Camera and method for facilitating installation of the camera

Abstract

To provide a camera to secure the privacy of an object and a method therein for facilitating installation of the camera.SOLUTION: A method includes: capturing a video stream of a scene 102 when a camera 108 is installed with a first field of view, the scene including an object; estimating a size in the video stream of at least one part of the object; as long as the size is above a first threshold and below a second threshold, providing a first, edge-filtered, version of the video stream; and, in response to the size being above the second threshold indicating that privacy is at risk of being revealed, entering an enhanced secure privacy mode that includes generating an alert to prompt an installer to re-install the camera with a second field of view different from the first field of view and disabling provision of the first, edge-filtered, version of the video stream.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a camera and an internal method for facilitating installation of the camera. [Background technology]

[0002] When a camera, such as a surveillance camera, is installed to capture an image of a scene, national privacy regulations may require that the privacy of one or more objects present in the scene be guaranteed. Privacy is typically achieved by distorting the captured image so that object recognition or object identification is prevented. Thus, distorting the captured image prevents facial recognition, identification of vehicle registration numbers, and the like. If privacy cannot be guaranteed, the camera may not be permitted to be installed.

[0003] Methods for distorting captured images to prevent object recognition and object identification are known. For example, US10755388 B2 describes a method for protecting the privacy of individuals in captured image data by controlling privacy masking of the image, in which the degree of blur applied to privacy areas of the image depends on a threshold distance from the image capture device and the spatial resolution of the scene content at this distance in the image. However, US10755388 B2 is silent on a method for facilitating the placement of cameras to ensure privacy.

[0004] US2014 / 0362215 A1 relates to camera placement correction. However, in this disclosure, the purpose of camera placement correction is to optimize face recognition in captured images. The average size of faces is measured in various sub-regions and used as one parameter to trigger changes in camera position, such as moving the camera away from the scene or zooming in.

[0005] Therefore, there is room for improvement to provide facilitated installation of cameras that meet national privacy regulations. Summary of the Invention

[0006] Therefore, in view of the above, it is an object of the present invention to mitigate the drawbacks associated with the prior art and to provide a technique for facilitating the installation of cameras, in particular cameras that are capable of maintaining privacy when capturing video streams.

[0007] According to a first aspect of the present invention, the above object is achieved by a camera-executed method for facilitating camera installation. The method includes capturing a video stream of a scene when the camera is installed with a first field of view, the scene including one or more objects. The method further includes estimating a size in the video stream of at least one portion of the one or more objects, and providing a first edge-filtered version of the video stream to protect the privacy of one or more objects depicted in the video stream so long as the estimated size in the video stream of at least one portion of the one or more objects is above a first threshold and below a second threshold. The method further includes entering an enhanced, secure privacy mode of operation in response to the estimated size in the video stream of at least one portion of the one or more objects being above a second threshold indicating a risk of the privacy of the at least one object being revealed, the enhanced, secure privacy mode of operation including generating an alert prompting the installer to reinstall the camera with a second field of view different from the first field of view and disabling the provision of the first edge-filtered version of the video stream.

[0008] By providing a first edge-filtered version of the video stream, so long as the estimated size in the video stream of at least one portion of the one or more objects is above a first threshold and below a second threshold, the privacy of the one or more objects depicted in the video stream is preserved thanks to the anonymization of the one or more objects provided by the first edge-filtered version of the video stream.

[0009] Furthermore, the privacy of one or more subjects is protected by disabling providing the first edge-filtered version of the video stream if an estimated size in the video stream of at least one portion of the one or more subjects is above a second threshold indicating that there is a risk that the privacy of the at least one subject may be revealed.

[0010] By generating an alert prompting the installer to reinstall the camera when the estimated size in the video stream of at least one portion of the one or more objects is above a second threshold, the installer is made aware that in the future, i.e., to protect privacy in upcoming captures of the video stream, the camera needs to be reinstalled with a second field of view different from the first field of view. Therefore, the second field of view should be selected, whereby the second field of view will provide privacy for one or more objects captured in the video stream.

[0011] The term installation as used in this disclosure refers to the mounting of a camera in a scene, e.g., a physical location, and / or the configuration of the camera to capture a video stream of the scene at a particular field of view. Thus, installation may refer to the geographic location where the camera is mounted and / or camera settings, such as particular pan, tilt, and / or zoom settings, used to capture the video stream.

[0012] As used herein, the term field of view refers to the portion of a scene that is visible through a camera at a particular location and orientation in space of the camera and at a particular zoom setting of the camera. The particular location is given by the installation location, and the orientation is given by the pan and / or tilt setting of the camera. It should therefore be understood that the field of view may depend on one or more different camera parameters. For example, the field of view may depend on the installation location of the camera, such as the height above ground, the zoom setting of the camera, the pan setting of the camera, and / or the tilt setting of the camera.

[0013] The estimated size of at least one portion of one or more objects in a video stream can be determined as the number of pixels that the at least one portion comprises along at least one direction in the video stream. For example, the estimated size of the at least one portion can be given as the number of pixels in the vertical (height) direction and / or horizontal (width) direction of an image frame of the video stream. A pixel, sometimes called a picture element, is the smallest single element in an image frame. Depending on the spatial resolution of the image frame, the image frame can include 1920 x 1080 (width x height) pixels, 2560 x 1440 pixels, 2560 x 1920 pixels, or 3840 x 2160 pixels, to name just a few examples.

[0014] In cases where a first edge-filtered version of the video stream should be provided for all estimated sizes below the second threshold, the first threshold may be zero pixels. However, if the estimated size in the video stream of at least one portion of one or more objects is sufficiently small, the captured video stream can be provided as is without risking revealing the privacy of the one or more objects. What should be considered a sufficiently small estimated size depends on the situation at hand, but the first threshold should be set to provide an upper threshold for when the video stream can be provided as is without revealing the privacy of one or more objects depicted in the video stream. In such a scenario, if the estimated size in the video stream of at least one portion of one or more objects is above the first threshold but below the second threshold, the first edge-filtered version of the video stream is provided.

[0015] The second threshold should be set to provide an upper threshold for when the first edge-filtered version of the captured video stream should be provided, above which there is a risk that the privacy of one or more subjects would be revealed if the first edge-filtered version of the video stream were provided, and therefore providing the first edge-filtered version of the video stream is disabled.

[0016] The first and second thresholds can be determined based on camera parameters and installation location. For example, the thresholds can be determined based on the camera's optics, such as the type of lens, and the camera's resolution and field of view. Additionally or alternatively, the thresholds can be determined based on an edge filter used to provide an edge-filtered version of the captured video stream and the size of the edge filter's kernel. The kernel is a small matrix used in edge detection when performing a convolution between the kernel and the image frame. Furthermore, the first and second thresholds determined for a camera installation in one country may differ from the first and second thresholds determined for a camera installation in another country due to differences in national privacy regulations. The first and second thresholds can be determined by performing tests or based on the first and second thresholds used in previous camera installations. The first and second thresholds can also be determined using machine learning techniques, such as a neural network configured to detect and / or recognize one or more objects in the video stream.

