Detection of approaching objects by surveillance cameras

Abstract

To provide a method, a system and a computer program product for determining existence of an object approached a lens of a camera which monitors a scene.SOLUTION: A method activates 102 a first infrared illumination light source arranged to illuminate a scene from a first angle, and acquires 104 a first image by an image capture device. The method inactivates a first infrared illumination light source, activates 106 a second infrared illumination light source arranged to illuminate the scene from a second angle, and acquires 108 a second image by the image capture device. The method compares intensity information of the first image with intensity information of the second image to determine existence of an object approached a camera lens.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to cameras, and more particularly to detecting objects in close proximity to the lens of a camera. [Background technology]

[0002] Camera health management is becoming increasingly common, especially in large surveillance systems that may include hundreds or thousands of cameras, where manually monitoring the status of each camera is practically impossible.One common problem that arises with surveillance cameras in both indoor and outdoor environments is that spiders and insects are attracted to the infrared light that is often built into the cameras.

[0003] Insects (e.g. butterflies, moths, etc.) and spiders can obstruct the camera's view by landing on or in close proximity to the lens, reducing the camera's ability to detect events occurring in the scene it monitors. When an insect or spider moves across the lens or field of view, the camera's analysis software may interpret this as movement in the scene rather than in close proximity to or on the lens, triggering a false alarm.

[0004] Furthermore, spiders in particular (and some insects as well) may leave "appendages" in front of the lens. One example of such an appendage is a spider web. Small insects and spiders tend to leave appendages in front of the lens because they are attracted by the infrared light of the camera. When an appendage such as a spider web is illuminated by the camera's light, a large portion of the light is reflected by the appendage back to the camera sensor, especially if there are water droplets on the appendage, reducing the camera's surveillance capabilities to some extent until the appendage is removed. There may also be situations in which cameras are tampered with by humans for illicit purposes, for example by placing certain objects in close proximity to the lens to obscure it.

[0005] For at least these reasons, it would be desirable to have a way to automatically detect an object approaching the lens so that false alarms can be prevented and / or to obtain an indication that some action on the camera (e.g., removal of an obstruction) is required. Summary of the Invention

[0006] According to a first aspect, the present invention relates to a method, in a computer system, for determining the presence of an object in proximity to the lens of an image capture device monitoring a scene, the method comprising: activating a first infrared illumination source positioned to illuminate the scene from a first angle; acquiring a first image by an image capture device; deactivating the first infrared illumination source and activating a second infrared illumination source positioned to illuminate the scene from a second angle; capturing a second image by an image capture device; Comparing the intensity information of the first image with the intensity information of the second image to determine the presence of an object proximate to the lens.

[0007] This method provides a way to improve the technique for detecting objects close to the lens, often without requiring modifications to the camera's hardware setup, where conventional cameras typically have illuminators that can be controlled to illuminate the scene from different angles. Because it can be automatically determined whether an object is close to the lens, the number of false alarms can be reduced, and appropriate alarms can be generated if the camera requires any attention. This method can also reduce the need for manual intervention and monitoring of individual camera feeds, thus contributing to cost savings in maintaining the camera system.

[0008] According to one embodiment, the first and second infrared illumination sources are arranged to illuminate the object with essentially equal intensity and wavelength. Having equal intensity and wavelength for illumination from both sides provides as similar conditions as possible in terms of illumination, eliminating differences that may arise from illuminated objects having different reflectance properties for different wavelengths. This also facilitates comparison of images, making it easier to more clearly identify differences that arise purely from illuminating an object from two different angles.

[0009] According to one embodiment, the first infrared illumination source and the second infrared illumination source each comprise one or more infrared light emitting diodes. Light emitting diodes (LEDs) are standard elements in most cameras, and the use of existing components avoids the need for significant modifications to the camera hardware. The number of LEDs in each illumination source may also vary. In some cases, one LED in each source may be sufficient, while in other cases multiple LEDs in each illumination source may be required.

