Controller, control method, and program
The present technology relates to a controller, a control method, and a program that enable self-localization with lower power consumption. Provided are a selection unit that selects, from a horizontal camera mounted in a horizontal direction and a downward camera mounted in a downward direction, a camera used for self-localization depending on speed, and a self-localization unit that performs self-localization using an image obtained by imaging with the horizontal camera or the downward camera selected by the selection unit. The selection unit selects the horizontal camera in a case where the speed is equal to or higher than a predetermined speed, and selects the downward camera in a case where the speed is not equal to or higher than the predetermined speed. The present technology can be applied to a self-localization system.
1. A controller comprising:
circuitry configured to:
select, depending on speed, one of a plurality of horizontal cameras mounted in a horizontal direction or a downward camera mounted in a downward direction for self-localization,
divide an image captured by an omnidirectional camera into a plurality of divided images corresponding to a number of the plurality of horizontal cameras, wherein the image comprises surroundings of the omnidirectional camera,
extract a plurality of feature points from the plurality of divided images, and
in a case that one of the plurality of horizontal cameras is selected for self-localization, select a particular horizontal camera from the plurality of horizontal cameras that images an area including a large number of the plurality of feature points that move over time in a direction that matches a self-moving direction, and perform self-localization using the particular horizontal camera.
2. The controller according to claim 1 , wherein the circuitry is further configured to:
select the horizontal camera in a case where the speed is equal to or higher than a predetermined speed, and select the downward camera in a case where the speed is not equal to or higher than the predetermined speed.
3. The controller according to claim 2 , wherein the circuitry is further configured to:
select the particular horizontal camera predicted to capture an area from which features are easily extracted from among the plurality of horizontal cameras.
4. The controller according to claim 1 , wherein the circuitry is further configured to:
use a first algorithm for self-localization in a case where the particular horizontal camera is selected and use a second algorithm for self-localization in a case where the downward camera is selected,
wherein the first algorithm and the second algorithm are different algorithms.
5. The controller according to claim 4 , wherein
the first algorithm is block matching, and the second algorithm is a brightness gradient method.
6. The controller according to claim 1 , wherein
a certain position imaged by the particular horizontal camera selected at a current time is estimated, the certain position corresponding to a position of a particular feature point extracted from a second image captured by the particular horizontal camera at a time before the current time.
7. A control method comprising:
selecting, depending on speed, one of a plurality of horizontal cameras mounted in a horizontal direction or a downward camera mounted in a downward direction for self-localization,
dividing an image captured by an omnidirectional camera into a plurality of divided images corresponding to a number of the plurality of horizontal cameras, wherein the image comprises surroundings of the omnidirectional camera,
extracting a plurality of feature points from the plurality of divided images, and
in a case that one of the plurality of horizontal cameras is selected for self-localization, selecting a particular horizontal camera from the plurality of horizontal cameras that images an area including a large number of the plurality of feature points that move over time in a direction that matches a self-moving direction, and performing self-localization using the particular horizontal camera.
8. A program comprising computer readable instructions stored on a non-transitory computer readable medium, the program for causing a computer to perform processing comprising:
selecting, depending on speed, one of a plurality of horizontal cameras mounted in a horizontal direction or a downward camera mounted in a downward direction for self-localization,
dividing an image captured by an omnidirectional camera into a plurality of divided images corresponding to a number of the plurality of horizontal cameras, wherein the image comprises surroundings of the omnidirectional camera,
extracting a plurality of feature points from the plurality of divided images, and
in a case that one of the plurality of horizontal cameras is selected for self-localization, selecting a particular horizontal camera from the plurality of horizontal cameras that images an area including a large number of the plurality of feature points that move over time in a direction that matches a self-moving direction, and performing self-localization using the particular horizontal camera.