Using an object key to deprioritize processing of relative regions

1. A method comprising:

capturing, using an image capture device, an image of an object to be tracked;

analyzing, using the image capture device, the image of the object to identify one or more recognizable portions of the object;

selecting an object key of the object, the object key comprising a portion of the one or more recognizable portions of the object, the object key attached to the object and comprising recognizable features, wherein the object key is recognizable by the image capture device based on the recognizable features of the object key, the object key comprising a portion of the object visible in a same light spectrum as the object;

calculating a relative size of the object key with respect to a size of the object and a location of the object key with respect to the object;

tracking one or more locations of the object from the relative size and location of the object with respect to the object key and based on capturing a plurality of images of the object key, using one or more image capture devices, at a resolution sufficient to identify the recognizable features of the object key and to track movement of the object key; and

periodically capturing, at a rate lower than a rate for the capturing of the plurality of images of the object key, an image of portions of the object that are not the object key at a resolution sufficient to identify recognizable features of the portions of the object that are not the object key and using the capture of the image of the portions of the object that are not the object key to verify that the object is still attached to the object key.

2. The method of claim 1 , wherein tracking the one or more locations of the object comprises:

capturing images of portions of the object that are not the object key at a lower resolution than the resolution sufficient to identify the recognizable features of the object key while tracking movement of the object key; and/or

capturing images of portions of the object that are not the object key at a lower rate than a rate of capturing images of the plurality of images of the object key.

3. The method of claim 1 , wherein tracking the one or more locations of the object comprises capturing images of the object key without capturing images of portions of the object that are not the object key.

4. The method of claim 1 , further comprising:

determining a degree of attachment between the object and the object key;

determining a verification rate based on the degree of attachment, wherein a higher degree of attachment results in a lower verification rate than a lower degree of attachment; and

periodically capturing, at the verification rate, an image of the object at a resolution sufficient to identify recognizable features of the object to verify that the object is still attached to the object key.

5. The method of claim 1 , wherein the captured image of the object is captured with an image capture device, and wherein the captured plurality of images of the object key are captured using one or more image capture devices and wherein one or more image capture devices capturing the image of the object and the plurality of images of the object key use visible light, infrared light, and/or thermal imaging.

6. The method of claim 1 , further comprising identifying, in response to capturing the image of the object, the object key within the image of the object, wherein the object key is a recognizable element of the object with physical properties sufficient to identify the recognizable features of the object key and to track the one or more locations of the object by capturing the plurality of images of the object key.

7. The method of claim 1 , further comprising:

identifying, in response to capturing the image of the object, a plurality of potential object keys within the image of the object;

determining a degree of attachment between each of the plurality of potential object keys and the object; and

determining a degree of recognizability of each of the plurality of potential object keys, the degree of recognizability of an object key of the plurality of potential object keys comprising a measure of physical properties of the object key sufficient to identify the recognizable features of the object key and to track the one or more locations of the object by capturing the plurality of images of the object key,

wherein selecting the object key of the object comprises selecting an object key of the plurality of potential object keys based on the degree of attachment and the degree of recognizability of each object key of the plurality of potential object keys.

8. The method of claim 1 , further comprising, in response to calculating the relative size of the object key with respect to the size of the object and the location of the object key with respect to the object, determining a pixel range of the portions of the object that are not the object key, wherein tracking the one or more locations of the object comprises capturing pixels of portions of the object that are not the object key at a lower resolution and/or a lower rate than a resolution and/or rate sufficient to identify the recognizable features of the object key and to track movement of the object key.

9. The method of claim 8 , wherein capturing pixels of portions of the object that are not the object key at a lower resolution and/or a lower rate than a resolution and/or rate sufficient to identify the recognizable features of the object key and to track movement of the object key comprises deprioritizing processing of the pixels of the portions of the object that are not the object key, lowering a fidelity of the pixels of the portions of the object that are not the object key, and/or avoiding sending the pixels of the portions of the object that are not the object key to a remote processing entity.

10. The method of claim 1 , wherein selecting the object key is based on a minimum size limit, the minimum size limit comprising a smallest size for a potential object key to be selected based on capabilities of the image capture device.

