Method, system and device for detecting an object proximate to a water/air type interface

• US 20040036766A1
• Filed: 06/05/2003
• Published: 02/26/2004
• Est. Priority Date: 12/06/2000
• Status: Active Grant

• Current Assignee: Vision Industries Group Incorporated
• Original Assignee: Vision Industries Group Incorporated
• Inventors: Lefebure, Martin, Guichard, Frederic, Meniere, Jerome, Migliorini, Christophe
• Granted Patent: US 7,362,351 B2
• Time in Patent Office: Days
• US Class Current: 348/135
• CPC Class Codes: G01V 8/10 Detecting, e.g. by using light barriers by reflection from the object G01S17/00
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G08B 21/082 by monitoring electrical characteristics of the water

Abstract

A method and system for detecting an object in a zone located proximate to an interface between two liquid and/or gaseous media having different refractive indices, for example of the air/water type. The method and system produce at least a video image of the interface and the zone and produces electric signals representing each video image. Then, the electric signals are digitized and the data is processed by discriminating the data corresponding to the video image of the real object from those corresponding to the apparent video image generated by the interface.

Claims

1. A method for detecting an object (601) in a zone (603) situated in the proximity of an interface (602) between two liquid media (604) and/or gaseous media (605) having different refractive indices, especially an interface of water/air type;

within the meaning of the present invention, “

in the proximity of”

also denotes “

at the interface (602)”

;

the said method comprising the following stages;

the stage of creating at least one video image of the said interface (602) and of the said zone (603) from at least one observation point (607), each of the observation points being situated on one side of the said interface (602);

the stage of producing electrical signals (608) representative of each video image;

the stage of digitizing the electrical signals (608) in such a way as to produce data corresponding to each video image;

the stage of processing the said data, while discriminating the data corresponding to the video image of a real object (601) from those that correspond to the apparent video image generated by the said interface (602).

2. A method according to claim 1;

the said object (601) being illuminated by light that produces reflections at the said interface (602);

the said method comprising the following stage;

the stage of creating at least one video image of the said interface (602) and of the said zone (603) by using a polarizing filter (611) to eliminate, at least partly, the light reflections at the said interface (602).

3. A method according to any one of claims 1 or 2;

the said method being such that, to process the said data while discriminating the data corresponding to the said video image of a real object (601) from those corresponding to the said apparent video image generated by the said interface (602), calottes (within the meaning of the present invention) are generated and/or primitives (within the meaning of the present invention) are associated with each pixel of the said video image.

Branch 1

4. A method according to claim 3;

the said method being such that the stage of processing the said data comprises the following stages;

the stage of associating characteristics with each calotte;

the stage of deducing the presence of an object (601) if the characteristics exceed a predetermined threshold SC.

5. A method according to claim 4, intended more particularly to discriminate between a stationary object (601) and a moving object (601);

the said method also comprising the following stages;

the stage of iterating, at specified time intervals, the process, specified in claim 4, of deducing the presence of an object (601);

the stage of calculating the number of times that the object (601) is detected during a specified time period T1;

the stage of discriminating, at a point of the said zone (603), between the objects (601) that are present a number of times larger than a specified threshold S1 (the said objects being referred to hereinafter as stationary objects) and the objects (601) that are present a number of times smaller than the said specified threshold S1 (the said objects being referred to hereinafter as moving objects).

6. A method according to claim 5, intended more particularly to determine whether a stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the said method also comprising the following stages;

the stage of calculating (707) the mean fluctuation per unit time of the gray levels of the said video images of the said object (601);

Case in which the object (601) is situated on the other side of the interface (602);

the stage of detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels larger than a specified threshold S3 (the said objects being referred to hereinafter as objects situated on the other side of the interface (602))

Case in which the object (601) is situated on the same side of the interface (602);

the stage of detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels smaller than a specified threshold S4 (the said objects being referred to hereinafter as objects situated on the same side of the interface (602)), the said threshold S4 being smaller than the threshold S3

Case in which the object (601) is situated at the interface (602);

the stage of detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels between the threshold S3 and the threshold S4 (the said objects being referred to hereinafter as objects situated at the interface (602)).

7. A method according to claim 5, intended more particularly to determine whether a stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the said method also comprising the following stage;

the stage of performing a stereoscopic analysis of the object (601) that is stationary relative to the said interface (602).

8. A method according to one of claims 6 or 7, also comprising the following stage:

the stage of emitting a warning signal (711) according to the detection criteria applied in one or the other of the cases specified in claim 6 or in claim 7, especially in the presence of a stationary object (601) situated under the surface of a water/air interface (602).

