More information
Description
Main objectives: the Spacetime Vision project will find practical answers to these scientific challenges. We will push the frontiers of AI and take important steps towards making the technologies of tomorrow possible, with direct impact in various parts of industry, energy and the environment sectors. 1) We will create fast methods for online and unsupervised learning in large spatiotemporal volumes of data, able to function in the dynamic world. We will use different kinds of imaging and 4D (3D + time) sensing capabilities, ranging from fixed sensors to cameras present on UAVs. We will develop efficient methods for learning with no human supervision. Given the huge amounts of unlabeled data available and the costly manual annotation, unsupervised learning is crucial for the creation of new AI technologies. 2) We will make powerful methods for complete scene understanding, from the level of objects and their activities to translating the visual scene into natural language. Vision to language translation is a new topic in AI, becoming a new exciting field of research. 3) We will give drones the capacity to “see” and understand the world in which they fly. They will be smart and have the possibility to fly and land safely. 4) We will develop smart cameras with new sensing and learning capabilities. They will make our research suitable for real world applications.
Impact: Our results will have immediate impact in different fields. We will orient our research towards the energy and environment sectors, in which there is a real need for performant AI technologies. While our scientific work will result in papers submitted to top IT conferences and journals, our experiments will include specific tests to answer the needs of our collaborators in the energy, industry and environment fields. Our approach to unsupervised learning in the 4D world and the results of our objectives will make a direct impact in the science and practice of artificial intelligence.
Summary of project results
Artificial intelligence can provide intelligent answers to the needs of our society by developing more trustworthy, safer, more sustainable and more efficient technologies. To achieve such goals, our Spacetime Vision Project aimed to address essential research challenges, such as unsupervised learning from spatiotemporal data, the ability to learn a complete, multi-interpretation and multi-modal understanding of the world as well as develop intelligent drones and smart cameras that can apply such technical solutions in the real-world, as also stated on the project’s public website: https://sites.google.com/view/spacetimevision/
The Spacetime Vision project created a strong collaboration between two leading Romanian research institutions (the project coordinator: University POLITEHNICA of Bucharest and partner University of Bucharest ) as well as a leading Norwegian research institution (NORCE), which included intensive research, communication and dissemination activities. We developed the relevant methods, collected and annotated datasets when needed, performed the necessary experimental validation, published papers in top international venues, presented numerous demos of our algorithms and systems, and organized together workshops and summers schools with top international participation.
The main results of the Spacetime Vision projects consists of a large body of algorithms, code and demos, data sets and experimental results, most published in top international conferences and journals. These results are publicly available and can be accessed through the project’s website: https://sites.google.com/view/spacetimevision/ The main beneficiaries of these results are the international society as a whole, being part of the public domain, as well as the research expertise and scientific knowledge of the specific research institutions involved, with direct impact at the national and international levels, by increasing the capacity of Romania and Norway for future technological developments and collaborations, along the directions established by the project results.
Summary of bilateral results
The project also contributed to strengthening the mutual collaboration between Romania and Norway, by starting new research and development projects with bilateral cooperation (including collaborations with Norwegian private sector), the bilateral organization of scientific meetings, workshops and summers schools, as well as submissions of European level scientific grant applications.