Systems and methods that employ object recognition

• US 9,497,393 B2
• Filed: 03/02/2012
• Issued: 11/15/2016
• Est. Priority Date: 03/02/2012
• Status: Active Grant

• Current Assignee: Express Imaging Systems, LLC
• Original Assignee: Express Imaging Systems, LLC
• Inventors: Reed, William G., DeGraff, Dale H.
• Primary Examiner(s): Anyikire, Chikaodili E
• Assistant Examiner(s): ABIMBOLA, KEHINDE
• Application Number:
  US13/411,321
• Publication Number:
  US 20130229518A1
• Time in Patent Office: 1,719 Days
• US Class Current: 1/1
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20
• CPC Class Codes: H05B 47/125 by using cameras
• CPC Class Codes: H05B 47/19 via wireless transmission
• CPC Class Codes: Y02B 20/40 Control techniques providing energy savings, e.g. smart controller or presence detection
• CPC Class Codes: Y02B 20/72 in street lighting

Abstract

An illumination system and methods to control a light source are provided. An illumination system includes a light source, a two-dimensional non-Passive Infrared (non-PIR) imager, and a controller. The light source may provide at least two levels of illumination. The non-PIR imager images an area and to produce image data representative of images across at least part of a visible portion of an electromagnetic spectrum. The controller is communicatively coupled to receive the image data from the non-PIR imager and process the received image data to detect at least one object in the area of a defined type of object. The controller is also coupled to control operation of the light source based on, at least in part, detection of the ambient characteristic of the environment. Alternatively, one or more components of a system may be used to monitor traffic, with or without active illumination.

Claims

1. An illumination system, comprising:

a light source which in use provides at least two levels of illumination;

a two-dimensional non-Passive Infrared (non-PIR) imager which in use images an area and to produce image data representative of images across at least part of a visible portion of an electromagnetic spectrum; and

a controller communicatively coupled to the non-PIR imager, the controller receives the image data from the non-PIR imager, wherein the controller performs one or more machine-vision object recognition techniques with respect to the received image data to detect one or more visual features within the received image data and determines a match between the one or more visual features and one or more defined features representative of a defined type of object to detect a presence of the defined type of object in the area, and the controller coupled to control operation of the light source based on at least in part detection of objects of the defined type of object in the area, wherein the controller adjusts the level of illumination provided to the area from the light source to a first level when a level of ambient light is greater than a threshold level, adjusts the level of illumination provided to the area from the light source to a second level that is greater than the first level when the level of ambient light is less than the threshold level, and adjusts the level of illumination provided to the area from the light source to a third level that is greater than the second level in response to detection of at least one object of the defined type object in the area.

2. The illumination system of claim 1 wherein the controller adjusts the level of illumination provided by the light source based on at least in part the detection of an object that corresponds to a motor vehicle in the area.

3. The illumination system of claim 1 wherein the controller causes the light source to provide illumination one of the first level or the second level when the image data indicates the defined type of object is not in the area and to provide illumination at the third level when the image data indicates the defined type of object is in the area.

4. The illumination system of claim 1 wherein the non-PIR imager captures a first image of the area at a first time and captures a second image of the area at a second time, after the first time, each of the first and the second images having a respective plurality of pixels, and wherein the controller compares the image data representative of the first and the second images to detect an appearance or a change between the first and the second images.

5. The illumination system of claim 4 wherein the controller adjusts an illumination level of the light source from one of the first level or the second level to the third level when the image data representative of the first image and the image data representative of the second image differ by more than a threshold amount.

6. The illumination system of claim 4 wherein the controller adjusts an illumination level of the light source from one of the first level or the second level to the third level when the image data representative of the first image and the image data representative of the second image differ by more than a threshold amount and when a quantity of the pixels that have changed and that are within a threshold distance from one another is greater than a threshold quantity.

7. The illumination system of claim 1 wherein the controller deducts the level of illumination provided by the light source from a detected level of ambient brightness and adjusts the illumination level provided by the light source in response to the deduction.

8. The illumination system of claim 1 wherein the controller adjusts the level of illumination from the light source a defined delay period after detecting the presence of the defined type of object in the area.

9. The illumination system of claim 1 wherein the defined type of object is at least one of a vehicle or a human.

10. The illumination system of claim 1 wherein the non-PIR imager comprises at least one of a solid-state camera, a video camera, or a digital still camera and the light source, non-PIR imager and controller are part of a light fixture that is mountable to an outdoor structure.

