Autonomous vehicle object detection
Methods, systems, and apparatuses related to autonomous vehicle object detection are described. An autonomous vehicle can capture an image corresponding to an unknown object disposed within a sight line of the autonomous vehicle. Processing resources available to a plurality of memory devices associated with the autonomous vehicle can be reallocated in response to capturing the image and an operation involving the image corresponding to the unknown object to classify the unknown object can be performed using the reallocated processing resources.
1. An autonomous vehicle, comprising:
a first memory device comprising a first type of media;
a second memory device comprising a second type of media;
and a controller configured to:
execute instructions to perform a traffic sequence prediction operation, wherein the traffic sequence prediction operation involves determining a likelihood that the autonomous vehicle will encounter greater than or less than a threshold quantity of objects within a particular threshold period of time;
reallocate processing resources available to the first memory device and the second memory device responsive to the traffic sequence prediction operation;
cause at least one image corresponding to an unknown object to be captured; and
perform, using the reallocated processing resources, an operation involving the captured at least one image to classify the unknown object.
2. The autonomous vehicle of claim 1 , wherein the threshold quantity of objects is a total quantity of objects including known and unknown objects.
3. The autonomous vehicle of claim 1 , wherein the first memory device and the second memory device have different corresponding performance characteristics.
4. The autonomous vehicle of claim 3 , wherein the first memory device and the second memory device have different corresponding bandwidths.
5. The autonomous vehicle of claim 3 , wherein the controller is configured to reallocate the processing resources available to the first memory device and the second memory device such that a greater amount of processing resources are available to the memory device that has a higher corresponding performance characteristics.
6. The autonomous vehicle of claim 3 , wherein the first memory device and the second memory device have different corresponding memory access times, and wherein the controller is configured to reallocate the processing resources available to the first memory device and the second memory device such that a greater amount of processing resources are available to the memory device that has a faster corresponding memory access time.
7. A method, comprising:
capturing, by an autonomous vehicle, an image corresponding to an unknown object disposed within a sight line of the autonomous vehicle;
responsive to capturing the image, reallocating processing resources available to a plurality of memory devices associated with the autonomous vehicle, wherein reallocating the processing resources includes increasing the amount of processing resources available to the plurality of memory devices based on respective performance characteristics corresponding to the plurality of memory devices;
performing, using the reallocated processing resources, an operation involving the image corresponding to the unknown object to classify the unknown object,
receiving information corresponding to the unknown object from a resource external to the autonomous vehicle; and
using the information received from the resource external to the autonomous vehicle along with data corresponding to the captured image to classify the unknown object.
8. The method of claim 7 , further comprising comparing the captured image corresponding to the unknown object to at least one image stored by the autonomous vehicle that is determined to be similar to the unknown object to classify the unknown object.
9. The method of claim 7 , wherein the plurality of memory devices comprises at least two different types of memory devices.
10. The method of claim 9 , wherein the at least two different types of memory devices includes at least two different types of nonvolatile memory devices.
11. An apparatus, comprising:
a first memory device comprising a first type of media; a second memory device comprising a second type of media; an imaging device; and a controller to:
perform a traffic sequence prediction operation;
reallocate processing resources available to the autonomous vehicle among the second memory device and the first memory device in response to a result of the traffic sequence prediction operation, wherein the result of the traffic sequence prediction operation corresponds to a determination that greater than a threshold quantity of objects will be encountered by the apparatus within a threshold period of time; and
perform, using the reallocated processing resources, an operation involving an image captured by the imaging device and corresponding to an unknown object to classify the unknown object.
12. The apparatus of claim 11 , wherein the apparatus is an electronic control unit of an autonomous vehicle.
13. The apparatus of claim 11 , wherein the controller is to reallocate the processing resources available to the autonomous vehicle among the second memory device and the first memory device based on respective performance characteristics corresponding to the first memory device and the second memory device.
14. The apparatus of claim 11 , wherein the controller is to reallocate the processing resources available to the autonomous vehicle among the second memory device and the first memory device based on respective bandwidths, memory access times, or both, corresponding to the first memory device and the second memory device.
15. The apparatus of claim 11 , wherein the controller is to reallocate processing resources available to the autonomous vehicle among the second memory device and the first memory device prior to image being captured by the imaging device.
16. The apparatus of claim 11 , wherein the first memory device is a NAND memory device and the second memory device is a DRAM device.
17. An autonomous vehicle, comprising:
a first memory device comprising a first type of media;
a second memory device comprising a second type of media;
and a controller configured to:
execute instructions to perform a traffic sequence prediction operation;
reallocate processing resources available to the first memory device and the second memory device responsive to the traffic sequence prediction operation;
cause at least one image corresponding to an unknown object to be captured; and
perform, using the reallocated processing resources, an operation involving the captured at least one image to classify the unknown object;
wherein the first memory device and the second memory device have different corresponding performance characteristics; and
wherein the controller is further configured to reallocate the processing resources available to the first memory device and the second memory device such that a greater amount of processing resources are available to the memory device that has a higher corresponding performance characteristics.
18. An apparatus, comprising:
a first memory device comprising a first type of media;
a second memory device comprising a second type of media;
an imaging device; and a controller to: perform a traffic sequence prediction operation;
reallocate processing resources available to the autonomous vehicle among the second memory device and the first memory device in response to a result of the traffic sequence prediction operation; and
perform, using the reallocated processing resources, an operation involving an image captured by the imaging device and corresponding to an unknown object to classify the unknown object; and
wherein the controller is configured to reallocate processing resources available to the autonomous vehicle among the second memory device and the first memory device prior to the image being captured by the imaging device.