Siemens Aktiengesellschaft

University System of Maryland

Rutgers, the State University of New Jersey

Cheng-Hao Kuo

Vinay Damodar Shet

Dorin Comaniciu

Andreas Hutter

Xianjun Sam Zheng

Sushil Mittal

Xiang Gao

Peter Meer

Sameh Khamis

Automated person re-identification may be assisted by consideration of attributes of the person in a joint classification with matching of the person. By both solving for similarities in a plurality of attributes and identities, discriminative interactions may be captured. Automated person re-identification may be assisted by consideration of a semantic color name. Rather than a color histogram, probability distributions are mapped to color terms of the semantic color name. Using other descriptors as well, similarity measures for the various descriptors are weighted and combined into a score. Either or both considerations may be used.

Machine-learnt person re-identification

A forensic video search user interface is disclosed that accesses databases of stored video event metadata from multiple camera streams and facilitates the workflow of search of complex global events that are composed of a number of simpler, low complexity events.

Method and user interface for forensic video search

A method for tracking pedestrians in a video sequence, where each image frame of the video sequence corresponds to a time step, includes using marginal space learning to sample a prior probability distribution p(x|Z) of multi-person identity assignments given a set of feature measurements from all previous image frames, using marginal space learning to estimate an observation likelihood distribution p(z|x) of the set of features given a set of multi-person identity assignments sampled from the prior probability distribution, calculating a posterior probability distribution p(x|Z) from the observation likelihood distribution p(z|x) and the prior probability distribution p(x|Z), and using marginal space learning to estimate the prior probability distribution p(x|Z) for a next image frame given the posterior probability distribution p(x|Z) and a probability p(x|x), where the posterior probability distribution of multi-person identity assignments corresponds to a set of pedestrian detection hypotheses for the video sequence.

Marginal space learning for multi-person tracking over mega pixel imagery

Growing community of inventors

Plainsboro, NJ, United States of America

Cheng-Hao Kuo