Information processing apparatus, information processing method, program, and moving body
An information processing apparatus includes a first self-position estimating section configured to estimate a self-position of a moving body using a visible image, a second self-position estimating section configured to estimate the self-position of the moving body using an infrared image, and a combining section configured to set, based on a situation in which the moving body is placed, a first weight for a first estimation result obtained by self-position estimation using the visible image and a second weight for a second estimation result obtained by self-position estimation using the infrared image, to thereby combine the first estimation result and the second estimation result using the first weight and the second weight. The present technology is applicable to moving bodies, for example, vehicles.
1. An information processing apparatus comprising:
a first self-position estimating section configured to estimate a self-position of a moving body using a visible image;
a second self-position estimating section configured to estimate the self-position of the moving body using an infrared image; and
a combining section configured to set, based on a situation in which the moving body is placed, a first weight for a first estimation result obtained by self-position estimation using the visible image and a second weight for a second estimation result obtained by self-position estimation using the infrared image, to thereby combine the first estimation result and the second estimation result using the first weight and the second weight.
2. The information processing apparatus according to claim 1 ,
wherein the situation in which the moving body is placed includes at least one of weather, brightness, time, or a location.
3. The information processing apparatus according to claim 2 ,
wherein the combining section increases the first weight and decreases the second weight in daytime.
4. The information processing apparatus according to claim 2 ,
wherein the combining section decreases the first weight and increases the second weight at night.
5. The information processing apparatus according to claim 2 ,
wherein the combining section increases the first weight and decreases the second weight in a case where the moving body is in a downtown area.
6. The information processing apparatus according to claim 2 ,
wherein the combining section increases the first weight and decreases the second weight in a case where the moving body travels at a speed equal to or higher than a predetermined threshold.
7. The information processing apparatus according to claim 2 ,
wherein the combining section decreases the first weight and increases the second weight in a case where it is foggy.
8. The information processing apparatus according to claim 2 ,
wherein the combining section decreases the first weight and increases the second weight in a case where it is snowing.
9. The information processing apparatus according to claim 1 ,
wherein the first weight and the second weight are set based on an effect of each situation on an image quality of the visible image and an effect of each situation on an image quality of the infrared image.
10. The information processing apparatus according to claim 9 ,
wherein the first weight and the second weight are set based on a relative relationship between the effect of each situation on the image quality of the visible image and the effect of each situation on the image quality of the infrared image.
11. The information processing apparatus according to claim 9 ,
wherein the first weight is increased in a situation where the image quality of the visible image is high, and
the second weight is increased in a situation where the image quality of the infrared image is high.
12. The information processing apparatus according to claim 1 ,
wherein the combining section decreases an error variance with respect to the first estimation result as the first weight is increased, and decreases an error variance with respect to the second estimation result as the second weight is increased, to thereby combine the first estimation result and the second estimation result using an extended Kalman filter.
13. The information processing apparatus according to claim 1 ,
wherein the first self-position estimating section and the second self-position estimating section estimate at least one of a position or an attitude of the moving body.
14. The information processing apparatus according to claim 1 ,
wherein the first self-position estimating section estimates the self-position of the moving body based on at least one of a feature point or a landmark in the visible image, and
the second self-position estimating section estimates the self-position of the moving body based on a landmark in the infrared image.
15. The information processing apparatus according to claim 1 , further comprising:
a situation detecting section configured to detect the situation in which the moving body is placed.
16. The information processing apparatus according to claim 1 ,
wherein the visible image is taken by a visible image sensor, and
the infrared image is taken by an infrared image sensor.
17. An information processing method comprising:
by an information processing apparatus,
estimating a self-position of a moving body using each visible image and infrared image; and
setting, based on a situation in which the moving body is placed, a first weight for a first estimation result obtained by self-position estimation using the visible image and a second weight for a second estimation result obtained by self-position estimation using the infrared image, to thereby combine the first estimation result and the second estimation result using the first weight and the second weight.
18. A non-transitory computer readable medium storing a program for causing a computer to execute processing of:
estimating a self-position of a moving body using each visible image and infrared image; and
setting, based on a situation in which the moving body is placed, a first weight for a first estimation result obtained by self-position estimation using the visible image and a second weight for a second estimation result obtained by self-position estimation using the infrared image, to thereby combine the first estimation result and the second estimation result using the first weight and the second weight.
19. A moving body comprising:
a visible image sensor configured to take a visible image;
an infrared image sensor configured to take an infrared image;
a first self-position estimating section configured to estimate a self-position using the visible image;
a second self-position estimating section configured to estimate the self-position using the infrared image; and
a combining section configured to set, based on a situation in which the moving body is placed, a first weight for a first estimation result obtained by self-position estimation using the visible image and a second weight for a second estimation result obtained by self-position estimation using the infrared image, to thereby combine the first estimation result and the second estimation result using the first weight and the second weight.