course-details-portlet

TTK4255 - Robotsyn

Om emnet

Vurderingsordning

Vurderingsordning: Mappevurdering
Karakter: Bokstavkarakterer

Vurdering Vekting Varighet Delkarakter Hjelpemidler
Hjemmeeksamen 25/100 4 timer
Rapport 75/100

Faglig innhold

Elements of Visual Perception, Image Sampling and Quantization, related Mathematical tools applied to Image Processing and Analysis (array, matrix, linear and non-linear operations, arithmetic and geometric operations, morphology, spatial and temporal operations, frequency analysis, linear algebra, probabilistic methods, image transformations and geometric operations) Image Formation: Camera Models, Calibration, Single view geometry, Multiple view geometry, Epipolar geometry, Feature extraction, Bundle adjustment Position and Orientation: Feature based alignment; Pose estimation; Time varying pose and trajectories, Structure from motion, dense Motion Estimation, Visual Odometry (Semi-direct VO, direct sparse odometry) Localization and Mapping: Initialization, Tracking, Mapping, geometric SLAM formulations (indirect vs. direct error formulation, geometry parameterization, sparse vs. dense model, optimization approach), Relocalization and map Optimization, Examples: Indirect (Feature based) methods (MonoSLAM, PTAM, ORB-SLAM), Direct methods (DTAM, LSD-SLAM), Sensor combinations (IMU, mono vs. Stereo, RGB-Depth), Analysis and parameter studies Recognition and Interpretation: Object detection, Instance recognition, Category recognition, Context and Scene understanding

Læringsutbytte

Knowledge: Knowledge about core applications in Robotic Vision. Knowledge about fundamental (physical) concepts about visual perception. Knowledge about image formation, image representation and camera models. Knowledge about image sampling, quantization and processing. Knowledge about structure from motion concepts for pose, tracking, motion estimation as well as visual odometry (VO) simultaneous localization an mapping (SLAM) strategies exploring popular methods. Basic knowledge about feature extraction, object recognition, context awareness/semantics and scene understanding. Skills: Be able to choose imaging systems with respect to specific applications. Calibrate the imaging system. Modify different imaging setups with respect to environmental conditions. Manipulate and implement pose, tracking and motion estimation techniques. Implement, tune and evaluate SLAM alorithms. Implement object recognition and classification methods. At the end of the semester a successful student should have skills in processing and analysis of digital images and be able to design simple robot vision and machine vision systems. General competence: Be able to apply the fundamental imaging principles. Consciousness about the role of visual sensing in robotic applications. Be able to analyze strength and weaknesses of different vision based approaches.

Læringsformer og aktiviteter

The course is given as a mixture of lectures, assignments and two projects. All assignments and projects must be approved to enter the final exam.

Obligatoriske aktiviteter

  • Øvinger

Mer om vurdering

Portfolio evaluation ("Mappevudering") is used to define the final grade in the subject. Parts of the portfolio are the final exam in writing 80%, and a project report (lab experiment findings) 20%. The result of each part is given in percentage units, while evaluation of the entire portfolio (the final grade) is given as a letter. If there is a re-sit examination, the examination form may change from written to oral. Both project report (20%) need to be retaken in addition to the main exam (80%).

Forkunnskapskrav

TMA4245 - Statistikk, TTK4115 - Linear System Theory

Kursmateriell

Information on this is given at the start of the semester.

Flere sider om emnet

Ingen

Fakta om emnet

Versjon: 1
Studiepoeng:  7.5 SP
Studienivå: Høyere grads nivå

Undervisning

Termin nr.: 1
Undervises:  VÅR 2022

Undervisningsspråk: Engelsk

Sted: Trondheim

Fagområde(r)
  • Datateknikk og informasjonsvitenskap
  • Marin kybernetikk
  • IKT og matematikk
  • Informatikk
  • Anvendt og industriell matematikk
  • Grafikk/bildebehandling
  • Medisinsk informatikk/datateknikk
  • Signalbehandling
  • Multivariat bildeanalyse
  • Numerisk matematikk
  • Havbruk
  • Prosessautomatisering
  • Mekanikk - fluidmekanikk
  • Fotogrammetri
  • Teknisk kybernetikk
  • Optikk
  • Bildediagnostikk
  • Informasjonsteknologi og informatikk
  • Matematikk
  • Statistikk
Kontaktinformasjon
Emneansvarlig/koordinator:

Ansvarlig enhet
Institutt for teknisk kybernetikk

Eksamensinfo

Vurderingsordning: Mappevurdering

Termin Statuskode Vurdering Vekting Hjelpemidler Dato Tid Eksamens- system Rom *
Vår ORD Rapport 75/100
Rom Bygning Antall kandidater
Vår ORD Hjemme-eksamen (1) 25/100

Utlevering
27.05.2022

Innlevering
27.05.2022


09:00


13:00

INSPERA
Rom Bygning Antall kandidater
Sommer UTS Rapport 75/100
Rom Bygning Antall kandidater
Sommer UTS Hjemme-eksamen 25/100 INSPERA
Rom Bygning Antall kandidater
  • * Skriftlig eksamen plasseres på rom 3 dager før eksamensdato. Hvis mer enn ett rom er oppgitt, finner du ditt rom på Studentweb.
  • 1) Merk at eksamensform er endret som et smittevernstiltak i den pågående koronasituasjonen.
Eksamensinfo

For mer info om oppmelding til og gjennomføring av eksamen, se "Innsida - Eksamen"

Mer om eksamen ved NTNU