Visual information processing allocation between a mobile device and a network
View Patent ↗An illustrative mobile device includes a data storage configured to at least temporarily store visual information and at least one processor that is configured to determine whether to request visual information processing from a network with which the mobile device may communicate. The processor is configured to determine a mobile device condition and a network condition. The processor determines a type of feature from the visual information to use for classification based on the determined mobile device and network conditions. The processor is configured to classify the visual information based on the determined type of feature and determine a confidence indicator based on the classification. The processor determines whether to request visual information processing from the network based on the determined confidence indicator.
1. A mobile device, comprising:
a data storage configured to at least temporarily store visual information; and
at least one processor configured to determine a mobile device condition;
determine a network condition of a network with which the mobile device may communicate;
determine a type of feature from the visual information to classify based on the determined mobile device and network conditions;
classify the visual information based on the determined type of feature;
determine a confidence indicator based on the classification; and
determine whether to request visual information processing from the network based on the determined confidence indicator.
2. The mobile device of claim 1 , wherein
the at least one processor is configured to determine a visual information processing model based on the determined mobile device condition and network condition;
the visual information processing model includes the type of feature to classify and a confidence indicator threshold; and
the at least one processor determines whether to request visual information processing from the network based on a relationship between the determined confidence indicator and the confidence indicator threshold.
3. The mobile device of claim 2 , wherein the at least one processor is configured to request visual information processing from the network if the determined confidence indicator is below the confidence indicator threshold.
4. The mobile device of claim 2 , wherein the at least one processor is configured to utilize the classification of the classified at least one feature if the determined confidence indicator is equal to or greater than the confidence threshold.
5. The mobile device of claim 1 , wherein the at least one processor is configured to
request visual information processing from the network when the confidence indicator indicates that the classified at least one feature is not acceptably classified; and
use the classification of the classified at least one feature when the confidence indicator indicates that the classification is acceptable.
6. The mobile device of claim 1 , wherein
the data storage includes a plurality of predetermined relationships between respective mobile device conditions, network conditions and the type of features from the visual information to classify; and
the at least one processor is configured to determine the type of feature from the visual information to classify by determining which of the predetermined relationships corresponds to the determined mobile device and network conditions.
7. The mobile device of claim 6 , wherein
the plurality of predetermined relationships include respective predetermined confidence indicator thresholds; and
the at least one processor is configured to determine whether to request visual information processing from the network based on a relationship between the determined confidence indicator and the predetermined confidence indicator threshold from the predetermined relationship that corresponds to the determined mobile device and network conditions.
8. The mobile device of claim 1 , wherein
the mobile device condition is indicative of a visual information processing capacity of the mobile device; and
the network condition is indicative of an ability of the network to handle information transfer associated with the processing of the visual information.
9. The mobile device of claim 8 , wherein the mobile device condition includes an indication of a charge level of a battery of the mobile device.
10. The mobile device of claim 1 , wherein the visual information comprises at least one of an image or at least a portion of a video.
11. A method of allocating a visual information processing task between a mobile device and a network with which the mobile may communicate, the method comprising the steps of:
determining a mobile device condition;
determining a network condition of a network with which the mobile device may communicate;
determining a type of feature from the visual information to classify based on the determined network condition and mobile device condition;
classifying the visual information based on determined type of feature;
determining a confidence indicator based on the classification; and
determining whether to request visual information processing from the network based on the determined confidence indicator.
12. The method of claim 11 , comprising
determining a visual information processing model based on the determined mobile device condition and network condition, wherein the visual information processing model includes the type of feature to classify and a confidence indicator threshold; and
determining whether to request visual information processing from the network based on a relationship between the determined confidence indicator and the confidence indicator threshold.
13. The method of claim 12 , comprising requesting visual information processing from the network if the determined confidence indicator is below the confidence indicator threshold.
14. The method of claim 12 , comprising utilizing the classification of the classified at least one feature if the determined confidence indicator is equal to or greater than the confidence threshold.
15. The method of claim 11 , comprising
requesting visual information processing from the network when the confidence indicator indicates that the classified at least one feature is not acceptably classified; and
using the classification of the classified at least one feature when the confidence indicator indicates that the classification is acceptable.
16. The method of claim 11 , wherein
the data storage includes a plurality of predetermined relationships between respective mobile device conditions, network conditions and the type of features from the visual information to classify; and
the method comprises determining the type of feature from the visual information to classify by determining which of the predetermined relationships corresponds to the determined mobile device and network conditions.
17. The method of claim 16 , wherein
the plurality of predetermined relationships include respective predetermined confidence indicator thresholds; and
the method comprises determining whether to request visual information processing from the network based on a relationship between the determined confidence indicator and the predetermined confidence indicator threshold from the predetermined relationship that corresponds to the determined mobile device and network conditions.
18. The method of claim 11 , wherein
the mobile device condition is indicative of a visual information processing capacity of the mobile device; and
the network condition is indicative of an ability of the network to handle information transfer associated with the processing of the visual information.
19. The method of claim 18 , wherein the mobile device condition includes an indication of a charge level of a battery of the mobile device.
20. The method of claim 11 , wherein the visual information comprises at least one of an image or at least a portion of a video.