Information processing method, information processing apparatus, and storage medium

Patent metadata

Field	Value
Publication number	US-9921689-B2
Application number	US-201514953988-A
Country	US
Kind code	B2
Filing date	Nov 30, 2015
Priority date	Dec 4, 2014
Publication date	Mar 20, 2018
Grant date	Mar 20, 2018

Abstract

An information processing method including: storing sequential data relating to movements of a target object over a specified plane, sequentially estimating a plurality of first likelihoods of a position of the target object in a direction of the specified plane based on the sequential data, each of the plurality of first likelihoods associating with each hypothesis on the movements of the target object, sequentially estimating a plurality of second likelihoods of touch of the target object on the specified plain based on the sequential data, each of the plurality of second likelihoods corresponding to each of the plurality of first likelihoods, and updating the plurality of first likelihoods based on the plurality of second likelihoods.

First claim

What is claimed is:

1. An information processing method comprising:
storing sequential data relating to movements of a target object over a specified plane;
generating a position hypothesis related to a candidate position of the target object at each sequential time point based on the stored sequential data;
sequentially estimating a plurality of first likelihoods of a position of the target object in a direction of the specified plane based on the sequential data, each of the plurality of first likelihoods being associated with a generated position hypothesis;
sequentially estimating a plurality of second likelihoods of touch of the target object on the specified plane based on the sequential data, each of the plurality of second likelihoods corresponding to one of the plurality of first likelihoods;
updating the plurality of first likelihoods based on the plurality of second likelihoods; and
determining a position of the target object in the direction of the specified plane based on the updated plurality of first likelihoods.

2. The information processing method according to claim 1 , wherein
the plurality of first likelihoods are estimated based on Multiple Hypothesis Tracking (MHT).

3. The information processing method according to claim 2 , wherein a tree of MHT is generated by adding a plurality of nodes each corresponding to each hypothesis on the movements in a Tth timing to a node corresponding to a hypothesis on the movements in a T−1th timing.

4. The information processing method according to claim 3 , the tree is pruned for each specified hierarchy based on each hypothesis on the movements.

5. The information processing method according to claim 3 , wherein
the plurality of nodes each corresponding to each hypothesis on the movements includes a first node, a second node, and a third node,
the first node corresponds to a first hypothesis on the movements under which the target object touches on the specified plane and which a corresponding first likelihood is estimated using the sequential data in Tth timing,
the second node corresponds to a second hypothesis on the movements under which the target object touches on the specified plane and which a corresponding first likelihood is estimated without using the sequential data in Tth timing, and
the first node corresponds to a first hypothesis on the movements under which the target object does not touch on the specified plane and which a corresponding first likelihood is estimated without using the sequential data in Tth timing.

6. The information processing method according to claim 1 , wherein the plurality of second likelihoods are estimated based on Dynamic Bayesian Network (DBN).

7. The information processing method according to claim 6 , wherein
the plurality of second likelihoods is estimated based on a plurality of DBNs each corresponding to each type of each hypothesis on the movements.

8. The information processing method according to claim 1 , wherein
the plurality of first likelihoods is estimated based on a specified movement model of the target object.

9. The information processing method according to claim 1 , further comprising:
determining whether the target object touches to the specified plane or not based on the plurality of second likelihoods.

10. An information processing apparatus comprising:
a memory configured to store sequential data relating to movements of a target object over a specified plane; and
a processor coupled to the memory and configured to:
generate a position hypothesis related to a candidate position of the target object at each sequential time point based on the stored sequential data;
sequentially estimate a plurality of first likelihoods of a position of the target object in a direction of the specified plane based on the sequential data, each of the plurality of first likelihoods being associated with a generated position hypothesis,
sequentially estimate a plurality of second likelihoods of touch of the target object on the specified plane based on the sequential data, each of the plurality of second likelihoods corresponding to one of the plurality of first likelihoods;
updating the plurality of first likelihoods based on the plurality of second likelihoods; and
determining a position of the target object in the direction of the specified plane based on the updated plurality of first likelihoods.

11. A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the computer including a memory, the process comprising:
storing sequential data relating to movements of a target object over a specified plane;
generating a position hypothesis related to a candidate position of the target object at each sequential time point based on the stored sequential data;
sequentially estimating a plurality of first likelihoods of a position of the target object in a direction of the specified plane based on the sequential data, each of the plurality of first likelihoods being associated with a generated position hypothesis;
sequentially estimating a plurality of second likelihoods of touch of the target object on the specified plane based on the sequential data, each of the plurality of second likelihoods corresponding to one of the plurality of first likelihoods;
updating the plurality of first likelihoods based on the plurality of second likelihoods; and
determining a position of the target object in the direction of the specified plane based on the updated plurality of first likelihoods.

Assignees

• Fujitsu Ltd

Inventors

• Chen Bin
• Murakawa Yoshihiko
• Yasukawa Yusuke

Classifications

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06V10/75

  Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries · CPC title

• G06V10/143

  Sensing or illuminating at different wavelengths · CPC title

• G06V10/56

  relating to colour · CPC title

• G06T2207/20076

  Probabilistic image processing · CPC title