28/01/2015
Ko roboti zavladajo zemlji ... ;)
Dvometrski robotski kiklop
Roboti so zavladali zemlji, pravi Matej Kristan iz Laboratorija za Umetne Vizualne Spoznavne Sisteme Fakultete za računalništvo in informatiko Univerze v Ljubljani. Tudi sam se ukvarja z raziskovanjem in razvojem robotov, ne zemeljskih, pa tudi ne zračnih, ampak morskih. Takih, ki plujejo ob obali i…
25/02/2014
Googlov prispevek k računalniškemu vidu in robotiki: http://www.youtube.com/watch?v=Qe10ExwzCqk
Say hello to Project Tango!
Project Tango is an exploration into giving mobile devices a human-scale understanding of space and motion. What if you never found yourself lost in a new bu...
27/11/2013
Še en lep dosežek MITa.
Inexpensive ‘nano-camera’ can operate at the speed of light - MIT News Office
Device could be used in medical imaging, collision-avoidance detectors for cars, and interactive gaming.
21/11/2013
Računalniška različica vseživljenjskega učenja B)
Press Release: Carnegie Mellon Computer Searches Web 24/7 To Analyze Images and Teach Itself...
PITTSBURGH—A computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day at Carnegie Mellon University, searching the Web for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.
23/10/2013
Nekaj utrinkov s terenskega dela v Kopru, v sodelovanju s Harpha Sea: testiranje metod računalniškega vida za uporabo na avtonomnem plovilu.
18/07/2013
Pravo vreme za open air testiranje :-)
17/05/2013
Naša katedra uspešno dočakala abrahama - it's torta time! :P
15/05/2013
Epska bitka članov laboratorija končana :)
I am pleased to confirm that your paper "Towards commoditized smart-camera design" has been accepted for publication in Journal of Systems Architecture.
08/05/2013
Danes, 8.5. od 12. ure do 15. ure v P8 drugi sklop predavanj prof. Vaclava Hlavaca. Vabljeni!
Lecture 4 ‒ CLASSIFIER (Task formulation; Perceptron, its learning, and beyond; Support Vector Machines (SVM), learning; Nonlinear classifiers
Lecture 5 ‒ LEARNING IN PATTERN RECOGNITION (Behaviorism, beginning of 20th century, no breakthrough; Learning by examples, knowledge engineering paradox; Feedbacks in learning -supervised, semisupervised,reinforcement, unsupervised; Four substitutive quality criteria in the related optimization
task
Lecture 6 ‒ PRACTICAL EXAMPLES FROM OUR RESEARCH