In this paper we describe our system for multi-source Human Identification. The system includes a collection of classifiers that classify feature streams derived from audio and video sources. We combine outputs of individual classifiers within our Approximate Bayesian combination framework. The system gives its prediction of the user identity instantaneously, whenever any useable measurement becomes available. That leads to almost 100% video frame utilization. That is, some prediction is available for almost every frame of the test video. The system is distributed across several machines running independent feature classifiers on the subscription basis. This architecture allows us to successfully use a heterogeneous network of computers regardless of their architecture and operating system. The system has undergone testing in an office environment and shows promising results with respect to increased accuracy and robustness of the classifier combination.
Multi-Modal Human Identification System
2005-01-01
539745 byte
Conference paper
Electronic Resource
English
Multi-Shaker Modal Testing and Modal Identification of Hollow-Core Floor System
British Library Conference Proceedings | 2016
|Multi-modal human aggression detection
British Library Online Contents | 2016
|Multi-modal human aggression detection
British Library Online Contents | 2016
|Multi-modal human aggression detection
British Library Online Contents | 2016
|Multi-modal sensing road anomaly identification method and system
European Patent Office | 2024
|