Human Activity Recognition Based Path Planning For Autonomous Vehicles

Simple item page
dc.contributor.advisorAnbarjafari, Gholamreza
dc.contributor.authorTammvee, Martin
dc.contributor.otherTartu Ülikool. Loodus- ja täppisteaduste valdkondet
dc.contributor.otherTartu Ülikool. Tehnoloogiainstituutet
dc.date.accessioned2021-05-31T08:56:46Z
dc.date.available2021-05-31T08:56:46Z
dc.date.issued2020
dc.description.abstractHuman activity recognition (HAR) is wide research topic in a field of computer science. Improving HAR can lead to massive breakthrough in humanoid robotics, robots used in medicine and in the field of autonomous vehicles. The system that is able to recognise human and its activity without any errors and anomalies, would lead to safer and more empathetic autonomous systems. During this thesis multiple neural networks models, with different complexity, are being investigated. Each model is re-trained on the proposed unique data set, gathered on automated guided vehicle (AGV) with the latest and the modest sensors used commonly on autonomous vehicles. The best model is picked out based on the final accuracy for action recognition. Best models pipeline is fused with YOLOv3, to enhance the human detection. In addition to pipeline improvement, multiple action direction estimation methods are proposed. The action estimation of the human is very important aspect for self-driving car collision free path planning.en
dc.identifier.urihttp://hdl.handle.net/10062/72124
dc.language.isoenget
dc.publisherTartu Ülikoolet
dc.rightsopenAccesset
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjecttehisnärvivõrket
dc.subjectisesõitev autoet
dc.subjectobjekti tuvastuset
dc.subjectinimese tuvastuset
dc.subjectinimese tegevuse tuvastuset
dc.subjecttrajektoori planeerimineet
dc.subjectNeural Networksen
dc.subjectself-driving caren
dc.subjectobject detectionen
dc.subjecthuman detectionen
dc.subjecthuman action detectionen
dc.subjectpath planningen
dc.subject.othermagistritöödet
dc.titleHuman Activity Recognition Based Path Planning For Autonomous Vehiclesen
dc.title.alternativeIsesõitvate autode tee planeerimine baseerudes inimese tegevuse tuvastamiseleet
dc.typeinfo:eu-repo/semantics/masterThesiset

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Tammvee_MSc2020.pdf
Size:
8.64 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.67 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Robotics and Computer Engineering - Master's theses