[0010] According to one embodiment, the method further includes deactivating the second infrared illumination source and activating a third infrared illumination source positioned to illuminate the scene from a third angle, acquiring a third image, and comparing the intensity information of the first image, the second image, and the third image to determine the presence of an object close to the lens. Since more than two infrared illumination sources can be used, more images can be acquired and pairwise comparisons between the three images can be made, allowing for a better determination of the presence of an object. This allows for a more reliable determination of the presence of an object close to the lens.

[0011] According to one embodiment, the method further comprises activating / deactivating the first and third infrared illumination sources together and activating / deactivating the second and fourth infrared illumination sources together, the first and third infrared illumination sources being disposed essentially perpendicularly from the second and fourth infrared illumination sources. The use of two groups of illumination sources disposed essentially perpendicularly with respect to each other not only provides superior illumination but also enhances intensity differences that may be caused by objects disposed close to the lens, thereby improving the accuracy of detection of such objects.

[0012] According to one embodiment, comparing the intensity information includes compensating for global intensity differences between the first and second images, determining whether any local intensity differences remain, and in response to a positive determination that there are local intensity differences, providing an indication of the presence of an object close to the lens. Intensity comparison is a computationally low cost comparison, and by first compensating for global intensity differences, local intensity differences will appear more clearly in the image comparison, thus making it easier to determine the presence of an object close to the lens.

[0013] According to one embodiment, the method includes comparing the local intensity difference pattern to a reference intensity difference pattern and providing an indication of the presence of an object approaching the lens when there is a match between the local intensity difference pattern and the reference intensity difference pattern. Having different reference intensity patterns may not only detect an object approaching the lens, but may also allow at least some identification of what the object is. For example, a butterfly may result in a different intensity pattern compared to a spider web, or compared to someone tampering with the camera, and may require a different type of action to be taken. Thus, different types of alerts may be generated based on what the most likely object is.

[0014] According to one embodiment, the method can include using a neural network to evaluate local intensity differences to determine the presence or absence of an object proximate to the lens. Similar to what has been described above, the neural network can be taught to automatically identify a particular object based on its intensity profile.

[0015] According to one embodiment, the method may include sending a notification to a camera operator in response to determining that there is an object proximate to the lens. As previously discussed, the notification may be generated automatically based on the result of the detection. There may also be various types of notifications, or different types of personnel may be notified based on what the object may be. For example, it may be more urgent to address a situation where a camera has been tampered with compared to a situation where a spider web has been detected.

[0016] According to one embodiment, the object may be a spider, an insect, a spider appendage, or an insect appendage, which are some examples of various insects and "appendages" that are common sources of problems in environments where surveillance cameras are installed.

[0017] According to one embodiment, acquiring a first image by an image capture device and acquiring a second image by an image capture device includes acquiring several short exposure images and combining them into the first image and the second image, respectively. This may be useful in situations where the scene monitored by the camera contains a lot of motion, such as when the camera is looking across choppy water, or when tree branches and leaves in the background are moving with the wind. By adding or averaging several such short exposure images, such motion may be evened out and objects approaching the lens may be more accurately identified.

[0018] According to one embodiment, capturing the first image by the image capture device and capturing the last image by the image capture device includes capturing several short exposure images and combining them into the first image and the last image, respectively, for which similar advantages as described in the previous paragraph can be obtained.

[0019] According to a second aspect, the present invention relates to a system for determining the presence of an object proximate to a lens of an image capture device monitoring a scene, the system comprising: a memory including instructions which, when executed by a processor, cause the processor to: activating a first infrared illumination source positioned to illuminate the scene from a first angle; acquiring a first image by an image capture device; deactivating the first infrared illumination source and activating a second infrared illumination source positioned to illuminate the scene from a second angle; capturing a second image by an image capture device; and comparing the intensity information of the first image with the intensity information of the second image to determine the presence of an object proximate to the lens.

[0020] The advantages of the system correspond to the advantages of the method and may be varied as well.