9. A method according to any one of claims 4 to 8, intended more particularly to detect the appearance of new objects (601) in the said zone (603);

the said method also comprising;

the stage of iterating, at specified time intervals, the process, specified in claim 4, for deducing the presence of an object (601);

the stage of calculating the number of times that the object (601) is detected during a specified time period T2;

the said time period T2 being chosen to be longer than the duration of the phenomena associated with the objects (601) being detected;

the stage of discriminating, at a point of the said zone (603), between the objects (601) that are present a number of times larger than a specified threshold S2 (the said objects being referred to hereinafter as usually present objects) and the objects (601) that are present a number of times smaller than the said specified threshold S2 (the said objects being referred to hereinafter as new objects).

10. A method according to claims 5 and 9 taken in combination, intended more particularly to detect new and stationary objects (601);

the said method being such that the time period T1 is chosen to be shorter than time period T2.

11. A method according to any one of claims 4 to 10, intended more particularly to yield a statistical estimate of the time of occupancy of the said zone Z (603) by at least one object (601) during a specified time period T;

the said method comprising the following stages;

the stage of performing a partition of the said zone (603) into elemental zones Δ

z,

the stage of applying the process, specified in claim 4, of deducing the presence of an object (601) in an elemental zone Δ

z (603) during elemental time intervals Δ

t;

the stage of calculating the number of times Δ

t/T that an object (601) is present in an elemental zone Δ

z (603) during the specified time period T.

12. A method according to any one of claims 4 to 11;

the said method also comprising the following stage;

the stage of calculating the trajectory of objects (601) whose presence has been detected.

13. A method according to claim 12, intended more particularly to detect the disappearance of an object (601) in a specified zone (603), especially the disappearance of a swimmer at the seashore;

the said method comprising the following stages;

the stage of detecting when a trajectory stops at the boundary of the said zone (603), especially beyond the surveillance limits.

Branch 2

14. A method according to claim 3, intended more particularly to detect a stationary object (601) in the proximity of the said interface (602);

the said method being such that the stage of processing the said data comprises the following stages;

the stage of validating a primitive as stationary if, during n successive time intervals Δ

t composing a specified time period T5, the said primitive is materialized (within the meaning of the present invention) at least a number of times larger than a specified threshold S5;

the stage of calculating and searching for the virtual images of stationary objects (601) (within the meaning of the present invention).

15. A method according to claim 14, intended more particularly to detect a new stationary object (601) in the proximity of the said interface (602);

the said method comprising the following stages;

the stage of iterating, at successive time intervals Δ

t composing a specified time period T6, the process, specified in claim 14, of detecting the presence of a stationary object (601),

the stage of calculating the number of times that an object (601) is detected as being stationary during the said specified time period T6;

the said time period T6 being chosen to be longer than the duration of the phenomena associated with the object (601) being detected;

the said time period T6 being shorter than the said time period T5,

the stage of discriminating, at a point of the said zone (603), between a stationary object (601) that is present a number of times larger than a specified threshold S6 and an object (601) that is present a number of times smaller than the said specified threshold S6 (the said object being referred to hereinafter as the new stationary object).

16. A method according to claim 15, intended more particularly to determine whether a stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the said method comprising the following stages;

the stage of iterating, at successive time intervals Δ

t composing a specified time period T7, the process, specified in claim 14, of detecting the presence of a stationary object (601),

the stage of calculating the number of times that an object (601) is detected as being stationary and new during the said specified time period T7;

the said time period T7 being chosen to be longer than the duration of the phenomena being observed;

the said time period T7 being shorter than the said time period T6,

Case in which the object (601) is situated on the other side of the interface (602);

the stage of detecting, at a point of the said zone (603), between an object (601) that is present a number of times larger than a specified threshold S7 and an object (601) that is present a number of times smaller than the said specified threshold S7 (the said object being referred to hereinafter as the new stationary object situated on the other side of the interface (602));

Case in which the object (601) is situated on the same side of the interface (602);

the stage of detecting, at a point of the said zone (603), between an object (601) that is present a number of times larger than a specified threshold S8 and an object (601) that is present a number of times smaller than the said specified threshold S8 (the said object being referred to hereinafter as the new stationary object situated on the same side of the interface (602));

the said threshold S8 being smaller than the threshold S7;

Case in which the object (601) is situated at the interface (602);

the stage of detecting, at a point of the said zone (603), an object (601) that is present a number of times between the threshold S7 and the threshold S8

(the said objects being referred to hereinafter as objects situated at the interface (602)).

17. A method according to claim 16, also including the stage of emitting a warning signal (711) according to the detection criteria applied in one or the other of the cases specified in claim 16, especially in the presence of a stationary object (601) situated under the surface of a water/air interface (602).

