As surveillance cameras become widespread, filters are needed to process large streams of image data and spot interesting events. Programmed image filters generally result in low to medium performing solutions. Data-derived filters perform better in that they tap on selected image features, but require a per-sensor effort by an analyst or a machine learning expert. This contribution addresses filter shaping as a data-driven process that is ‘placed in the hands of many end-users’ with extensive domain knowledge but no expertise in machine learning. The focus is on interactive machine learning technologies as a means to achieve selfprogramming and specialization of image filters that learn to search images by their content, sequential order, and temporal attributes. We describe and assess the performance of two interactive algorithms designed and implemented for a real case study in process monitoring for nuclear safeguards. Experiments show that interactive machine learning helps detect safeguards relevant event while significantly reducing the number of false positives.

VERSINO Cristina;  LOMBARDI Paolo; 

2011-05-26

Springer

JRC51814

978-3-642-19550-1,   

https://publications.jrc.ec.europa.eu/repository/handle/JRC51814,   

10.1007/978-3-642-19551-8_10,