11. The illumination system of claim 1 wherein an area illuminated by the light source is at least approximately coincident with the area imaged by the non-PIR imager.

26. The illumination system of claim 1 wherein the controller causes a count of a total number of the objects of the defined type of object that pass through the area over a period of time based on at least in part on the detection of the presence of the defined type of object in the area.

27. The illumination system of claim 1 wherein the defined type of object comprises a license plate of a vehicle.

28. The illumination system of claim 1 wherein the one or more visual features comprise one or more of headlights and taillights of a vehicle.

29. The illumination system of claim 1 wherein the one or more visual features comprise one or more of a relative position and a spacing between a pair of headlights or taillights of a vehicle depicted in the received imagery and the one or more defined features comprise one or more of an expected relative position and an expected spacing.

30. The illumination system of claim 1 wherein the one or more visual features comprise a reflectance pattern exhibited by one or more of a windshield, a rear window, and a side window of a vehicle depicted in the received imagery.

12. A method of controlling a light source, the method comprising:

imaging an area with a non-Passive Infrared (non-PIR) imager to produce image data representative of at least part of a visible portion of an electromagnetic spectrum;

processing receiving by a processor the image data from the non-PIR imager;

performing by the processor one or more machine-vision object recognition techniques with respect to the image data from the non-PIR imager to detect one or more visual features within the received image data, the one or more visual features comprising one or more of headlights and taillights of a vehicle;

determining by the processor a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area;

analyzing by the processor the received image data to determine whether the image data includes motion of the detected at least one object of the defined type of object;

in response to the detection of the at least one object of the defined type of object in the area but not motion of the detected at least one object, adjusting a level of illumination provided to the area from a light source to a first non-zero illumination level; and

in response to the detection of the at least one object of the defined type of object in the area and motion of the detected at least one object, adjusting the level of illumination provided to the area from the light source to a second non-zero illumination level that is greater than the first non-zero illumination level.

31. The method of claim 12, further comprising:

in response to the detection of the at least one object of the defined type of object in the area, adjusting a count of a number of objects that have passed through the area over a period of time.

32. The method of claim 12 wherein performing by the processor one or more machine-vision object recognition techniques with respect to the image data from the non-PIR imager to detect one or more visual features within the received image data comprises performing by the processor the one or more machine-vision object recognition techniques with respect to the image data from the non-PIR imager to detect a reflectance pattern exhibited by one or more of a windshield, a rear window, and a side window of a vehicle depicted in the received imagery.

13. A traffic monitor and illumination system, comprising:

a light source which in use provides at least two levels of illumination;

a two-dimensional non-Passive Infrared (non-PIR) imager which in use images an area and to produce image data representative of successive images of the area over time; and

a controller communicatively coupled to the non-PIR imager, the controller receives the image data from the non-PIR imager, wherein the controller performs one or more machine-vision object recognition techniques with respect to the received image data to detect one or more visual features within the received image data, the one or more visual features comprising one or more of headlights and taillights of a vehicle, and the controller determines a match between the one or more visual features and one or more defined features representative of a defined type of object to detect a presence of the defined type of object in the area, and causes a count of a total number of the objects of the defined type of object that pass through the area over a period of time based on at least in part on the detection of the presence of the defined type of object in the area, wherein the controller is coupled to control operation of the light source based on at least in part detection of objects of the defined type of object in the area.

14. The traffic monitor system of claim 13 wherein the controller distinguishes motor vehicles from other types of objects.

15. The traffic monitor system of claim 14 wherein the controller distinguishes types of motor vehicles from other types of motor vehicles.

16. The traffic monitor system of claim 14 wherein the controller distinguishes types of makes and models of motor vehicles from other types of makes and models of motor vehicles.

17. The traffic monitor system of claim 14 wherein the controller distinguishes types of unique identifiers carried by motor vehicles from other types of unique identifiers carried by motor vehicles.

18. The traffic monitor system of claim 13 wherein the controller causes the light source to provide illumination at a first illumination level when the image data indicates the defined type of object is not in the area and to provide illumination at a second illumination level when the image data indicates the defined type of object is in the area, the second illumination level greater than the first illumination level.

