RESEARCH AREAS

Cutting edge Research in Computer Vision and Machine Learning

0 People
0 Total Projects
0 Active Projects
0 Publications

Best Paper Award ICBHI 2017

This work presented a fall detection method based on Recurrent Neural Networks. It leverages the ability of recurrent networks to process sequential data, such as acceleration measurements from body-worn devices, as well as data augmentation in the form of random rotations of the input acceleration signal. Τhe proposed method was able to find all but one fall event, while at the same time producing no false alarms when tested on the publicly available URFD dataset. Proceedings/Precision Medicine Powered by pHealth…

0
Read More

The Visual Computing Lab of CERTH-ITI, participated in the IEEE International Conference on Computer Vision (ICCV) 2017

The Visual Computing Lab of CERTH-ITI, participated in the IEEE International Conference on Computer Vision (ICCV) 2017, held between 22-29 October, in Venice, Italy. The conference, being the major international computer vision event, had an exciting programme of 621 papers, presenting the latest advances in the field. This year, the attendance of ICCV increased by 113%, having 3107 attendees! Our presented work was a poster paper, entitled “Non-linear Convolution Filters for CNN-based Learning”, by G. Zoumpourlis, A. Doumanoglou, N. Vretos…

0
Read More

MaTHiSiS – educational scheme based on custom-made and adaptable learning goals and educational material

PRESS RELEASE Release Date: 01/11/2017 MaTHiSiS – educational scheme based on custom-made and adaptable learning goals and educational material   Three-year EU Co-funded Project to create a ubiquitous e-learning ecosystem for Mainstream & Special Education, Industrial Training and Career Guidance MaTHiSiS is a 36-month project funded by the European Union under the H2020 work programme that will assist the educational process for learners and their tutors and caregivers by creating a novel and continuously adaptable “robot/machine/computer”-human interaction ecosystem. This system…

0
Read More

Deep Affordance-grounded Sensorimotor Object Recognition CVPR 2017 HONOLULU

S. Thermos, G. T. Papadopoulos, P. Daras, G. Potamianos, “Deep Affordance-grounded Sensorimotor Object Recognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, Hawaii, USA, July 2017. Abstract: It is well-established by cognitive neuroscience that human perception of objects constitutes a complex process, where object appearance information is combined with evidence about the so-called object “affordances”, namely the types of actions that humans typically perform when interacting with them. This fact has recently motivated the “sensorimotor” approach to…

0
Read More

Volterra-based convolution filter implementation in Torch

Download the layer’s code from here: VolterraConvolution.zip The code is based on the following publication: G. Zoumpourlis, A. Doumanoglou, N. Vretos, P. Daras, “Non-linear Convolution Filters for CNN-based Learning”, IEEE International Conference on Computer Vision (ICCV 2017), Venice, Italy, October 22-29 2017

0
Read More

FORENSOR: Action Recognition

Action Recognition via Motion Analysis In this method, the first step of performing real-time object tracking is based on background subtraction. Initially, the algorithm grabs an image of the background, assuming that the frame is empty of subjects. Subsequently, while capturing each new frame, the background is subtracted by the newly acquired image and the resulted outcome is thresholded to form a foreground binary mask. This mask is further enhanced by the morphological operation of dilation and finally a connected…

0
Read More

Factory2Fit – Developing the Factories of the Future

The Factory2Fit Project By developing solutions to make the factory environment more flexible and adaptable, the Factory2Fit project will bring increased worker motivation, satisfaction and productivity. It will help current and future workers to become knowledge workers in smart factories with fulfilling careers. The Factory2Fit Idea The core idea behind the Factory2Fit project is that the workers are experts in their own work – therefore they should have an active role in designing their work. The adaptation solutions that Factory2Fit will deliver are based on a…

0
Read More

Sensorimotor Object Recognition 3D Dataset

The CERTH-SOR3D dataset contains 20830 instances of human-object interactions. The capturing process involved three synchronized Microsoft Kinect v2 sensors (three capturing views) under controlled environmental conditions. The available data contain 1) RGB videos (1920×1080 pixels ), 2) depth map sequences (512×424 pixels). and c) 3D optical flow fields. Visit the official site

0
Read More
Visual Computing Lab

The focus of the Visual Computing Laboratory is to develop new algorithms and architectures for applications in the areas of 3D processing, image/video processing, computer vision, pattern recognition, bioinformatics and medical imaging.

Contact Information

Dr. Petros Daras, Principal Researcher Grade Α
1st km Thermi – Panorama, 57001, Thessaloniki, Greece
P.O.Box: 60361
Tel.: +30 2310 464160 (ext. 156)
Fax: +30 2310 464164
Email: daras@iti.gr