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.