IP Library Granted Patent US 10,949,656
Granted Patent B2
US 10,949,656 · App. 15/760,380 · Granted Mar 16, 2021

Information processing apparatus and information processing method

Inventors: Suguru Aoki (Tokyo, JP); Taketo Akama (Tokyo, JP); Hideki Oyaizu (Tokyo, JP); Yasutaka Hirasawa (Tokyo, JP); Yuhi Kondo (Tokyo, JP)
Assignee: SONY CORPORATION
G06K9/00335G06K9/00342G06K9/00348G06K9/00805G06T7/246G06T7/60G08G1/16G08G1/166B60W50/14G06K9/00369
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,949,656
App. No.
15/760,380
Granted
Mar 16, 2021
Kind
B2
Abstract

An information processing apparatus according to an embodiment of the present technology includes a detection unit, an estimation unit, and a prediction unit. The detection unit detects a target object from an input image. The estimation unit estimates a posture of the detected target object. The prediction unit predicts an action of the target object on a basis of the estimated posture.

Claims (53)

1. An information processing apparatus, comprising:

circuitry configured to:

detect a target object from an input image;

calculate at least one contact point of the detected target object with a road surface;

set a ground line in a vertical direction from the calculated at least one contact point;

determine a relative position of a feature point of the target object with respect to the set ground line;

estimate a posture of the target object based on the determined relative position of the feature point of the target object; and

predict an action of the target object based on the estimated posture.

2. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to:

detect a pedestrian from the input image; and

predict an action of the pedestrian based on an estimated posture of the pedestrian.

3. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to:

detect a two-wheeled vehicle and a rider from the input image;

estimate a posture of the rider; and

predict an action of the two-wheeled vehicle and an action of the rider, based on the estimated posture of the rider.

4. The information processing apparatus according to claim 3 , wherein the circuitry is further configured to:

estimate a posture of the two-wheeled vehicle; and

predict the action of the two-wheeled vehicle and the action of the rider, based on the estimated posture of each of the two-wheeled vehicle and the rider.

5. The information processing apparatus according to claim 1 , wherein the feature point is a barycenter point of the target object.

6. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to:

detect a two-wheeled vehicle and a rider from the input image; and

calculate, as the feature point, one of a barycenter point of the rider or an overall barycenter point of the two-wheeled vehicle and the rider.

7. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to predict a movement direction of the target object.

8. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to predict an abrupt acceleration of the target object.

9. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to estimate a framework of the detected target object.

10. The information processing apparatus according to claim 1 , wherein

the information processing apparatus is mounted on a mobile object apparatus, and

the circuitry is further configured to:

generate danger avoidance information, to avoid a danger related to a drive of the mobile object apparatus, based on the predicted action of the target object; and

output the generated danger avoidance information.

11. The information processing apparatus according to claim 10 , wherein the circuitry is further configured to:

judge a possibility of a contact of the mobile object apparatus and the target object; and

output information on the judged possibility.

12. The information processing apparatus according to claim 10 , wherein the circuitry is further configured to:

predict a movement direction of the target object; and

output an image including the predicted movement direction.

13. The information processing apparatus according to claim 10 , wherein

the circuitry is further configured to output an image including a dangerous area, and

in the dangerous area, a contact of the mobile object apparatus and the target object is possible.

14. An information processing method, comprising:

detecting a target object from an input image;

calculating at least one contact point of the detected target object with a road surface;

setting a ground line in a vertical direction from the calculated at least one contact point;

determining a relative position of a feature point of the target object with respect to the set ground line;

estimating a posture of the target object based on the determined relative position of the feature point of the target object; and

predicting an action of the target object based on the estimated posture.

15. A non-transitory computer-readable medium having stored thereon computer-executable instructions, which when executed by an information processing apparatus, cause the information processing apparatus to execute operations, the operations comprising:

detecting a target object from an input image;

calculating at least one contact point of the detected target object with a road surface;

setting a ground line in a vertical direction from the calculated at least one contact point;

determining a relative position of a feature point of the target object with respect to the set ground line;

estimating a posture of the target object based on the determined relative position of the feature point of the target object; and

predicting an action of the target object based on the estimated posture.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 15, 2018
From: AOKI, SUGURU; AKAMA, TAKETO; OYAIZU, HIDEKI; HIRASAWA, YASUTAKA; KONDO, YUHI
To: SONY CORPORATION
Reel/Frame 045235/0294 →
Priority Claims (1)
JP JP2015-191187 · Sep 29, 2015 · national
Continuity (1)
Related Publication 20180253595A1 · Sep 6, 2018
Cited By (1)
US 12,354,285