[0017] It should be understood that a video stream includes at least one image frame of a scene, and therefore a video stream can include one image frame or multiple image frames, for example multiple temporally subsequent image frames.

[0018] A scene can be any three-dimensional physical space with a size and shape defined by the field of view of the camera recording the scene.

[0019] By the term object as used herein, it is meant any kind of object that is capable of revealing privacy information about itself, about a person possessing the object, or about a person associated with the object. Thus, an object can be a person or a part thereof (such as a face or body part), a group of people, a vehicle or a part thereof (such as a vehicle license plate), to name just a few examples.

[0020] An edge-filtered version of a video stream is a version of the video stream in which edge points are emphasized and non-edge points are suppressed. Edge points correspond to points in image frames of the video stream where image brightness changes abruptly, or more formally, where there is a discontinuity. Correspondingly, non-edge points correspond to pixels in image frames where image brightness does not change abruptly, or more formally, where there is no discontinuity. In the edge-filtered version of the video stream, edge points are emphasized and are typically shown as a set of connected curves indicating boundaries of objects, boundaries of surface markings, and / or sets of curves corresponding to discontinuities in surface orientation. Because non-edge points are suppressed in the edge-filtered version of the video stream, points within the boundaries emphasized by the edge points are suppressed. For example, if facial contours are emphasized in the edge-filtered version of the video stream, surface texture within the facial contours will be suppressed, resulting in a degree of anonymization of the face. The degree of anonymization depends on the degree of enhancement and the degree of suppression in the edge-filtered version of the video stream. However, it should be understood that the degree of anonymization also depends on the spatial resolution of the video stream.

[0021] In some variations of this method, the enhanced secure privacy mode of operation includes providing a second version of the video stream that further protects the privacy of one or more subjects.

[0022] By providing a second version of the video stream in which the privacy of one or more subjects is further protected, the privacy of the one or more subjects can be ensured if that privacy could not be ensured in the first edge-filtered version of the video stream, and so the first edge-filtered version of the video stream is disabled, whereby the second version of the video stream can be provided to a user for monitoring or to a storage device for storage without revealing any privacy-sensitive information.

[0023] In some variations of this method, providing the second version of the video stream includes generating the second version of the video stream by applying a privacy mask to at least a portion of the video stream to preserve the privacy of one or more subjects depicted in the video stream.

[0024] This is a first alternative to providing a second version of the video stream to ensure the privacy of one or more subjects.

[0025] The term privacy mask as used in this disclosure should be understood as a privacy masking function used to protect an individual's privacy by hiding portions of an image frame from view with a masked area. Privacy masks can be static or dynamic. Static privacy masks typically remain in place until an operator decides to move or remove them. Dynamic privacy masks can change over time, and an operator can also define when a privacy mask should be applied. For example, an operator can define a dynamic privacy mask so that if a face is detected within the masked area, the face will be masked out, but otherwise, no mask will be applied to that area.

[0026] Privacy masks are often applied to images as overlays. Privacy masks can have polygonal shapes, although other shapes are possible, which more closely follow the shape of the area they occlude. Some privacy masks take the form of opaque areas (e.g., solidly black or blue areas), while others take the form of blurs, where image data is "painted" across the privacy mask area or pixilation. Pixilation is a process in which a single pixel value (often the average value of several or all pixels in a coding unit) replaces all pixels in a coding unit. Pixilation can be achieved by downscaling the image frame, for example, by a factor between 8 and 64, and then upscaling the image frame using a simple scaling algorithm such as a nearest neighbor algorithm. However, blurring for privacy masking is generally considered preferable to pixilation because blurring allows for smoother edges, which results in a more aesthetically pleasing image. However, blurring is more difficult to achieve and requires more computational resources to implement than is currently economically feasible in hardware blocks.

[0027] In a video stream, a privacy mask is applied to each image frame of the video stream to conceal the privacy of one or more objects depicted in the video stream. For example, the privacy mask can be applied to a human face or body parts, thereby concealing those parts from being seen and identified. The privacy mask can be applied to at least one portion of the video stream by identifying an area that covers one or more objects depicted in the video stream and presenting the area using a solid color, blurring, or pixilation, as described above. The area can be identified, for example, as the outline of one or more objects. However, the area can have another shape (e.g., circular, rectangular, oval) suitable for covering at least one portion of the video stream.

[0028] In some variations of this method, providing the first edge-filtered version of the video stream includes generating the first edge-filtered version of the video stream by applying an edge filter to the video stream to emphasize edge points in the video stream and suppressing non-edge points in the video stream, wherein pixel values ​​of the video stream are represented using a first number of quantization levels.

[0029] As described above, by generating a first edge-filtered version of the video stream, the privacy of one or more subjects depicted in the video stream is preserved due to the anonymization of the one or more subjects provided by the first edge-filtered version of the video stream.

[0030] An edge filter is a filter that emphasizes edge points and suppresses non-edge points. Therefore, applying an edge filter to a video stream will enhance edge points while suppressing non-edge points. For example, an edge filter may also be called an edge detection filter and can be a Sobel filter, a Canny filter, a Difference of Gaussian (DoG) filter, a Laplacian filter, a Prewitt filter, or a Scharr filter, to name just a few. To suit a use case, the output of the edge filter, i.e., the edge-filtered version of the video stream, can be modified using one or more operations, such as an absolute value operation to not distinguish between positive and negative gradients, a gain operator to adjust intensity, an offset operator to make edge points black and non-edge points white, and / or a noise reduction operator to remove unwanted sparse black edge pixels that are not part of an actual edge or other structure in the image.

[0031] As described above, pixels in a video stream are represented using a first number of quantization levels. For example, pixels can be represented using 8 bits, which correspond to 256 quantization levels. Therefore, each pixel can take on a value between 0 and 255 to represent one of 256 possible colors. After applying an edge filter to a video stream, the resulting edge-filtered version of the video stream typically consists of pixels with values ​​on a grayscale; that is, the pixels only represent the amount of light, i.e., each pixel represents only intensity information. In the case of an 8-bit display, each pixel in the edge-filtered version of the video stream could represent an intensity level between 0 and 255 using a grayscale. Therefore, if 0 is represented by white and 255 is represented by black, there are 254 shades of gray in between.

[0032] In some variations of this method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the spatial resolution of the video stream to reduce the size in the video stream of at least one portion of the one or more objects below a second threshold before applying the edge filter to the video stream.

[0033] This is a second alternative to providing a second version of the video stream to ensure the privacy of one or more subjects. For some use cases, this may be an effective way to ensure the privacy of one or more subjects.