[0021] According to a fourth aspect, the present invention relates to a computer program for determining the presence of an object in proximity to a lens of an image capture device monitoring a scene, the computer program comprising: activating a first infrared illumination source positioned to illuminate the scene from a first angle; acquiring a first image by an image capture device; deactivating a first infrared illumination source and activating a second infrared illumination source positioned to illuminate the scene from a second angle; acquiring a second image by an image capture device; and comparing the intensity information of the first image to the intensity information of the second image to determine the presence of an object proximate to the lens.

[0022] The computer programs include advantages corresponding to those of the methods and may be varied in a similar manner.

[0023] The details of one or more embodiments of the invention are set forth in the accompanying drawings and the description below. Other features and advantages of the invention will become apparent from the description and drawings, and from the claims. [Brief description of the drawings]

[0024] [Figure 1] 1 is a flow diagram illustrating a method 100 for determining whether an object is present close to a lens, according to one embodiment. [Diagram 2] 2 is a flow diagram illustrating a method 200 for determining whether an object is present close to a lens, according to one embodiment. [Diagram 3] FIG. 3 is a schematic diagram illustrating a camera 300 having separate IR illumination sources, an image captured by the camera, and an image analysis component, according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Like reference symbols in the various drawings indicate like elements.

[0026] As explained above, one of the goals of various embodiments of the present invention is to be able to automatically detect objects approaching the lens so that false alarms can be prevented, and / or an indication that some action on the camera (e.g., removal of an obstacle) is required. The present invention stems from the general principle that objects approaching the camera lens will look different, i.e., will have different intensities in the image when illuminated from different angles. Thus, when two images are recorded by a camera and the images are captured using IR illumination from different angles, the objects in the images will look different (i.e., will have different intensities in the acquired image). Thus, by comparing the acquired images, and in particular looking for local intensity differences between the acquired images, it is possible to conclude whether an object has approached the lens. What is considered a "approaching" object may vary depending on the particular situation at hand, but as a general guideline, an object "approaching" the camera in this context refers to one that is within about 0.5 meters of the camera, and preferably within 0.2 meters of the camera lens. In response to the detection of an object, an appropriate alarm may be generated to address the problem. Various embodiments will now be described in more detail, by way of example, with reference to the figures.

[0027] FIG. 1 is a flow diagram showing a method 100 for determining whether an object is present in proximity to a lens, according to one embodiment. The method 100 may be automatically performed at various intervals as necessary to efficiently detect objects located in proximity to the lens. As seen in FIG. 1, the method 100 begins by activating a first infrared illumination source (step 102). This is shown diagrammatically in FIG. 3, which shows a surveillance camera 300 with a first infrared illumination source 302 activated. Typically, the infrared illumination source includes several IR LEDs, which are common in most cameras used to monitor a scene. However, the type of illuminator that may be used with the present invention is not limited to IR LEDs, but other types of illuminators, such as laser diodes, may also be used.

[0028] Next, a first image is captured in step 104. This image is shown diagrammatically in Figure 3 as Image #1, 304. The image is typically captured by the camera 300 using the same type of image capture that is used during normal operation, for example using a CMOS sensor in combination with rolling shutter technology.

[0029] Once the first image is captured, the first infrared illumination source 302 is turned off and the second infrared illumination source 306 is turned on (step 106). Typically, the first infrared illumination source 302 and the second infrared illumination source 306 are positioned on opposite sides of the lens 301 (e.g., top and bottom or left and right sides, etc.) so that the object may be illuminated from two opposing angles. However, it should be noted that this is not a requirement and there may be a smaller angular distance between the first infrared illumination source 302 and the second infrared illumination source 306. One or more IR LEDs may also be part of both the first group 302 and the second group 306. Furthermore, it should be noted that although the first infrared illumination source 302 and the second infrared illumination source 306 are shown in FIG. 3 as being integrated within the camera 300, they may also be separate units located outside (e.g., on either side) of the camera 300 itself. A second image 308 is acquired with the second infrared illumination source turned on in the same manner that the first image 304 was acquired (step 108).

