Abstract: A method and a device associate an object detection in a first frame with an object detection in a second frame using a convolutional neural (CNN) network trained to determine feature vectors such that object detections relating to separate objects are arranged in separate clusters. The CNN determines a reference set of feature vectors associated with the object detection in the first frame, and candidate sets of feature vectors associated with a respective one of identified areas corresponding to object detections in the second frame. A set of closest feature vectors is determined, and then measure of closeness to the reference set of feature vectors is determined for each candidate. A respective weight is determined for each object detection in the second frame. The object detection in the first frame is associated with one of the object detections in the second frame based on the assigned weights.

Abstract: A method for handling a radio-frequency connection between a control unit and a mobile device of an access control system. The mobile device is connected to the control unit using radio-frequency signal communication. The method comprises obtaining an indication of a first event generated in the access control system in response to a first request for the control unit to arrange to carry out an action. After a release of the connection by the control unit, the method further comprises obtaining an indication of whether or not a second event has been generated in the access control system in response to a second request for the control unit to arrange to carry out the action. The method further comprises determining, based on the indication of whether or not the second event has been generated, whether or not to allow the mobile device to re-connect to the control unit.

Abstract: A method of processing a video stream comprises receiving a first/second set of input image frames comprising image data originating from a first/second source of input image frames; encoding the sets of input image frames into first/second sets of encoded image frames, forming a combined video stream, wherein an encoded image frame of the first set of encoded image frames exclusively references one or more other encoded image frames of the first set of encoded image frames, and an encoded image frame of the second set of encoded image frames references both an encoded image frame of the first set of encoded image frames and another encoded image frame of the second set of encoded image frames; and signing, using a first/second key, a first/second signing group comprising one or more encoded image frames of the first/second set of encoded image frames, wherein each key pertains to the respective source.

Abstract: There is provided a camera and a method therein for facilitating installation of the camera. The method comprises capturing a video stream of a scene when the camera is installed with a first FOV, which scene comprises an object. A size in the video stream of at least one part of the object is estimated. As long as the estimated size is above a first threshold and below a second threshold, providing a first, edge-filtered, version of the video stream to secure privacy of the object. In response to the estimated size being above the second threshold indicating that the privacy is at risk of being revealed, entering an enhanced secure privacy mode comprising generating an alert to prompt an installer to re-install the camera with a second FOV different from the first FOV, and disabling provision of the first, edge-filtered, version of the video stream.

Abstract: A method for streaming a live video stream in a system comprising a video camera generating the live video stream, a video recorder, and a video. The method comprises: at the video server, receiving, from a client device, a request for the live video stream from the video camera; transmitting from the video server, a push trigger to the video camera, the push trigger instructing the video camera to push the live video stream to the video recorder; upon receiving the push trigger, initiating a push of the live video stream from the video camera to the video recorder; pushing the live video stream from the video camera to the video recorder; pulling, by the video server, the live video stream from the video recorder; and transmitting, by the video server, the live video stream to the client device.

Abstract: A dome for a surveillance camera comprises an at least partially transparent spherical portion, a front transition portion, a back transition portion, and lateral transition portions. All transition portions extend to a perimeter plane and a tangent to the spherical portion where it connects to the front transition portion has an angle ? relative to a normal to the perimeter plane, as measured in a symmetry plane, and a tangent to the spherical portion where it connects to the back transition portion has an angle ? relative to a normal to the perimeter plane, as measured in the same plane and the same direction as the angle ?. The angle ? is equal to or larger than the angle ?.

Abstract: A device configured for mounting to a surface, comprises a base part and an attachment part, the attachment part being attachable to the base part, wherein the base part is provided with a keyhole-shaped opening for receiving a fastener comprising a head and a shaft for attaching the base part to the surface, the keyhole-shaped opening comprises a first segment permitting passage of the head and shaft and a second segment permitting passage of the shaft but preventing passage of the head.