11. An apparatus comprising:

a processor; and

a memory storing code, the code being executable by the processor to perform operations comprising:

capturing, using an image capture device, an image of an object to be tracked;

analyzing, using the image capture device, the image of the object to identify one or more recognizable portions of the object;

selecting an object key of the object, the object key comprising a portion of the one or more recognizable portions of the object, the object key attached to the object and comprising recognizable features, wherein the object key is recognizable by the image capture device based on the recognizable features of the object key, the object key comprising a portion of the object visible in a same light spectrum as the object;

calculating a relative size of the object key with respect to a size of the object and a location of the object key with respect to the object; and

tracking one or more locations of the object from the relative size and location of the object with respect to the object key and based on capturing a plurality of images of the object key, using one or more image capture devices, at a resolution sufficient to identify the recognizable features of the object key and to track movement of the object key; and

periodically capturing, at a rate lower than a rate for the capturing of the plurality of images of the object key, an image of portions of the object that are not the object key at a resolution sufficient to identify recognizable features of the portions of the object that are not the object key and using the capture of the image of the portions of the object that are not the object key to verify that the object is still attached to the object key.

12. The apparatus of claim 11 , wherein tracking the one or more locations of the object comprises:

capturing images of portions of the object that are not the object key at a lower resolution than the resolution sufficient to identify the recognizable features of the object key while tracking movement of the object key;

capturing images of portions of the object that are not the object key at a lower rate than a rate of capturing images of the plurality of images of the object key; and/or

capturing images of the object key without capturing images of portions of the object that are not the object key.

13. The apparatus of claim 11 , the operations further comprising:

determining a degree of attachment between the object and the object key;

determining a verification rate based on the degree of attachment, wherein a higher degree of attachment results in a lower verification rate than a lower degree of attachment; and

periodically capturing, at the verification rate, an image of the object at a resolution sufficient to identify recognizable features of the object to verify that the object is still attached to the object key.

14. The apparatus of claim 11 , wherein the captured image of the object is captured with an image capture device, and wherein the captured plurality of images of the object key are captured using one or more image capture devices.

15. The apparatus of claim 11 , the operations further comprising identifying, in response to capturing the image of the object, the object key within the image of the object, wherein the object key is a recognizable element of the object with physical properties sufficient to identify the recognizable features of the object key and to track the one or more locations of the object by capturing the plurality of images of the object key.

16. The apparatus of claim 11 , the operations further comprising:

identifying, in response to capturing the image of the object, a plurality of potential object keys within the image of the object;

determining a degree of attachment between each of the plurality of object keys and the object; and

determining a degree of recognizability of each of the plurality of object keys, the degree of recognizability of an object key of the plurality of object keys comprising a measure of physical properties of the object key sufficient to identify the recognizable features of the object key and to track the one or more locations of the object by capturing the plurality of images of the object key,

wherein selecting the object key of the object comprises selecting an object key of the plurality of object keys based on the degree of attachment and the degree of recognizability of each object key of the plurality of object keys.

17. A program product comprising a non-volatile computer readable storage medium storing code, the code being configured to be executable by a processor to perform operations comprising:

capturing, using an image capture device, an image of an object to be tracked;

analyzing, using the image capture device, the image of the object to identify one or more recognizable portions of the object;

selecting an object key of the object, the object key comprising a portion of the one or more recognizable portions of the object, the object key attached to the object and comprising recognizable features, wherein the object key is recognizable by the image capture device based on the recognizable features of the object key, the object key comprising a portion of the object visible in a same light spectrum as the object;

calculating a relative size of the object key with respect to a size of the object and a location of the object key with respect to the object; and

tracking one or more locations of the object from the relative size and location of the object with respect to the object key and based on capturing a plurality of images of the object key, using one or more image capture devices, at a resolution sufficient to identify the recognizable features of the object key and to track movement of the object key; and

periodically capturing, at a rate lower than a rate for the capturing of the plurality of images of the object key, an image of portions of the object that are not the object key at a resolution sufficient to identify recognizable features of the portions of the object that are not the object key and using the capture of the image of the portions of the object that are not the object key to verify that the object is still attached to the object key.

18. The program product of claim 17 , wherein tracking the one or more locations of the object comprises:

capturing images of portions of the object that are not the object key at a lower resolution than the resolution sufficient to identify the recognizable features of the object key while tracking movement of the object key; and/or

capturing images of portions of the object that are not the object key at a lower rate than a rate of capturing images of the plurality of images of the object key.