[0030] Finally, image analysis 310 is performed to determine if there is an object approaching the lens (step 110). Note that this image analysis 310 does not concern the actual depth of the object itself, but only the determination of whether there is an object approaching the lens. This is an important advantage since depth determination typically requires significant data processing. The relatively small computing resources required for various embodiments of the invention allow the invention to be implemented in environments where large computing resources are not available, such as the camera itself. In addition, the low computing resource requirements allow the overall power consumption of the camera to be reduced. This is important not only to reduce heat, but also when LEDs are used at night, since the power supply of the camera is limited by the available power according to the Ethernet standard.

[0031] In one embodiment, the image analysis 310 works as follows: First, the global intensity difference between the two images is calculated and compensated for. Such a global intensity difference may be due to, for example, exposure differences or IR LED intensity differences. This global intensity difference is the same for all pixels in the images and can be compensated for by adding the global intensity difference to one of the images to make it uniform.

[0032] It is then determined whether there is any local intensity difference pattern between the first image 304 and the second image 308. In other words, it is determined whether the intensity is different in some areas between the images than in other areas. If such a local pattern exists, this is an indication of the presence of an approaching object. In some embodiments, this analysis alone may determine that an approaching object is present. In other embodiments, this analysis may serve as an indication that a more advanced analysis may be required, for example, the determined local pattern is compared to a reference intensity difference pattern to identify the type of object. Based on this image analysis, an alert may be generated to a user of the camera system or some maintenance crew. Alternatively, the alert may serve as a trigger to an automatic system, such as a wiper, vibration, noise, for example to remove cobwebs from the area close to the lens. Many such variations may be envisioned by one skilled in the art.

[0033] In many cameras, a portion of the camera housing protrudes a certain distance above and / or to the side of the lens (often similar to the way that a house's shade protrudes over a window) to serve as weather protection. Generally, this camera housing protrusion is not shown in the image captured by the lens. However, when the first and second infrared illumination sources are illuminated, light may bounce off the protrusion, which results in a weak but stable intensity difference between the two images recorded with the first and second illumination sources activated. This difference can be addressed by recording two calibration images in a completely dark room, activating each illumination source without an object close to the lens, and then storing these calibration images in the camera. When the camera is later used to register the first and second images, each of these two calibration images can first be subtracted from the respective image before performing the image processing described above. In this way, the intensity difference resulting from the configuration of the camera housing can be taken into account.

[0034] FIG. 2 is a flow chart illustrating a method 200 for determining whether an object is present close to a lens according to different embodiments. In FIG. 2, first, an initial image is captured in step 201. The initial image is captured with both IR illumination sources on when the scene is dark (e.g., at night) and with both IR illumination sources off when the scene is bright (e.g., during the day). Steps 202-208 are then performed in a manner corresponding to steps 102-108 described above with reference to FIG. 1. After capturing a second image in step 208, a final image is captured in step 209. This final image, like the initial image, is also captured with both IR illumination sources on or off depending on whether the scene is dark or bright.

[0035] The image analysis of step 210 is similar to the image analysis of step 110, with one important difference: the first image captured in step 201 is compared to the last image captured in step 209, in addition to the image analysis described in step 110. If these images, captured with both IR illumination sources on and off, differ from each other, this is an indication that there was likely motion in the scene during the capture of the first and second images. That is, any differences detected when comparing the first and second images are likely due to motion in the scene captured by the camera, rather than due to an object actually approaching the lens. Thus, 、 On both sides of the first and second image capture first With images of last Image of Import The comparison can serve as a good additional "verification" of the obtained results when it is indeed valid to compare the first and second images.

[0036] It should be noted that although the description focuses on two images and two IR illumination sources, the same concepts can be extended to any number of images and any number of IR illumination sources. The exact selection of how many images or IR illumination sources to use in a given situation is well within the skill of one of ordinary skill in the art.

