Smartphone-based methods and systems
Arrangements involving portable devices (e.g., smartphones and tablet computers) are disclosed. One arrangement enables a content creator to select software with which that creator's content should be rendered—assuring continuity between artistic intention and delivery. Another utilizes a device camera to identify nearby subjects, and take actions based thereon. Others rely on near field chip (RFID) identification of objects, or on identification of audio streams (e.g., music, voice). Some technologies concern improvements to the user interfaces associated with such devices. Others involve use of these devices in connection with shopping, text entry, sign language interpretation, and vision-based discovery. Still other improvements are architectural in nature, e.g., relating to evidence-based state machines, and blackboard systems. Yet other technologies concern use of linked data in portable devices—some of which exploit GPU capabilities. Still other technologies concern computational photography. A great variety of other features and arrangements are also detailed.
1. A mobile discovery method for recognizing and/or identifying media and physical objects, the method employing a mobile device equipped with plural sensors, including an optical sensor, the mobile device being operated in an ambient environment illuminated by a solid state lamp fixture that is separate from the mobile device, the method including the acts:
in a first circumstance, a processor of said device selecting a first recognition agent, from among plural available recognition agents, and launching said first recognition agent, the first recognition agent performing a recognition process selected from the list: image watermark recognition, pattern matching, object recognition, facial recognition, barcode recognition, sign language recognition, optical character recognition, audio watermark recognition, speech recognition, and music recognition; and
in a second circumstance, the processor selecting a second recognition agent different than the first recognition agent, and launching said second recognition agent, the second recognition agent performing a second, different, recognition process selected from said list;
wherein the method includes the optical sensor of the mobile device sensing an encoded optical signal emitted by said solid state lamp fixture, and the mobile device decoding said optical signal sensed by the optical sensor to extract plural-bit payload data, wherein said selecting of the first recognition agent from among the plural available recognition agents depends at least in part on said plural-bit payload data decoded by the mobile device from the encoded optical signal emitted from the lamp fixture.
2. The method of claim 1 in which, in the first circumstance, a first pair of recognition agents is selected and launched, both of said pair of recognition agents performing recognition processes selected from said list.
3. The method of claim 2 in which said first pair of recognition agents perform barcode recognition and image watermark recognition.
4. The method of claim 1 in which said selecting the first recognition agent depends at least in part on plural-bit data decoded from a solid state lamp fixture that includes a GPS receiver.
5. The method of claim 1 in which the plural-bit data decoded from the solid state lamp fixture depends at least in part on data wirelessly received by the lamp fixture using an antenna.
6. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs image watermark recognition, and launching said first recognition agent.
7. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs pattern matching, and launching said first recognition agent.
8. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs object recognition, and launching said first recognition agent.
9. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs facial recognition, and launching said first recognition agent.
10. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs barcode recognition, and launching said first recognition agent.
11. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs sign language recognition, and launching said first recognition agent.
12. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs optical character recognition, and launching said first recognition agent.
13. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs audio watermark recognition, and launching said first recognition agent.
14. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs speech recognition, and launching said first recognition agent.
15. The method of claim 1 that includes, in the first circumstance, and in dependence on the plural-bit data decoded from the optical signal, selecting a first recognition agent that performs music recognition, and launching said first recognition agent.
16. The method of claim 1 in which the plural-bit payload data decoded by the mobile device represents location context data, and the method further includes storing said location context data as a Resource Description Framework (RDF) triple, enabling such data to later trigger an action based on a linked-data query.
17. non-transitory computer readable medium containing software instructions operative to configure a mobile device, equipped with a processor and plural sensors, including an optical sensor, to perform acts including:
in a first circumstance, selecting a first recognition agent, from among plural available recognition agents, and launching said first recognition agent, the first recognition agent performing a recognition process selected from the list: image watermark recognition, pattern matching, object recognition, facial recognition, barcode recognition, sign language recognition, optical character recognition, audio watermark recognition, speech recognition, and music recognition; and
in a second circumstance, selecting a second recognition agent different than the first recognition agent, and launching said second recognition agent, the second recognition agent performing a second, different, recognition process selected from said list;
wherein the instructions configure the mobile device to sense an encoded optical signal emitted by a solid state lamp fixture that is distinct from the mobile device, and to decode the sensed optical signal to extract plural-bit payload data, wherein said selecting of the first recognition agent from among the plural available recognition agents depends at least in part on said plural-bit payload data decoded by the mobile device from the encoded optical signal emitted from the lamp fixture.
18. A system including a mobile device and a solid state lamp fixture distinct from the mobile device, the lamp fixture including a GPS receiver, and circuitry adapted to modulate light emitted from the fixture to encode geolocation data from the GPS receiver, the mobile device comprising a camera for sensing the modulated light, and a microprocessor programmed to select from among plural available recognition agents to choose at least one image or audio recognition agent to launch, depending at least in part on said plural-bit geolocation data encoded in the modulated light.