Accession Number : AD1011558


Title :   MATHEMATICS OF SENSING, EXPLOITATION, AND EXECUTION (MSEE) Sensing, Exploitation, and Execution (SEE) on a Foundation for Representation, Inference, and Learning


Descriptive Note : Technical Report,26 Sep 2011,15 Mar 2015


Corporate Author : University of California Los Angeles Los Angeles United States


Personal Author(s) : Zhu,Song-Chun


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1011558.pdf


Report Date : 01 Jul 2016


Pagination or Media Count : 81


Abstract : This project developed a mathematical foundation for unified representation, inference, and learning for ISR problems. The result of the project is an end-to-end system for scene and event understanding from various imaging sensor inputs. It computes 3D scene-based probabilistic spatial-temporal-causal and-or graph representations for human activities and human-object interactions, and answers binary (yes/no) queries via Who, What, Where, When, and How storylines.


Descriptors :   computer vision , scene generation , learning machines , video images


Distribution Statement : APPROVED FOR PUBLIC RELEASE