GENERIC PROBABILISTIC APPROXIMATE COMPUTATIONAL INFERENCE MODEL FOR STREAMING DATA PROCESSING

A generic online, probabilistic, approximate computational inference model for learning-based data processing is presented. The model includes detection, feature production and classification steps. It employs Bayesian Probabilistic Models (BPMs) to characterize complex real-world behaviors under uncertainty. The BPM learning is incremental. Online learning enables BPM adaptation to new data. The available data drives BPM complexity (e.g., number of states) accommodating spatial and temporal ambiguities, occlusions, environmental clutter, and large inter-domain data variability. Generic Sequential Bayesian Inference (GSBI) efficiently operates over BPMs to process streaming or forensic data. Deep Belief Networks (DBNs) learn feature representations from data. Examples include model applications for streaming imagery (e.g., video) and automatic target recognition (ATR).