[0034] The term spatial resolution, as used herein, refers to the number of pixels utilized in constructing a video stream, for example, in constructing one or more image frames of the video stream. Reducing the spatial resolution of a video stream reduces the number of pixels that make up one or more image frames of the video stream. This may be referred to as downscaling or downsampling. Correspondingly, increasing the spatial resolution of a video stream, i.e., upscaling / upsampling the video stream, increases the number of pixels that make up one or more image frames of the video stream. It should be understood that the size of each pixel remains the same, resulting in a reduced image size when the spatial resolution is reduced and an increased image size when the spatial resolution is increased. As a result, video streams, for example, the original captured video stream, the first version of the video stream, and the second version of the video stream, when provided to a user, will all have the same pixel size, regardless of the level of privacy. However, it should be understood that after downscaling a video stream, upscaling of the video stream can be performed to keep the video stream with the same number of pixels, but with less sensitive information because image detail is lost during downscaling.

[0035] By reducing the spatial resolution of the video stream such that the size in the video stream of at least one portion of the one or more objects is below a second threshold, privacy of the one or more objects is ensured in the second edge-filtered version of the video stream.

[0036] In some variations of this method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the number of quantization levels used to represent pixel values ​​of the video stream from a first number of quantization levels to a second number of quantization levels before applying the first edge filter to the video stream.

[0037] This is a third alternative method of providing a second version of the video stream to ensure privacy of one or more subjects. It should be understood that pixel values ​​in the second edge-filtered version of the video stream will be represented using a second number of quantization levels.

[0038] By reducing the number of quantization levels in the video stream from the first number of quantization levels to a second, lower number of quantization levels, granular noise in the second, edge-filtered version of the video stream is increased due to the greater number of intensities that would be represented by each quantization level in the second number of quantization levels compared to the number of intensities that would be represented by each quantization level in the first number of quantization levels. The greater granular noise preserves the privacy of one or more subjects depicted in the second, edge-filtered version of the video stream.

[0039] For example, if the first number of quantization levels were 256 as described above using an 8-bit representation, the second number of quantization levels could be 4 (using a 2-bit representation). In such a case, the 256 quantization levels of the first number of quantization levels, each representing one intensity, would be grouped into four groups of 64 quantization levels. The first groups could be combined into a first quantization level (e.g., 0) of the second number of quantization levels. This first quantization level (e.g., 0) of the second number of quantization levels would therefore represent each of the 64 different intensities represented by quantization levels 0-63 of the first number of quantization levels. Therefore, in the second edge-filtered version of the video stream, it would not be possible to see any differences between the 64 different intensities represented by quantization levels 0-63 of the first number of quantization levels in the first edge-filtered version of the video stream. Correspondingly, the second group can be combined into a second quantization level (e.g., 1) of a second number of quantization levels, which represents each of the 64 different intensities represented by quantization levels 64-127 of the first number of quantization levels. Therefore, in the second edge-filtered version of the video stream, it would not be possible to see any differences between the 64 different intensities represented by quantization levels 64-127 of the first number of quantization levels in the first edge-filtered version of the video stream. The same applies to the third and fourth groups.

[0040] In some variations of this method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the spatial resolution of the first edge-filtered version of the video stream to obtain a second edge-filtered version of the video stream in which a size of at least one portion of the one or more objects is below a second threshold.

[0041] This is a fourth alternative method of providing a second version of the video stream to ensure the privacy of one or more subjects.

[0042] The privacy of the one or more objects is preserved by reducing the spatial resolution of the first edge-filtered version of the video stream to obtain a second edge-filtered version of the video stream in which the size of at least one portion of the one or more objects is below a second threshold.

[0043] In some variations of this method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by representing edge points in the first edge-filtered version of the video stream that have edge strengths below an edge strength threshold as non-edge points in the second edge-filtered version of the video stream.

[0044] This is a fifth alternative method for providing a second version of the video stream to ensure the privacy of one or more objects. By representing edge points in the first edge-filtered version of the video stream that have edge strengths below an edge strength threshold as non-edge points in the second edge-filtered version of the video stream, the contours of the one or more objects are further emphasized and the surface texture within the contours of the one or more objects is further suppressed. This results in a higher degree of anonymization of the one or more objects, thereby preserving the privacy of the one or more objects. The expression "edge strength" refers to the degree of the edge and how abruptly the image brightness changes at the edge.

[0045] In some variations of this method, providing the first edge-filtered version of the video stream includes transmitting the first edge-filtered version of the video stream to the receiver, and disabling providing the first edge-filtered version of the video stream includes disabling transmission of the first edge-filtered version of the video stream to the receiver.

[0046] The receiver can be any device operably connected to the camera either directly or indirectly via a network, via wires or wirelessly. For example, the receiver can be a storage, a user terminal, a server, or a cloud device.

[0047] In some variations of this method, disabling the provision of the first edge-filtered version of the video stream includes disabling the camera from capturing the video stream, meaning that the capture of the video stream is terminated, such that there is no captured video stream that, if provided, may pose a risk of revealing the privacy of one or more subjects.

[0048] In some variations of this method, disabling providing the first edge-filtered version of the video stream includes disabling an image sensor of the camera from communicating image information used to create the captured video stream.

[0049] By disabling the image sensor from transmitting image frames used to create the captured video stream, there is no image information to process and thus no captured video stream that could reveal privacy if provided.

[0050] In some variations of this method, the method further includes providing the captured video stream if the estimated size in the video stream of at least one portion of the one or more objects is below a first threshold.

[0051] Therefore, it is concluded that if the size of at least one portion of one or more objects in the video stream is below the first threshold, the captured video stream will not reveal privacy if provided as is, and therefore, if the size of at least one portion of one or more objects in the video stream is below the first threshold, the captured video stream is provided.

[0052] According to a second aspect of the present invention, the above object is achieved by a camera for facilitating camera installation, the camera including: an image capture module configured to capture a video stream of a scene when the camera is installed at a first field of view, the scene including one or more objects; a size estimation component configured to estimate a size in the video stream of at least one portion of the one or more objects; and a providing component configured to provide a first edge-filtered version of the video stream to preserve the privacy of one or more objects depicted in the video stream so long as the estimated size in the video stream of the at least one portion of the one or more objects is above a first threshold and below a second threshold. In response to the estimated size in the video stream of at least one portion of one or more subjects exceeding a second threshold indicating there is a risk of the privacy of the at least one subject being revealed, the camera is configured to enter an enhanced secure privacy mode of operation, the alert generation component is configured to generate an alert prompting an installer to reinstall the camera with a second field of view different from the first field of view, and the providing component is configured to disable providing of the first edge-filtered version of the video stream.

[0053] According to a third aspect of the present invention, the above object is achieved by a non-transitory computer readable medium having computer code instructions stored thereon, the computer code instructions being adapted to perform the method of the first aspect when executed by a device having processing capability.