[0037] Furthermore, rather than capturing a single first image, a single second image, etc., as previously described, in some implementations, multiple short exposure images are captured and then added together to form the first image and the second image, respectively. This is beneficial in that it allows intensity differences due to motion in the images to be taken into account. For example, the camera may be looking out over the ocean, or trees may be moving in the wind within the camera's field of view. The effects of these types of motion may be mitigated with this type of setup, in which case several short exposure images are employed rather than a single image.

[0038] As will be appreciated by those skilled in the art, aspects of the present invention may be embodied as a system, method, or computer program product. Thus, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be referred to generally herein as a "circuit," "module," or "system." Moreover, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied therein.

[0039] Any combination of one or more computer readable media may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples (non-exhaustive list) of computer readable storage media would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with a system, apparatus, or device that executes instructions.

[0040] A computer-readable signal medium may include a propagated data signal having computer-readable program code embodied therein, for example in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium is not a computer-readable storage medium, but may be any computer medium capable of communicating, propagating, or carrying a program for use by or in connection with a system, apparatus, or device that executes instructions.

[0041] Program code embodied in a computer readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wireline, fiber optic cable, RF, or the like, or any suitable combination of the above. Computer program code for carrying out operations related to aspects of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet Service Provider).

[0042] Aspects of the present invention will be described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. Each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, executed by a processor of the computer or other programmable data processing apparatus, produce means for performing the functions / acts specified in one or more blocks in the flowcharts and / or block diagrams.

[0043] These computer program instructions may also be stored on a computer-readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored on the computer-readable medium produce an article of manufacture including instructions that perform the functions / acts specified in one or more blocks in the flowcharts and / or block diagrams.

[0044] These computer program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, result in a process for performing the functions / acts specified in one or more blocks in the flow charts and / or block diagrams.

[0045] The flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flow charts or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions shown in the blocks may deviate from the order shown in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or may sometimes be executed in reverse order depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flow charts, and combinations of blocks in the block diagrams and / or flow charts, may be implemented by a dedicated hardware-based system that performs the specified functions or acts or executes a combination of dedicated hardware and computer instructions.

[0046] The description of various embodiments of the present invention has been presented for purposes of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will become apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. Accordingly, many other variations that fall within the scope of the claims may be envisioned by those skilled in the art.

[0047] The terminology used herein has been selected to best explain the principles of the embodiments, practical applications or technical improvements to technology found in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein. [Explanation of symbols]

[0048] 300 Camera 301 Lens 302 first infrared illumination source 304 1st image 306 Secondary infrared illumination source 308 Second Image 310 Image Analysis

Claims

1. 1. A method for determining the presence of an object in proximity to a lens (301) of an image capture device (300) monitoring a scene, comprising: activating a first infrared illumination source (302) positioned to illuminate the scene from a first angle; acquiring a first image (304) with the image capture device (300); deactivating the first infrared illumination source (302) and activating a second infrared illumination source (306) positioned to illuminate the scene from a second angle; acquiring a second image (306) with the image capture device (300); comparing intensity information of the first image (304) with intensity information of the second image (306) to determine the presence of an object approaching the lens (301); Including, Comparing the intensity information Compensating for overall intensity differences between the first image (304) and the second image (308); determining whether any local intensity differences remain; in response to a positive determination that there is a local intensity difference, providing an indication of the presence of an object proximate to the lens. The method includes:

2. The method of claim 1 , wherein the first infrared illumination source (302) and the second infrared illumination source (306) are positioned to illuminate the object with essentially equal intensity and wavelength.

3. The method of claim 1 or 2, wherein the first infrared illumination source (302) and the second infrared illumination source (306) each comprise one or more infrared emitting diodes.