33. The traffic monitor and illumination system of claim 13 wherein the light source provides at least three levels of illumination that include at least a first non-zero illumination level and a second non-zero illumination level that is greater than the first non-zero illumination level and the controller analyzes the received image data to determine whether the image data includes motion of the detected defined type of object in the area, adjusts a level of illumination provided to the area from the light source to the first non-zero illumination level in response to the detection of the presence of the defined type of object in the area but not motion of the detected defined type of object, and adjusts the level of illumination provided to the area from the light source to the second non-zero illumination level in response to the detection of the presence of the defined type of object in the area and motion of the detected defined type of object.

34. The traffic monitor and illumination system of claim 13 wherein the controller, in response to the detection of the presence of the defined type of object in the area, stores the received imagery and associates a time of detection with the stored imagery.

19. A method of controlling a traffic monitoring and illumination system, the method comprising:

imaging an area with a non-Passive Infrared (non-PIR) imager to produce image data representative of at least part of a visible portion of an electromagnetic spectrum;

performing by a processor one or more machine-vision object recognition techniques with respect to the image data from the non-PIR imager to detect one or more visual features within the image data from the non-PIR imager, the one or more visual features comprising one or more of headlights and taillights of a vehicle;

determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area; and

in response to the detection of the at least one object of the defined type of object in the area, adjusting a count of traffic in the area and adjusting a level of illumination provided to the area from a light source.

20. The method of claim 19 wherein determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area includes distinguishing motor vehicles from other types of objects.

21. The method of claim 20 wherein determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area includes distinguishing types of motor vehicles from other types of motor vehicles.

22. The method of claim 20 wherein determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area includes distinguishing types of makes and models of motor vehicles from other types of makes and models of motor vehicles.

23. The method of claim 20 wherein determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area includes distinguishing types of unique identifiers carried by motor vehicles from other types of unique identifiers carried by motor vehicles.

24. The method of claim 19 wherein adjusting a level of illumination provided to the area from a light source comprises operating the light source to provide illumination at a first illumination level when the defined type of object is not detected in the area and to provide illumination at a second illumination level when the defined type of object is detected in the area, the second illumination level greater than the first illumination level.

25. The method of claim 19, further comprising:

wherein processing by a processor the image data from the non-PIR imager to detect at least one object of a defined type of object in the area includes determining a speed of the at least one object.

35. The method of claim 19 wherein adjusting a level of illumination provided to the area from a light source in response to the detection of the at least one object of the defined type of object in the area comprises:

analyzing by the processor the received image data to determine whether the image data includes motion of the detected at least one object of the defined type;

in response to the detection of the at least one object of the defined type of object in the area but not motion of the detected at least one object, adjusting the level of illumination provided to the area from the light source to a first non-zero illumination level; and

in response to the detection of the at least one object of the defined type of object in the area and motion of the detected at least one object, adjusting the level of illumination provided to the area from the light source to a second non-zero illumination level.

36. The method of claim 19, further comprising:

periodically transmitting the count to a remotely located computing system.

37. A method of controlling a traffic monitoring and illumination system, the method comprising:

imaging an area with a non-Passive Infrared (non-PIR) imager to produce image data representative of at least part of a visible portion of an electromagnetic spectrum;

performing by a processor one or more machine-vision object recognition techniques with respect to the image data from the non-PIR imager to detect one or more visual features within the image data from the non-PIR imager;

determining a match between the one or more visual features and one or more defined features representative of a defined type of object to detect at least one object of the defined type of object in the area;

determining a level of ambient light;

adjusting the level of illumination provided to the area from a light source to a first level when the level of ambient light is greater than a threshold level;

adjusting the level of illumination provided to the area from the light source to a second level that is greater than the first level when the level of ambient light is less than the threshold level; and

in response to the detection of the at least one object of the defined type of object in the area, adjusting a count of traffic in the area and adjusting a level of illumination provided to the area from the light source to a third level that is greater than the second level in response to detection of the at least one object of the defined type object in the area.

38. An illumination system, comprising:

a light source which in use provides at least two levels of illumination;

a two-dimensional non-Passive Infrared (non-PIR) imager which in use images an area and to produce image data representative of images across at least part of a visible portion of an electromagnetic spectrum; and

a controller communicatively coupled to the non-PIR imager, the controller receives the image data from the non-PIR imager, wherein the controller performs one or more machine-vision object recognition techniques with respect to the received image data to detect one or more visual features within the received image data and determines a match between the one or more visual features and one or more defined features representative of a defined type of object to detect a presence of the defined type of object in the area, the one or more visual features comprise one or more of headlights and taillights of a vehicle, and the controller coupled to control operation of the light source based on at least in part detection of objects of the defined type of object in the area.