[0054] The second and third aspects may generally have the same features and advantages as the first aspect. It is further noted that the present invention relates to all possible combinations of features disclosed herein unless expressly stated otherwise.

[0055] The above, as well as further objects, features, and advantages of the present invention will be better understood through the following illustrative and non-limiting detailed description of embodiments thereof, taken in conjunction with the accompanying drawings, in which like reference numerals are used for similar elements, in which: [Brief explanation of the drawings]

[0056] [Figure 1] FIG. 1 illustrates a schematic diagram of an exemplary environment in which various embodiments of the present invention may be implemented. [Figure 2] FIG. 1 is a diagram illustrating a camera according to an embodiment. [Figure 3] 1 is a flowchart of a method for facilitating camera installation according to an embodiment. [Figure 4] FIG. 1 illustrates a schematic diagram of an image processing pipeline according to an embodiment. [Figure 5] FIG. 2 shows a schematic diagram of image frames of a captured video stream depicting four objects. [Figure 6] FIG. 10 is a schematic diagram illustrating privacy masked image frames of a captured video stream that preserve the privacy of four subjects. [Figure 7] FIG. 2 shows a schematic diagram of edge-filtered image frames of a first edge-filtered version of a captured video stream depicting four objects. [Figure 8] FIG. 10 is a diagram illustrating an example of an edge-filtered image frame of a second edge-filtered version of a captured video stream. [Figure 9]FIG. 10 is a schematic diagram illustrating an example of an edge-filtered image frame of another second edge-filtered version of the captured video stream. [Figure 10] 1A-1C are schematic diagrams illustrating example edge-filtered image frames of an edge-filtered version of a captured video stream; [Figure 11] 11A is a diagram schematically illustrating an example of an edge-filtered image frame 1100 of a second edge-filtered version of a captured video stream, where the number of quantization levels is reduced. [Figure 12] 12A and 12B are schematic diagrams illustrating example edge-filtered image frames 1200 of a second edge-filtered version of a captured video stream. DETAILED DESCRIPTION OF THE INVENTION

[0057] The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown.

[0058] FIG. 1 shows a schematic diagram of an exemplary environment 100 in which various embodiments of the present invention may be implemented. As can be seen in FIG. 1, a scene 102 involving a subject 104, e.g., a person walking toward a building 106, is captured by a camera 108 mounted on a pole 109. It should be noted that the depiction of the scene 102 is a simplified diagram for illustrative purposes only. In a more general sense, the scene 102 can be described as any three-dimensional physical space having a size and shape defined by the field of view of the camera recording the scene. It should further be understood that the camera 108 can be mounted in other suitable locations, such as on a building, a ceiling, a wall, or a fence, and therefore the mounting on the pole 109 is given by way of example only.

[0059] The camera 108 may be a monitoring camera, sometimes referred to as a surveillance camera. Furthermore, the camera may be a fixed camera, such as a stationary camera, or a mobile camera, such as a pan-tilt-zoom (PTZ) camera or a body-worn camera (BWC). The camera 108 may be a visible light camera, an infrared (IR) sensitive camera, or a thermal (long-wave infrared (LWIR)) camera.

[0060] 1, camera 108 is configured to transmit a video stream wirelessly via wireless link 110 to a wired network 112 and ultimately to a client 114 and / or server 116 that may be connected to network 112. It should be understood that there are many combinations of wireless and wired transmission models that may be used, and that FIG. 1 shows only one example.

[0061] The client 114 may have a display on which an operator can view images and / or video streams from the camera. Typically, the client 114 is also connected to a server 116, where the images and / or video streams can be further stored and / or processed. Often, the client 114 is also used to control the camera 108, for example, by an operator issuing control commands at the client 114. For example, the operator may instruct the camera to zoom out on a particular detail of the scene 102. This may be the case if the size in the video stream of a portion of one or more objects 104 is estimated to exceed a second threshold when capturing the video stream using a first field of view, e.g., a first zoom setting, and an alert is generated to the installer, who can instruct the camera to zoom out on that portion of the one or more objects to reduce the size in the video stream of the portion to below the second threshold when capturing the video stream using a second field of view, e.g., a second zoom setting, that is different from the first field of view. This can ensure the privacy of the one or more subjects. However, there are situations in which an operator does not control the camera, and the camera 108 is stationary and simply provides a video stream for the operator to view on the client 120. In such a scenario, the installer may need to relocate the camera 108 to another physical location to obtain a second field of view in which the size of the portion in the video stream is below a second threshold when capturing the video stream using the second field of view. Therefore, relocating the camera 108 at a different physical location can also achieve the desired privacy of the one or more subjects. The different physical location can be a location that is farther away from the one or more subjects than the distance to the one or more subjects when the camera 108 was installed with the first field of view.

[0062] FIG. 2 shows a schematic representation of an embodiment of the camera 108.

[0063] The camera 108 includes a lens 202 that captures the scene 102 and projects the scene 102 onto an image sensor 204. Together, the lens 202 and the image sensor 204 may form an image capture module 206. The image sensor 204 captures image frames that form a video stream. The camera further includes an image processing pipeline (IPP) 208, an encoder 210, and an input / output interface 212.

[0064] Image processing pipeline 208 is configured to perform a range of different operations on image frames received from image sensor 204. Such operations may include filtering, demosaicing, color correction, noise filtering to remove spatial and / or temporal noise, distortion correction to remove, e.g., the effects of barrel distortion, global and / or local tone mapping to enable image processing of scenes containing a wide range of intensities, transformations, e.g., rotation, flat-field correction to remove, e.g., the effects of vignetting, overlays, e.g., privacy masks, application of descriptive text, etc. It should be noted, however, that some of these operations, e.g., transformation operations such as barrel distortion correction, rotation, etc., may be performed by one or more modules, components, or circuits located outside image processing pipeline 208, e.g., in one or more units between image processing pipeline 208 and encoder 210.

[0065] Following the image processing pipeline 208, the image frames are forwarded to an encoder 210, where they are encoded according to an encoding protocol and forwarded using an input / output interface 212 over the network 112 to a receiver, e.g., a client 114 and / or a server 116. It should be noted that the camera 108 shown in Figure 2 also includes many other components, such as a processor, memory, etc., which are common in conventional camera systems and whose purpose and operation are well known to those skilled in the art. Such components have been omitted from the illustration and description of Figure 2 for reasons of clarity.

[0066] The camera 108 may also include data storage 214 for storing data related to the capture of the video stream and data related to methods for facilitating installation of the camera 108. Thus, the data storage may store the captured video stream, first and second versions of the video stream, first and second thresholds, first and second fields of view, an estimated size in the video stream of at least one portion of one or more objects, just to name a few examples. The data storage may be non-volatile memory, such as an SD card.

[0067] There are several conventional video encoding formats, some common video encoding formats that work with various embodiments of the present invention include JPEG, MJPEG (Motion JPEG), HEVC (High Efficiency Video Coding) (also known as H.265 and MPEG-H Part 2), AVC (Advanced Video Coding) (also known as H.264 and MPEG-4 Part 10), VVC (Versatile Video Coding) (also known as H.266, MPEG-I Part 3, and FVC (Future Video Coding)), VP9, ​​VP10, and AV1 (AOMedia Video 1), to name just a few.

[0068] As mentioned, the input and output interface 212 is configured to serve as a communication interface between the camera 108, the network 112, and one or more receiving devices, such as the client 114 and the server 116. Thus, the camera 108 can receive instructions from the client 114 and can send video streams to the client and / or the server 116 via the input and output interface 212.

[0069] The image processing pipeline 208, the encoder 210, and the input / output interface 212 may form an image processing / encoding module 214, which is connected to the image capture module 206. The image capture module 206 and the image processing / encoding module 214 may be arranged as two separate units located at a distance from each other and in communication with each other. In such a scenario, the camera 108 may be referred to as a camera system. Alternatively, the image capture module 206 and the image processing / encoding module 214 may be arranged as a single unit included in the camera 108. Furthermore, the image capture module 206 may be movable, for example in a pan and / or tilt direction, while the image processing / encoding module 214 may be stationary.

[0070] With reference now to the flowchart of FIG. 3 and with reference to FIGS. 2 and 4, a method for facilitating installation of a camera 108 will be described. FIG. 4 schematically illustrates an image processing pipeline 208 according to an embodiment. As shown, an embodiment of the image processing pipeline 208 includes a size estimation component 402, a provisioning component 404, and an alert generation component 406. However, it should be understood that one or more of the size estimation component 402, the provisioning component 404, and the alert generation component 406 may be otherwise disposed on the camera 108. For example, the camera 108 may include one or more of the size estimation component 402, the provisioning component 404, and the alert generation component 406 as separate units communicatively connected to each other and to other portions of the camera 108, such as the image processing pipeline 208, the encoder 210, the input and output interface 212, and the data storage 214.

[0071] 3 may be performed by separate portions of the camera 108, some of the steps may be optional, and the steps may be performed in another suitable order. Furthermore, in this disclosure, one or more steps are described as being performed on image frames of a captured video stream. This may be understood as one or more steps being performed on a temporal portion of the video stream.

[0072] In step S302, a video stream of the scene 102 is captured where the camera 108 is positioned in a first field of view. This step is performed by the image capture module 206, for example, by the lens 202 and the image sensor 204.

[0073] As previously mentioned, the scene 102 includes one or more objects 104 .

[0074] As also previously mentioned, the term field of view refers to the portion of a scene that is visible through the camera 108 at a particular location and orientation in space of the camera 108 and at a particular zoom setting of the camera 108. The particular location is given by the installation location, and the orientation is given by the pan and / or tilt setting of the camera. It should therefore be understood that the first field of view may depend on one or more different camera parameters. For example, the first field of view may depend on the installation location of the camera 108, such as height above ground, the zoom setting of the camera 108, the pan setting of the camera 108, and / or the tilt setting of the camera.

[0075] Additionally, as previously discussed, one or more objects 104 can be any type of object that can reveal privacy information about the object itself, about a person possessing the object, or about a person associated with the object. Thus, an object can be a person or a portion thereof (such as a face or body part), a group of people, a vehicle or a portion thereof (such as a vehicle license plate), to name just a few examples.

[0076] FIG. 5 shows a schematic image frame 500 of a captured video stream depicting four subjects 104, for example four individuals 104a, 104b, 104c, 104d walking on the pavement.

[0077] In step S304, the size of at least one portion of one or more objects 104 in the video stream is estimated. This step may be performed by the size estimation component 402. The size of at least one portion of one or more objects in the video stream may be estimated as the number of pixels that the at least one portion comprises along at least one direction of the video stream. For example, the estimated size of the at least one portion may be given as the number of pixels in the vertical (height) direction and / or the horizontal (width) direction of an image frame of the video stream. Thus, the estimated size may be a length, height, width, or distance between two points given as a number of pixels. For example, the estimated size may be the number of pixels between an individual's eyes or the number of pixels between the left side of an individual's face and the right side of the face. However, the estimated size may also be the number of pixels that at least one portion, e.g., an area, comprises in the image frame. In embodiments in which the estimated size is estimated as the size in the video stream of an individual's face, the estimation component 402 may include or be connected to a face detector (402a) configured to detect faces in the video stream. However, the estimation component 402 may additionally or alternatively include or be connected to one or more other object detectors (402b) configured to detect other objects or portions thereof, such as vehicles and license plates. In FIG. 5, bounding boxes 104a', 104b', 104c', and 104d' schematically illustrate the faces of individuals 104a-104d detected, for example, by face detector 402a. The size of a vehicle in the captured video may be detected, for example, by object detector 402b estimating the distance between the vehicle's headlights or the size of the vehicle's license plate in the captured video stream.

[0078] In step S306, a first edge-filtered version of the video stream is provided to preserve the privacy of one or more objects 104 depicted in the video stream so long as the estimated size in the video stream of at least one portion of the one or more objects 104 is above a first threshold and below a second threshold. This step is performed by the providing component 404.

[0079] In some embodiments, providing the first edge-filtered version of the video stream includes applying an edge filter to the video stream to emphasize edge points in the video stream and suppressing non-edge points in the video stream to generate the first edge-filtered version of the video stream, wherein pixel values ​​of the video stream and pixel values ​​of the first edge-filtered version of the video stream are represented using a first number of quantization levels.

[0080] Providing the first edge-filtered version of the video stream may include transmitting the first edge-filtered version of the video stream to a receiver. As mentioned above, the receiver may be any device operably connected to or contained within the camera 108, via wires or wirelessly. Thus, it should be understood that the first edge-filtered version of the video stream may be transmitted to the client 114, the server 116, and / or the data storage 214.

[0081] FIG. 7 schematically illustrates an edge-filtered image frame 700 of a first edge-filtered version of a captured video stream depicting four subjects 104, e.g., four individuals 104a, 104b, 104c, and 104d. The edge-filtered image frame 700 is obtained by applying a Sobel filter to the image frame 500 and has the highest possible spatial resolution. By highest possible spatial resolution, it is meant that the spatial resolution of the edge-filtered image frame is the same as that of the corresponding image frame of the captured video stream. In other words, the spatial resolution of the edge-filtered image frame 700 is the same as that of the image frame 500. As can be seen in FIG. 7 , the privacy of individuals is revealed as they move closer to the camera, and thus, for example, when the size of their faces in the image frame 700 increases. Therefore, providing the first edge-filtered version of the captured video stream should be disabled before privacy is revealed, for example, if there is already a risk that the privacy of one or more subjects will be revealed.

[0082] Thus, in step S308, in response to the estimated size in the video stream of at least one portion of one or more subjects 104 being above a second threshold indicating that there is a risk that the privacy of at least one subject is being revealed, the camera 108 enters an enhanced secure privacy mode of operation.

[0083] If in the enhanced secure privacy mode of operation, an alert is generated in step S310 prompting the installer to reinstall the camera 108 with a second field of view different from the first field of view, and the provision of the first edge-filtered version of the video stream is disabled in step S312. The provision of the first edge-filtered version of the video stream can be disabled for a predetermined period of time, for example, one or more days, or for a period of time corresponding to the expected period needed for reinstallation of the camera 108.

[0084] It should be appreciated that relocating the camera 108 to obtain a second, different field of view can include changing the camera setting from a first pan level to a second, different pan level, and / or from a first tilt setting to a second, different tilt setting, and / or from a first zoom setting to a second, different zoom setting. The second zoom setting is preferably a zoomed-out setting compared to the first zoom setting. Alternatively, or additionally, relocating can include the camera 108 being moved from a first physical location to a second, different physical location, i.e., from being mounted on a pole on the ground to being mounted high up on a tall building.

[0085] After repositioning the camera 108 at the second field of view, the method steps can be repeated from step S302, with the second field of view now being the new first field of view, i.e., the first field of view referred to in steps S302 to S312.

[0086] Step S310 may be performed by the alert generation component 406, and step S312 may be performed by the provisioning component 404.

[0087] In some embodiments, disabling the provision of the first edge-filtered version of the video stream includes disabling transmission of the first edge-filtered version of the video stream to the receiver, which in some embodiments means that the camera 108 stops recording the first edge-filtered version of the video stream. For example, the first edge-filtered version of the video stream is not stored in the data storage 214.

[0088] Alternatively, in some embodiments, disabling the provision of the first edge-filtered version of the video stream includes disabling the camera from capturing the video stream. This may be the case when the second version of the video stream is not needed or desired, and thus the camera 108 is deactivated when the first edge-filtered version of the video stream is not capable of ensuring the privacy of one or more subjects. In such cases, the image capture module 206, e.g., the lens 202 and / or the image sensor 204, may be disabled from capturing the video stream.

[0089] In some embodiments, disabling the provision of the first edge-filtered version of the video stream includes disabling the camera's image sensor from communicating image information used to create the captured video stream. Thus, in some cases, the camera 108 is disabled by disabling the image sensor 204 from communicating image frames used to create the captured video stream. For example, the image sensor 204 can be disabled from communicating image frames to the image processing / encoding module 214 of the camera 108.

[0090] In optional step S314, the enhanced secure privacy mode of operation further includes providing a second version of the video stream that further protects the privacy of one or more subjects 104. This step may be performed during the predetermined period referred to in step S312 above, during which time the provision of the first edge-filtered version of the video stream is disabled to await repositioning of the camera 108. As described below, providing the second version of the video stream may be achieved in a variety of ways.

[0091] In a first alternative method, providing the second version of the video stream includes generating the second version of the video stream by applying a privacy mask to at least a portion of the video stream to preserve the privacy of one or more objects 104 depicted in the video stream. The privacy mask can be a color mask or a mosaic (pixel) mask. For example, the privacy mask masks the identity of objects in live and recorded video streams by comparing a set background scene with a live camera view and applying dynamic masking to areas of change (essentially moving objects). Furthermore, it may be possible to configure the level of masking required. Color masking may provide the greatest privacy protection of the two while still allowing movement to be seen. Mosaic masking shows moving objects in low resolution, and by seeing the different colors of the objects, it may be easier to distinguish their shapes compared to a color mask that applies a single masking color to the entire object.

[0092] FIG. 6 shows a schematic representation of a privacy masked image frame 600 of a captured video stream that preserves the privacy of four subjects 104, for example, four individuals 104a, 104b, 104c, 104d.

[0093] In a second alternative method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the spatial resolution of the video stream before applying the edge filter to the video stream to reduce a size in the video stream of at least one portion of the one or more objects below a second threshold. As described above, by reducing the spatial resolution of the video stream before applying the edge filter such that a size in the video stream of at least one portion of the one or more objects is below a second threshold, privacy of the one or more objects is preserved in the second edge-filtered version of the video stream.

[0094] FIG. 8 schematically illustrates an example of an edge-filtered image frame 800 of a second edge-filtered version of the captured video stream. The spatial resolution of the edge-filtered image frame 800 is half that of the edge-filtered image frame 700. As can be seen by comparing the edge-filtered image frames 700 and 800, the size of the edge-filtered image frame 800 is reduced compared to the image size of the edge-filtered image frame 700. However, as can be seen in the edge-filtered image frame 800, the privacy of the four individuals is not preserved. To preserve privacy, the spatial resolution should be further reduced before applying the edge filter to reduce the size in the video stream of at least one portion of one or more subjects below a second threshold. FIG. 9 schematically illustrates an example of an edge-filtered image frame 900 of another second edge-filtered version of the captured video stream. The spatial resolution of the edge-filtered image frame 900 is one-quarter of the spatial resolution of the edge-filtered image frame 700. As shown in FIG. 9, the privacy of four individuals is preserved in an edge-filtered image frame 900 .

[0095] In a third alternative method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the number of quantization levels used to represent pixel values ​​of the video stream from a first number of quantization levels to a second number of quantization levels before applying the edge filter to the video stream.

[0096] It should be appreciated that pixel values ​​of the second edge-filtered version of the video stream may be represented using a second number of quantization levels.

[0097] However, it should also be understood that the number of possible quantization levels can be increased again to correspond to the first number of quantization levels, and in such a scenario, only the number of quantization levels corresponding to the second number of quantization levels is used to represent pixel values ​​of the second edge-filtered version of the video stream. For example, if the first number of quantization levels of the video stream corresponds to 256 (8 bits) and the second number of quantization levels is 16 (4 bits), the second edge-filtered version of the video stream can be a 4-bit video stream, and 16 quantization levels are used to represent pixel values, or the number of quantization levels can be increased to 256 (8 bits), but only 16 of the 256 quantization levels are used to represent pixel values.

[0098] As discussed above, by reducing the number of quantization levels used in the video stream from a first number of quantization levels to a second, lower number of quantization levels, granular noise in the second, edge-filtered version of the video stream is increased due to the greater number of intensities that would be represented by each quantization level in the second number of quantization levels compared to the number of intensities that would be represented by each quantization level in the first number of quantization levels. The greater granular noise preserves the privacy of one or more subjects depicted in the second, edge-filtered version of the video stream.

[0099] 11 shows a schematic diagram of an example edge-filtered image frame 1100 of a second edge-filtered version of the captured video stream, where the number of quantization levels is reduced to preserve privacy. In this illustrative diagram, the number of quantization levels in edge-filtered image frame 1100 is 8 (3 bits) compared to 256 quantization levels (8 bits) in edge-filtered image frame 700.

[0100] In a fourth alternative method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by reducing the spatial resolution of the first edge-filtered version of the video stream to obtain a second edge-filtered version of the video stream in which at least one portion of one or more objects has a size below a second threshold. As described above, reducing the spatial resolution of the first edge-filtered version of the video stream reduces the number of pixels that make up one or more image frames of the first edge-filtered version of the video stream. Furthermore, by reducing the spatial resolution of the first edge-filtered version of the video stream such that at least one portion of one or more objects has a size below the second threshold in the second edge-filtered version of the video stream, privacy of the one or more objects is preserved in the second edge-filtered version of the video stream if privacy could not be ensured in the first edge-filtered version of the video stream.

[0101] To preserve privacy regarding subjects depicted in various areas of the captured video stream, a first image resolution of a first area of ​​the edge-filtered image frame depicting a first subject can be different from a second image resolution of a second area of ​​the edge-filtered image frame depicting a second subject. The first image resolution of a first area relates to the amount of image detail in the first area, and correspondingly, the second image resolution of a second area relates to the amount of image detail in the second area. The first and second image resolutions can be obtained by separately downscaling the first and second areas and then upscaling them to contain their original number of pixels. As described above, downscaling reduces the number of pixels, resulting in a loss of image detail, while upscaling increases the number of pixels but cannot restore the lost image detail. Therefore, separately downscaling the first and second areas results in different amounts of image detail being lost in the first and second areas, resulting in different amounts of anonymization. After downscaling, by upscaling the first and second areas to their original pixel counts, the first and second areas will have their original size in the edge-filtered image frame. Figure 10 schematically shows an example of an edge-filtered image frame 1000 of a second edge-filtered version of the captured video stream. In this example, a first resolution of a first area 1002 of the edge-filtered image frame 1000 is half the image resolution of the edge-filtered image frame 700, and a second resolution of a second area 1004 of the edge-filtered image frame 1000 is one-quarter the image resolution of the edge-filtered image frame 700.

[0102] In a fifth alternative method, providing the second version of the video stream includes generating the second version of the video stream as a second edge-filtered version of the video stream by representing edge points in the first edge-filtered version of the video stream that have edge strengths below an edge strength threshold as non-edge points in the second edge-filtered version of the video stream. Figure 12 schematically illustrates an example of an edge-filtered image frame 1200 of the second edge-filtered version of the captured video stream, where edge points that have edge strengths below the edge strength threshold are suppressed by representing them as non-edge points in the second edge-filtered version of the video stream. This increases the privacy of one or more subjects 104. It should be appreciated that further increasing the edge strength threshold may result in further anonymization of one or more subjects 104, which in turn may result in even more secure privacy for one or more subjects 104.

[0103] In optional step S316, if the estimated size of at least one portion of the video stream is below a first threshold, the captured video stream is provided. The captured video stream can be provided by transmitting the captured video stream to a receiver. As mentioned above, the receiver can be any device operably connected to or included within the camera 108 via a wire or wirelessly. Thus, it should be understood that the captured video stream can be transmitted to the client 114, the server 116, and / or the data storage 214.

[0104] Embodiments also relate to a camera 108 for facilitating installation of the camera 108. The camera 108 includes an image capture module 206 configured to capture a video stream of a scene 102 when the camera 108 is installed in a first field of view, the scene 102 including one or more subjects 104.

[0105] The camera 108 also includes a size estimation component 402 that is configured to estimate the size in the video stream of at least one portion of one or more objects 104 .

[0106] Additionally, the camera 108 includes a providing component 404 configured to provide a first edge-filtered version of the video stream to preserve the privacy of one or more subjects 104 depicted in the video stream so long as an estimated size in the video stream of at least a portion of the one or more subjects 104 is above a first threshold and below a second threshold.

[0107] The rendering component 404 is configured to detect and enhance edge points and suppress non-edge points in the captured video stream, and to provide an edge-filtered version of the captured video stream, such as the first and second edge-filtered versions of the captured video stream described above. The rendering component 404 can be or include an edge detector configured to provide the edge-filtered version of the captured video stream.

[0108] Additionally, the rendering component 404 is configured to disable rendering of the first edge-filtered version of the video stream when the camera 108 is in an enhanced secure privacy mode of operation.

[0109] In some embodiments, the providing component 404 is configured to provide a second version of the captured video stream, which may be a privacy masked version or a second edge-filtered version of the captured video stream.

[0110] The rendering component 404 may also be configured to render the captured video stream if an estimate of the size in the video stream of at least one portion of one or more objects 104 is below a first threshold.

[0111] The camera 108 is configured to enter an enhanced secure privacy mode of operation in response to the estimated size in the video stream of at least one portion of one or more subjects 104 being above a second threshold indicating that there is a risk that the privacy of the at least one subject is at risk of being revealed.

[0112] Additionally, the camera 108 includes an alert generation component 406 configured to generate an alert prompting the installer to reinstall the camera with a second field of view that is different from the first field of view when the camera 108 is in the enhanced secure privacy mode of operation.

[0113] Embodiments also relate to non-transitory computer-readable media having computer code instructions stored thereon, which computer code instructions, when executed by a device having processing capabilities, are adapted to perform the method embodiments described herein.

[0114] As described above, the camera 108 can be configured to perform methods to facilitate installation of the camera 108. To this end, the camera 108 can include circuitry configured to perform the various method steps described herein.

[0115] In a hardware implementation, a circuit can be dedicated to and specially designed for performing one or more of the method steps. The circuit can be in the form of one or more integrated circuits, such as one or more application-specific integrated circuits or one or more field-programmable gate arrays. As an example, the camera 108 can thus include a circuit that, in use, estimates the size in the video stream of at least one portion of one or more objects, and, in use, provides a first edge-filtered version of the video stream to preserve the privacy of one or more objects depicted in the video stream so long as the estimated size in the video stream of the at least one portion of the one or more objects is above a first threshold and below a second threshold. The camera 108 can further include a circuit that, in use, enters an enhanced, secure privacy mode of operation in response to the estimated size in the video stream of at least one portion of the one or more objects being above a second threshold, indicating that there is a risk that the privacy of the at least one object is revealed. Additionally, the camera 108 may include circuitry that, when in use, when in the enhanced secure privacy mode, generates an alert prompting the installer to reinstall the camera with a second field of view different from the first field of view and disables providing the first edge-filtered version of the video stream.

[0116] In a software implementation, the circuitry may instead be in the form of a processor, such as a microprocessor, that causes camera 108 to perform any of the methods disclosed herein in association with computer code instructions stored on a (non-transitory) computer-readable medium, such as non-volatile memory. Examples of non-volatile memory include read-only memory, flash memory, ferroelectric RAM, magnetic computer storage devices, optical disks, etc. In the case of software, each of the method steps described above may therefore correspond to a portion of computer code instructions stored on a computer-readable medium that, when executed by the processor, causes camera 108 to perform any of the methods disclosed herein.