4. deactivating the second infrared illumination source (306) and activating a third infrared illumination source positioned to illuminate the scene from a third angle; acquiring a third image; 4. The method of claim 1, further comprising comparing intensity information of the first image (304), the second image (308), and the third image to determine the presence of an object approaching the lens.

5. activating / deactivating the first infrared illumination source (302) and the third infrared illumination source together; activating / deactivating the second infrared illumination source (306) and the fourth infrared illumination source together; Further comprising:

4. The method of claim 1, wherein the first and third infrared illumination sources are disposed essentially perpendicularly from the second and fourth infrared illumination sources.

6. comparing the local intensity difference pattern with a reference intensity difference pattern; providing an indication of the presence of an object proximate to said lens (301) when there is a match between said local intensity difference pattern and said reference intensity difference pattern. The method of any one of claims 1 to 5, further comprising:

7. The method of any one of claims 1 to 6, further comprising using a neural network to evaluate the local intensity differences to determine the presence or absence of an object approaching the lens (301).

8. capturing an initial image prior to capturing the first image using both the first infrared illumination source (302) and the second infrared illumination source (306); capturing a second image using both the first infrared illumination source (302) and the second infrared illumination source (306) followed by capturing a final image; comparing intensity information of the first image with intensity information of the last image to determine whether there is motion in the scene; in response to determining that there is no motion in the scene, verifying the determination of the presence of an object proximate to the lens (301); The method of any one of claims 1 to 7, further comprising:

9. In response to determining that an object is approaching said lens (301), sending a notification to a camera operator. The method of any one of claims 1 to 8, further comprising:

10. 10. The method of any one of claims 1 to 9, wherein the object is one or more of a spider, an insect, a spider appendage, and an insect appendage.

11. 11. The method of claim 1, wherein acquiring the first image (304) by the image capture device and acquiring the second image (308) by the image capture device (300) comprises acquiring several short-term exposure images and combining the short-term exposure images into the first image (304) and the second image (308), respectively.

12. 12. The method of claim 7, wherein each of acquiring an initial image by the image capture device (300) and acquiring a final image by the image capture device (300) comprises acquiring several short-term exposure images and combining the short-term exposure images into the initial image and the final image, respectively.

13. 1. A system for determining the presence of an object in proximity to a lens (301) of an image capture device (300) monitoring a scene, comprising: Memory, An image capture device (300); a first infrared illumination source (302); a second infrared illumination source (306); Processor and Equipped with The memory includes instructions that, when executed by the processor, cause the processor to activating the first infrared illumination source (302) positioned to illuminate the scene from a first angle; acquiring a first image (304) with the image capture device (300); deactivating the first infrared illumination source (302) and activating the second infrared illumination source (306) positioned to illuminate the scene from a second angle; acquiring a second image (308) with the image capture device (300); comparing intensity information of the first image (304) with intensity information of the second image (308) to determine the presence of the object in proximity to the lens (301); Comparing the intensity information Compensating for overall intensity differences between the first image (304) and the second image (308); determining whether any local intensity differences remain; in response to a positive determination that there is a local intensity difference, providing an indication of the presence of an object proximate to the lens. A system for carrying out a method comprising the steps of:

14. 1. A non-transitory computer readable storage medium having program instructions for determining the presence of an object proximate to a lens (301) of an image capture device (300) monitoring a scene, the program instructions comprising: activating a first infrared illumination source (302) positioned to illuminate the scene from a first angle; acquiring a first image (304) with the image capture device (300); deactivating the first infrared illumination source (302) and activating a second infrared illumination source (306) positioned to illuminate the scene from a second angle; acquiring a second image (308); comparing intensity information of the first image (304) with intensity information of the second image (308) to determine the presence of the object in proximity to the lens (301); Comparing the intensity information Compensating for overall intensity differences between the first image (304) and the second image (308); determining whether any local intensity differences remain; in response to a positive determination that there is a local intensity difference, providing an indication of the presence of an object proximate to the lens.

23. A computer-readable storage medium executable by a processor to perform a method comprising:

Images