System

35. A method according to any one of claims 1 to 17, intended more particularly for surveillance of a swimming pool.

37. The application of the method according to any one of claims 1 to 17 to surveillance of a swimming pool.

18. A system for detecting an object (601) in a zone (603) situated in the proximity of an interface (602) between two liquid media (604) and/or gaseous media (605) having different refractive indices, especially an interface of the water/air type;

within the meaning of the present invention, “

in the proximity of”

also denotes “

at the interface (602)”

;

the said system comprising;

the following stages;

means, especially a video camera (606), for creating at least one video image of the said interface (602) and of the said zone (603) from at least one observation point (607), each of the observation points being situated on one side of the said interface (602);

digital conversion means (609) for producing digital data from the electrical signals (608) representative of each video image;

information-processing means (700) for discriminating the data corresponding to the video image of a real object (601) from those corresponding to the apparent video image generated by the said interface (602).

19. A system according to claim 18;

the said object (601) being illuminated by light that produces reflections at the said interface (602);

the said system being such that the said means for creating at least one video image of the said interface (602) and of the said zone (603) comprise a polarizing filter (611) to eliminate, at least partly, the light reflections at the said interface (602).

20. A system according to any one of claims 18 or 19;

the said information-processing means for discriminating the data corresponding to the video image of a real object (601) from those corresponding to the apparent video image generated by the said interface (602) comprising calculating means (702) (701) for;

generating calottes (within the meaning of the present invention), and/or

associating primitives with each pixel of the said video image (within the meaning of the present invention).

Branch 1

21. A system according to claim 20;

the said system being such that the said information-processing means (700) comprise calculating means (702) (701) for;

associating characteristics with each calotte;

deducing the presence of an object (601) if the characteristics exceed a predetermined threshold SC.

22. A system according to claim 21, intended more particularly to discriminate between a stationary object (601) and a moving object (601);

the said system also comprising;

iterating means (703) for iterating, at specified time intervals, the process, specified in claim 21, of deducing the presence of an object (601);

the said calculating means (702) (701) comprising;

totalizers (705) for calculating the number of times that the object (601) is detected during a specified time period T1;

discriminators (706) for discriminating, at a point of the said zone (603), between the objects (601) that are present a number of times larger than a specified threshold S1 (the said objects (601) being referred to hereinafter as stationary objects (601)) and the objects (601) that are present a number of times smaller than the said specified threshold S1 (the said objects (601) being referred to hereinafter as moving objects (601)).

23. A system according to claim 22, intended more particularly to determine whether a stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the calculating means (702) (701) also comprising;

means for calculating (707) the mean fluctuation per unit time of the gray levels of the said video images of the said object (601),

Case in which the object (601) is situated on the other side of the interface (602);

the said calculating means (702) (701) also comprising;

detecting means S3 (708a) for detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels larger than a specified threshold S3 (the said objects (601) being referred to hereinafter as objects (601) situated on the other side of the interface (602)),

Case in which the object (601) is situated on the same side of the interface (602);

detecting means S4 (708b) for detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels smaller than a specified threshold S4 (the said objects (601) being referred to hereinafter as objects (601) situated on the same side of the interface (602)), the said threshold S4 being smaller than the threshold S3

Case in which the object (601) is situated at the interface (602);

detecting means S3/S4 (708c) for detecting, at a point of the said zone (603), the objects (601) that exhibit a mean fluctuation per unit time of the gray levels between the threshold S3 and the threshold S4 (the said objects (601) being referred to hereinafter as objects (601) situated at the interface (602)).

24. A system according to claim 22, intended more particularly to determine whether a stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the said system also comprising;

means (709) for stereoscopic analysis of the object (601) that is stationary relative to the said interface (602).

25. A system according to one of claims 23 or 24, also including:

emitting means (716) for emitting a warning signal (711) according to the detection criteria applied in one or the other of the cases specified in claim 23 or in claim 24, especially in the presence of a stationary object (601) situated under the surface of a water/air interface (602).

26. A system according to any one of claims 21 to 25, intended more particularly to detect the appearance of new objects (601) in the said zone (603);

the said system also comprising;

iterating means (703) for iterating, at specified time intervals, the process, specified in claim 21, of deducing the presence of an object (601);

the said calculating means (702) (701) also comprising means for;

calculating the number of times that the object (601) is detected during a specified time period T2;

the said time period T2 being chosen to be longer than the duration of the phenomena associated with the objects (601) being detected;

discriminating, at a point of the said zone (603), between the objects (601) that are present a number of times larger than a specified threshold S2 (the said objects (601) being referred to hereinafter as usually present objects (601)) and the objects (601) that are present a number of times smaller than the said specified threshold S2 (the said objects (601) being referred to hereinafter as new objects (601)).