[0117] It should be understood that it is also possible to have a combination of hardware and software implementations, meaning that some method steps are performed in hardware and other method steps are performed in software.

[0118] It will be understood by those skilled in the art that the above-described embodiments can be modified in many ways and still utilize the advantages of the present invention as illustrated in the above embodiments. For example, the camera 108 need not be a single unit including the image capture module 206 and the image processing / encoding module 214 in one location, but can be a virtual unit, where the image capture module 206 and the image processing / encoding module 214 operate together but are provided in separate locations. Furthermore, the size estimation component 402, the provisioning component 404, and the alert generation component 406 need not be located in the image processing pipeline 208, but can be located as separate units of the image processing / encoding module 214 and can be in communication with the image processing pipeline 208, the encoder 210, the input and output interface 212, and the data storage 214. Therefore, the present invention should not be limited to the illustrated embodiments, but should be defined only by the appended claims. In addition, as will be understood by those skilled in the art, the illustrated embodiments can be combined. [Explanation of symbols]

[0119] 100 Example Environments 102 scenes 104 Subject 104a Individual 104b Individual 104c personal 104d personal 104a' Bounding Box 104b' bounding box 104c' bounding box 104d' bounding box 106 Building 108 Camera 109 Paul 110 Wireless Link 112 Wired Network 114 clients 116 servers 120 clients 202 Lens 204 Image Sensor 206 Image Acquisition Module 208 Image Processing Pipeline 210 Encoder 212 Input / Output Interface 214 Data Storage 214 Image Processing / Encoding Module 402 Size Estimation Component 402a Face Detector 402b Object detector 404 Serving Component 406 Alert Generation Component 500 image frames 600 image frames 700 image frames 800 image frames 900 image frames 1000 image frames 1002 First Area 1004 Second Area 1100 image frames 1200 image frames

Claims

1. 1. A method in a camera for facilitating installation, comprising: capturing a video stream of a scene when the camera is positioned in a first field of view (S302), the scene including one or more objects; Estimating (S304) a size in the video stream of at least one portion of each of the one or more objects; providing (S306) a first edge-filtered version of the video stream to preserve privacy of the one or more objects depicted in the video stream so long as the estimated size in the video stream of the at least one portion of each of the one or more objects is above a first threshold and below a second threshold; and in response to the estimated size in the video stream of one of the portions being above the second threshold indicating that there is a risk that the privacy of at least one subject is revealed within the provided first edge-filtered version of the video stream, entering an enhanced secure privacy mode of operation (S308), wherein the enhanced secure privacy mode of operation comprises: generating an alert (S310) prompting an installer to reinstall the camera in a second field of view that is different from the first field of view and in which the size of one of the portions is below the second threshold; and temporarily disabling (S312) the provision of the first edge-filtered version of the video stream for the time required to reposition the camera in the second field of view.

2. The enhanced secure privacy mode of operation further comprises:

2. The method of claim 1, further comprising: providing (S314) a second version of the video stream that further protects the privacy of the one or more subjects compared to the first edge-filtered version of the video stream during the time required to reposition the camera in the second field of view.

3. providing (S314) the second version of the video stream; 3. The method of claim 2, comprising generating the second version of the video stream by applying a privacy mask to at least a portion of the video stream to preserve privacy of the one or more subjects depicted in the video stream.

4. Providing (S306) the first edge-filtered version of the video stream, 4. The method of claim 1, further comprising generating the first edge-filtered version of the video stream by applying an edge filter to the video stream to emphasize edge points in the video stream and suppressing non-edge points in the video stream, wherein pixel values ​​of the video stream are represented using a first number of quantization levels.

5. Providing (S314) a second version of the video stream, reducing a spatial resolution of the video stream to reduce the size in the video stream of the at least one portion of the one or more objects below the second threshold before applying the edge filter to the video stream.

5. The method of claim 4, comprising generating a second version of the video stream as a second edge-filtered version of the video stream by:

6. Providing (S314) a second version of the video stream, reducing the number of quantization levels used to represent pixel values ​​of the video stream from the first number of quantization levels to a second number of quantization levels before applying the edge filter to the video stream.

5. The method of claim 4, comprising generating a second version of the video stream as a second edge-filtered version of the video stream by:

7. Providing (S314) a second version of the video stream, a second edge-filtered version of the video stream, the second edge-filtered version of the video stream having a reduced spatial resolution such that the size of the at least one portion of the one or more objects is below the second threshold; to get 5. The method of claim 2, further comprising generating a second version of the video stream as a second edge-filtered version of the video stream by:

8. Providing (S314) a second version of the video stream, representing edge points having edge strengths below an edge strength threshold in the first edge-filtered version of the video stream as non-edge points in a second edge-filtered version of the video stream.

5. The method of claim 2, further comprising generating a second version of the video stream as a second edge-filtered version of the video stream by:

9. Providing (S306) the first edge-filtered version of the video stream, transmitting the first edge-filtered version of the video stream to a receiver; Disabling providing the first edge-filtered version of the video stream 9. The method of claim 1, comprising disabling transmission of the first edge-filtered version of the video stream to the receiver.

10. Disabling (S312) the provision of the first edge-filtered version of the video stream, The method of claim 1 , comprising disabling the camera (108) from capturing the video stream.

11. Disabling (S312) the provision of the first edge-filtered version of the video stream, The method of claim 1 , comprising disabling an image sensor (204) of the camera (108) from transmitting image frames used to create the captured video stream.

12. providing the captured video stream if the estimated size in the video stream of the at least one portion of the one or more objects is below the first threshold (S316); 12. The method of claim 1, further comprising:

13. A camera for facilitating installation, an image capture module (206) configured to capture a video stream of a scene when the camera is positioned at a first field of view, the scene including one or more objects; a size estimation component (402) configured to estimate a size in the video stream of at least one portion of each of the one or more objects; a rendering component (404) configured to render a first edge-filtered version of the video stream to preserve privacy of the one or more objects depicted in the video stream so long as the estimated size in the video stream of the at least one portion of each of the one or more objects is above a first threshold and below a second threshold; in response to the estimated size in the video stream of one of the portions being above the second threshold indicating that there is a risk that the privacy of at least one subject is revealed within the provided first edge-filtered version of the video stream, the camera (108) is configured to enter an enhanced secure privacy mode of operation; an alert generation component (406) included in the camera is configured to generate an alert prompting an installer to reinstall the camera in a second field of view that is different from the first field of view and in which the size of one of the portions is below the second threshold; the providing component (404) is configured to temporarily disable providing the first edge-filtered version of the video stream for the time required to reposition the camera in the second field of view.

14. 13. A non-transitory computer readable medium having stored thereon computer code instructions adapted to perform the method of any one of claims 1 to 12 when executed by a device having processing capability.

Images