Video Processing and Understanding Lab
Universidad Autónoma de Madrid Escuela Politécnica Superior |
Supported by the AEI of the Ministerio de Ciencia e Innovación of the Spanish Goverment |
This work package aims at the initial establishment and maintenance of a development framework for the remaining work packages.
Arrangement and configuration of the available equipment, and the acquisition of complementary equipment, for establishing the necessary infrastructure to meet the objectives of the project (storage, communication, and computing infrastructures).
Support to other tasks for generating test data and defining evaluation methodologies. It includes the selection of appropriate datasets (sequences and associated ground-truth from the state-of-the-art) and their generation (required nuew dataset geopositioned), as well as the research, selection, and proposal of evaluation metrics and benchmarks.
Milestones:
Deliverables:
To develop the necessary technology to automatize the generation and update of a street elements catalogue using Computer Vision. This workpackage makes use of the dataset generated in WP1.
To explore strategies to localize the street elements in urban scenarios. In this direction, we propose to use a geopositioned video camera in conjunction with computer vision object detection algorithms.
To develop mechanisms to maintain updated the street elements catalogue over time. In this direction, we propose: (1) exploring different visual representations, classification, or higher semantic abstractions of the urban elements in order to enrich the generation and completeness of the street elements catalogue; (2) exploring computer vision based object re-identification alternatives.
To explore strategies to adapt continuously to new additional elements, both new instances of elements already presented in the catalogue and completely new categories. In this direction, we propose three different continual lifelong learning alternatives: incremental domain learning, incremental class learning and incremental task learning.
Milestones:
Deliverables:
To coordinate the project activities, follow-up progress, the dissemination, define the final uses cases (to be defined with the help of the Observing Partner) and develop technology transfer initiatives. This workpackage makes use of the results from WP1 and WP2.
This task has the following activities: monthly follow up of Project progress and achievements, workplan milestones and outcomes deadlines control, workplan updates, corrective actions, and administrative issues.
This task coordinates the communication of the project advances to the Observing Partner and general public. A web site will include a description of the project, status, advances, and announcements, as well as the periodic information updates (e.g., SEGA-CV Newsletters). In addition, this task also coordinates the compilation and internal publication of intermediate results, in order to have a clear plan for dissemination based on a commitment for bi-monthly reports’ updates that will constitute seeds for publications, as well as the analysis of target journals and conferences for the different works in progress. It will also coordinate the dissemination of results via Research Reports, GitHub software repositories and generated datasets, to be made available at the project’s web page, via links to open repositories. This task also handles the Data Management plan.
Using WP2 outcomes, use cases will be defined with the help and recommendations of the Observing Partner (as described in section 4.3). Information meetings will be held with the Observing Partner, open to other companies and interested parties, will be held in the form of Industry Days.
Milestones:
Deliverables: