian area. Laser range sensors are often used sensors on mobile platforms for
autonomous driving due to high range measurement accuracy with respect to other sensors.
In this thesis an algorithm is developed which can detect objects with structural
regularities, like the road curb, from the point cloud measured with laser range sensor
and its’ peformance is validated. The algorithm is based on calculating geometric
features to detect curbs and a particle filter to filter the detection results.

• Keywords: autonomna vožnja; detekcija rubnika; prometni scenariji; laserski senzori
• Keywords (english): autonomous driving; curb detection; traffic scenarios; laser sensors
• Language: english
• URN:NBN: urn:nbn:hr:168:896978
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 08:25:56