OBJECT POSITION TRACKING SYSTEM AND METHOD

• US 20110064269A1
• Filed: 11/30/2009
• Published: 03/17/2011
• Est. Priority Date: 09/14/2009
• Status: Abandoned Application

• Current Assignee: Manipal Institute of Technology
• Original Assignee: Manipal Institute of Technology
• Inventors: Rajpurohit, Vijay S., PAI M.M, Manohara
• Application Number:
  US12/627,709
• Publication Number:
  US 20110064269A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/24765 Rule-based classification
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 20/36 Indoor scenes
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

A method of tracking an object is provided. The method includes obtaining sensed positions of the object at a plurality of time instants and predicting a future position of the object by applying fuzzy predictive rules to the sensed positions of the object obtained from at least two previous time instants.

Claims

1. A method of tracking an object, comprising:

obtaining sensed positions of the object at a plurality of time instants; and

predicting a future position of the object by applying fuzzy predictive rules to the sensed positions of the object obtained from at least two previous time instants.

2. The method of claim 1, wherein the at least two previous time instants are two substantially equal time instants.

3. The method of claim 1, further comprising generating the fuzzy predictive rules using the sensed position of the object at the plurality of time instants, and refining the plurality of fuzzy predictive rules by correcting structural errors in the fuzzy predictive rules.

4. The method of claim 3, comprising:

obtaining first and second sensed positions of the object with reference to a sensing device at first and second time instants respectively;

obtaining a third sensed position of the object at a third time instant; and

generating the fuzzy predictive rule using the first and second sensed positions as antecedents and the third sensed position as a consequent of the fuzzy predictive rule.

5. The method of claim 4, wherein each of the first, second and third sensed positions comprises a distance range and an angle of the object with reference to the sensing device.

6. The method of claim 4, further comprising partitioning a navigation space of the object into a plurality of fuzzy subsets based upon the distance range and the angle, wherein each of the first second and third sensed positions corresponds to one of the plurality of range and angle subsets.

7. The method of claim 3, further comprising:

identifying the structural errors in the plurality of fuzzy predictive rules using fuzzy Petri nets; and

correcting the identified structural errors in the plurality of fuzzy predictive rules to generate optimized fuzzy predictive rules.

8. The method of claim 7, wherein identifying the structural errors comprises identifying at least one of missing fuzzy predictive rules, conflicting fuzzy predictive rules, circular fuzzy predictive rules and redundant fuzzy predictive rules via a reachability graph of the fuzzy Petri net.

9. The method of claim 8, further comprising selectively partitioning the navigation space of the object to alter or remove identified conflicting fuzzy predictive rules.

10. The method of claim 8, further comprising estimating a reliability factor for each of the identified conflicting and redundant fuzzy predictive rules and removing conflicting and redundant fuzzy predictive rules based upon the estimated reliability factor.

11. The method of claim 1, wherein predicting the position of the object comprises defuzzifying a position output obtained by applying the fuzzy predictive rules to the sensed position obtained from at least two previous time instants.

12. A method of tracking an object, comprising:

generating a plurality of fuzzy predictive rules using sensed positions of the object at a plurality of time instants;

optimizing the plurality of fuzzy predictive rules by removing or altering at least one of missing fuzzy predictive rules, conflicting fuzzy predictive rules, circular fuzzy predictive rules and redundant fuzzy predictive rules to generate optimized fuzzy predictive rules;

obtaining first and second sensed positions of the object at first and second time instants; and

predicting the position of the object at a third time instant by applying the optimized fuzzy predictive rules to the first and second sensed positions.

13. The method of claim 12, wherein each of the first, second and third sensed positions comprises a distance range and an angle of the object with reference to a sensing device.

14. The method of claim 12, wherein optimizing the plurality of fuzzy predictive rules comprises:

characterizing the plurality of fuzzy predictive rules using fuzzy Petri nets;

identifying the at least one of missing fuzzy predictive rules, conflicting fuzzy predictive rules, circular fuzzy predictive rules and redundant fuzzy predictive rules via a reachability graph of the fuzzy Petri nets; and

removing or altering the identified conflicting and redundant fuzzy predictive rules by selectively partitioning the navigation space of the object or by using a reliability factor in a table-lookup operation.

15. The method of claim 12, further comprising defuzzifying a position output at the third time instant.

16. An object position tracking system, comprising:

a sensing device configured to obtain a plurality of sensed positions of an object in an environment;

a memory circuit configured to store a plurality of fuzzy predictive rules for estimation of future positions of the object based upon the sensed positions; and

a processor configured to predict the future position of the object by applying the fuzzy predictive rules to sensed positions of the object for at least two previous time instants.

17. The object position tracking system of claim 16, further comprising a simulator configured to receive sensed positions of the object and to generate the fuzzy predictive rules from the sensed positions.

18. The object position tracking system of claim 16, further comprising a plurality of sensors disposed at multiple locations to sense the position of the object within the environment.

19. The object position tracking system of claim 16, wherein the sensing device comprises a stereo vision based sensor.

20. The object position tracking system of claim 16, wherein the processor is configured to develop a polar position map of a navigation space of the object wherein each sensed position is characterized by a distance range and an angle of the object in the polar position map.