27. A system according to claims 22 and 26 taken in combination, intended more particularly to detect new and stationary objects (601);

the said system being such that the time period T1 is chosen to be shorter than the time period T2.

28. A system according to any one of claims 21 to 27, intended more particularly to yield a statistical estimate of the time of occupancy of the said zone Z (603) by at least one object (601) during a specified time period T;

the said system comprising the following stages;

partitioning means for performing a partition of the said zone (603) into elemental zones Δ

z,

iterating means (703) for iterating, in an elemental zone Δ

z (603) during elemental time intervals Δ

t, the process, specified in claim 21, of deducing the presence of an object (601);

the said calculating means (702) (701) also comprising means for calculating the number of times Δ

t/T that an object (601) is present in an elemental zone Δ

z (603) during the specified time period T.

29. A system according to any one of claims 21 to 28;

the said calculating means (702) (701) also comprising means for calculating the trajectory of the objects (601) whose presence has been detected.

30. A system according to claim 29, intended more particularly to detect the disappearance of an object (601) in a specified zone (603), especially the disappearance of a swimmer at the seashore;

the said system also comprising;

detecting means (708) for detecting when a trajectory stops at the boundary of the said zone (603), especially beyond the surveillance limits.

Branch 2

31. A system according to claim 29, intended more particularly to detect a stationary object (601) in the proximity of the said interface (602);

the said system being such that the said information-processing means (700) for discriminating the data corresponding to the video image of a real object (601) from those corresponding to the apparent video image generated by the said interface (602) comprise calculating means (702) (701) for;

validating a primitive as stationary if, during n successive time intervals Δ

t composing a specified time period T5, the said primitive is materialized (within the meaning of the present invention) at least a number of times larger than a specified threshold S5;

calculating and searching for the virtual images of stationary objects (601) (within the meaning of the present invention).

32. A system according to claim 31, intended more particularly to detect a new stationary object (601) in the proximity of the said interface (602);

the said system comprising;

iterating means (703) for iterating, at successive time intervals Δ

t composing a specified time period T6, the process, specified in claim 31, of detecting the presence of a stationary object (601),

the said calculating means (702) (701) comprising;

means for calculating the number of times that an object (601) is detected as being stationary during the said specified time period T6;

the said time period T6 being chosen to be longer than the duration of the phenomena associated with the object (601) being detected;

the said time period T6 being shorter than the said time period T5,

discriminating means for discriminating, at a point of the said zone (603), between a stationary object (601) that is present a number of times larger than a specified threshold S6 and an object (601) that is present a number of times smaller than the said specified threshold S6 (the said object (601) being referred to hereinafter as the new stationary object (601)).

33. A system according to claim 32, intended more particularly to determine whether a new stationary object (601) is situated:

on the other side of the interface (602),

on the same side of the interface (602),

at the interface (602)

relative to one of the said observation points;

the video images being recorded from the said observation point (607) at specified time intervals;

the said system also comprising;

iterating means (703) for iterating, at successive time intervals Δ

t composing a specified time period T7, the process, specified in claim 31, of detecting the presence of a stationary object (601);

the said calculating means (702) (701) also comprising;

means for calculating the number of times that an object (601) is detected as being stationary and new during the said specified time period T7;

the said time period T7 being chosen to be longer than the duration of the phenomena being observed;

the said time period T7 being shorter than the said time period T6,

Case in which the object (601) is situated on the other side of the interface (602);

detecting means (708a) for detecting, at a point of the said zone (603), between an object (601) that is present a number of times larger than a specified threshold S7 and an object (601) that is present a number of times smaller than the said specified threshold S7 (the said object (601) being referred to hereinafter as the new stationary object (601) situated on the other side of the interface (602);

Case in which the object (601) is situated on the same side of the interface (602);

detecting means (708b) for detecting, at a point of the said zone (603), between an object (601) that is present a number of times larger than a specified threshold S8 and an object (601) that is present a number of times smaller than the said specified threshold S8 (the said object (601) being referred to hereinafter as the new stationary object (601) situated on the same side of the interface (602));

the said threshold S8 being smaller than the threshold S7;

Case in which the object (601) is situated at the interface (602);

detecting means (708c) for detecting, at a point of the said zone (603), an object (601) that is present a number of times between the threshold S7 and the threshold S8

(the said objects (601) being referred to hereinafter as objects (601) situated at the interface (602)).

34. A system according to claim 33;

the said system also including emitting means (716) for emitting a warning signal (711) according to the detection criteria applied in one or the other of the cases specified in claim 33, especially in the presence of a stationary object (601) situated under the surface of a water/air interface (602).

36. A system according to any one of claims 18 to 34, intended more particularly for surveillance of a swimming pool.

38. The application of the system according to any one of claims 18 to 34 to surveillance of a swimming pool.