Polaris Wireless, Inc.

Manlio Allegra

Martin J Feuerstein

David S De Lorenzo

Mahesh B Patel

Jasvinder Singh

Robert Lewis Martin

Robert Morris Dressler

James Vincent Steele

Mark Douglas Reudink

David Stevenson Spain, Jr

Data from a wireless network location system is used in conjunction with the known geographic location of a video surveillance area such that the system according to the present invention infers that a person who appears in an image in the video is the user of a mobile phone estimated to be at the person's location. When facial recognition is applied and the person's identity is thus recognized, an association is generated as between the identity according to the facial recognition and the identity of the co-located mobile phone. This association can be critical when there is no personal identification available for a mobile phone such as a pre-paid mobile.

Surveillance system

A technique for designing and testing drive-test plan for gathering location-dependent RF data is disclosed. In accordance with some embodiments of the present invention, one candidate drive-test plan is chosen for implementation over a second based on an economic cost-benefit analysis of both plans. This is in marked contrast to, for example, a selection of drive-test plans, or the design of a drive-test plan, based on a calibration-cost analysis, in which the data estimated to be the most effective to calibrate a radio-frequency tool is sought for a given cost or the least cost. Although a data-estimated-to-be-most-effective-to-calibrate-a-radio-frequency-tool vs. cost analysis is a species of cost-benefit analyzes in general, it is not an economic cost-benefit analysis because a data-estimated-to-be-most-effective-to-calibrate-a-radio-frequency-tool vs. cost analysis has deficiencies that an economic cost-benefit analysis does not.

Efficient deployment of mobile test units to gather location-dependent radio-frequency data

A technique for designing and testing drive-test plan for gathering location-dependent RF data is disclosed. In accordance with some embodiments of the present invention, one candidate drive-test plan is chosen for implementation over a second based on an economic cost-benefit analysis of both plans. This is in marked contrast to, for example, a selection of drive-test plans, or the design of a drive-test plan, based on a calibration-cost analysis, in which the data estimated to be the most effective to calibrate a radio-frequency tool is sought for a given cost or the least cost. Although a data-estimated-to-be-most-effective-to-calibrate-a-radio-frequency-tool vs. cost analysis is a species of cost-benefit analyses in general, it is not an economic cost-benefit analysis because a data-estimated-to-be-most-effective-to-calibrate-a-radio-frequency-tool vs. cost analysis has deficiencies that an economic cost-benefit analysis does not.

A location engine is disclosed that estimates the location of a wireless terminal using (i) cell ID, (ii) triangulation, (iii) GPS, (iv) RF pattern-matching, or (v) any combination of them. The location engine is adept at discounting the contribution of apparently reasonable but erroneous data. The location engine receives data that are evidence of the location of a wireless terminal at each of a plurality of different times. The location engine then generates an initial hypothesis for the location of the wireless terminal at each time assuming that all of the data is correct and equally probative. Next, the location engine generates one alternative hypothesis for each initial hypothesis and each datum assuming that the datum is erroneous. Finally, the location engine generates the estimate for the location of the wireless terminal at each time by determining which combination of initial hypotheses and alternative hypothesis is the most self-consistent.

Estimating the location of a wireless terminal despite apparently reasonable but misleading or erroneous empirical data

An integrated wireless location and facial/speaker-recognition system that provides distinct advantages over facial-recognition systems and speaker-recognition systems of the prior art is disclosed. The integrated system is capable of using information from a wireless location system to improve the performance of the facial recognition and speaker recognition. The system is capable of processing photographs and/or audio samples captured by a camera/microphone at a fixed location (e.g., a digital pan-zoom-tilt (PZT) surveillance camera, etc.) as well as those captured by a mobile camera/microphone (e.g., a digital camera and microphone in a smartphone, etc.). The system also features a feedback mechanism by which the location-informed results can be used to improve the system's recognition abilities.

Growing community of inventors

Los Altos Hills, CA, United States of America

Manlio Allegra