Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS
Content archived on 2024-05-24

Visual Active Memory Processes and Interactive REtrieval

Objective

In traditional vision systems the model acquisition and recognition processes are decoupled in time and control. The coupling of both processes leads to significant challenges in computer vision. The model acquisition task has to be performed by active memory processes that have to implement visual learning and categorization capabilities. The recognition process must be substituted by an interactive retrieval that performs a reasoning process about the memorized and perceived input data. The project aims at the development of an active memory and retrieval system in the context of an Augmented Reality scenario. The user wears a head-mounted camera and display such that the system is able to build up a hierarchical structured memory of what the user sees. Query results are re-visualized in a virtual world or projected into the real world using the head-mounted display.

Objectives:
Despite of great progress in the field of image understanding the simulation of the human visual system is still far unreachable. It is characterized by the ability to categorize unknown objects and events with regard to the situational context and background knowledge. The main thesis put forth by the project VAMPIRE is that learning and cognitive capabilities in vision systems cannot be realized without Visual Active Memory (VAM) Processes. VAM maintains the visual history of the dynamic world over an extended period of time. It provides the context and background knowledge for learning and categorization of objects and motion behaviors in a dynamically changing environment. The categorization process is enforced by interactive retrieval where acquired concepts must be related to queries provided by a user opening up the full cognitive performance of the system.

Work description:
The realization of a visual active memory and interactive retrieval system can be broken down into the following aspects that each is a research aim for its own. The combination of these aspects will result in a system that out rules the performance and functionality of today's vision systems. Robust real-time detection and tracking of objects in complex scenes is one of the most important requirement for a visual active memory and interactive retrieval system. The aim is to provide fast and robust modules at the low level of vision for object/background segmentation and sparse 3-d reconstruction. Another important step is the development of the concept of visual Active Memory and the implementation of the associated tools for learning visual concepts and events by observing dynamic environments. The conceptual models will be used to aid the scene interpretation process. A further research goal is the implementation of a fully mobile multi-user Augmented Reality (AR) demonstrator having active visual memory capabilities. This demonstrator is a realization of all-important features of a wearable, distributed real-time cognitive vision system. The system is distributed over several users, each of them wearing a fully mobile AR-gear. The final aim to have demo systems in (at least) 4 labs serving as project demonstrator and evaluation platforms. The demonstrator will evolve over gradually more complex tasks. We will start by evaluating the system in two different environments, e.g office and lab. Additional domains will be successively introduced modelling context switches and learning facilities.

Milestones:
The project will progress according to a set of annual milestones that range from the design of an integrated vision architecture over the realization of content- based retrieval to the implementation of visual learning and categorization capabilities on the basis of the Visual Active Memory. All these skills will be demonstrated in an augmented reality scenario where query results of a user request are constructed to visual data and projected into the real world using a head-mounted display.

Fields of science (EuroSciVoc)

CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.

You need to log in or register to use this function

Programme(s)

Multi-annual funding programmes that define the EU’s priorities for research and innovation.

Topic(s)

Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.

Call for proposal

Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.

Data not available

Funding Scheme

Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.

CSC - Cost-sharing contracts

Coordinator

UNIVERSITAET BIELEFELD
EU contribution
No data
Address
UNIVERSITAETSSTRASSE 25
33501 BIELEFELD
Germany

See on map

Total cost

The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.

No data

Participants (3)

My booklet 0 0