Abstract: An image system (100) comprising a camera (110), a control unit (120), a processing unit (130), one or more illumination devices (140). The image system (100) is configured to obtain a distance matrix for a scene. Each cell of the distance matrix corresponds to a zone of the scene and a value in each cell represents the distance from an object in the zone to the camera. The image system is further configured to obtain an illumination intensity matrix for the scene. Each cell of the illumination intensity matrix corresponds to a zone of the scene and a value in each cell represents illumination intensity of one or more illumination devices in each zone of the scene. The image system is further configured to generate a compensation matrix based on the illumination intensity matrix and the distance matrix and generate an image of the scene based on the compensation matrix.

Abstract: A camera and a method of counteracting an increase in humidity of a first air volume inside an enclosure of a camera, the increase in humidity being induced by a first electrical component being shifted from a first state to a second state being associated with an increase in heat dissipation from the first electrical component, the first electrical component directly or indirectly dissipating heat to the first air volume. The concept involves: temporarily decreasing, as the first electrical component is shifted the second state, electrical power consumption of a second electrical component having a variable electrical power consumption, the second electrical component directly or indirectly dissipating heat to the first air volume.

Abstract: Methods and apparatus, including computer program products, for selecting a cropping area in a sequence of images captured by a camera. First external motion data including data of external factors affecting movement of the camera is correlated with internal motion data describing a movement of the camera. The first external motion data and the internal motion data are obtained during a first time interval. Second external motion data is obtained during a second time interval subsequent to the first time interval. A sequence of images being captured during a third time interval is stabilized by selecting a cropping area based on the correlation and the second external motion data. The cropping area remains constant and maximized in size with respect to the field of view of the images during the third time interval. The third time interval is subsequent to, or partly overlapping with, the second time interval.

Abstract: A tag for indicating a region of interest, ROI, has a predefined format and codes ROI information, which is readable by imaging the tag and which includes a size indication and a relative position indication, the respective indications allowing the ROI's size and position to be determined relative to the tag's size and position. A method for locating a ROI in an image comprises: obtaining an image; searching in the image for a tag with the predefined format; and determining a ROI on the basis of the tag's size and position in the image and the ROI information. A method for generating a tag comprises: obtaining an image including a visible provisional tag of same physical size as the tag to be generated; obtaining operator input identifying a ROI in the image; deriving the size indication and relative position indication; and printing the tag.

Abstract: An image processing device a camera and a method for of encoding images captured by a camera are disclosed. For each image of an image sequence captured by the camera, the image is pre-processed by filtering the image by applying a privacy filter, the privacy filter being configured to distort the image in such a way that privacy is achieved in the filtered image, and, for at least a subset of the filtered images, by colour revising the filtered image by changing colour of pixels of a plurality of scattered areas of the filtered image such that a respective colour of one or more pixels of each area of the plurality of scattered areas represents one or more original colours of one or more pixels before filtering at a location of that area in the filtered image. The pre-processed images are then encoded into an encoded video stream.

Abstract: Methods, systems and computer program products, for producing streams of image frames. Image frames in streaming video are segmented into background segments and instance segments. A background image frame containing the background segments is created. At least some of the instance segments are classified into movable objects of interest and movable objects of non-interest. During a background update time period, the background image frame is updated when a movable object of non-interest has moved to reveal a background area, to include the revealed background area in the background image frame. A foreground image containing the movable objects of interest is created. Blocks of pixels of the updated background and foreground image frames are encoded. A stream of encoded foreground image frames having a first frame rate is produced. A stream of encoded updated background image frames a second, lower frame rate is produced.

Abstract: A method for image stabilization of a video stream captured by a panable and/or tiltable video camera the method comprising: generating a motor position signal, Y1, of a pan/tilt motor of the video camera; generating a gyro signal, Y2, of a gyroscopic sensor of the video camera; generating a reference signal from a predetermined movement curve of the pan/tilt motor of the video camera, the reference signal is a reference on how a pan/tilt operation of the video camera is made without shaking of the video camera; from the motor position signal, Y1, and the gyro signal, Y2, generating a combined signal, Y, according to: Y=F1*Y1+F2*Y2, wherein F1 is a low pass filter and F2 is a high pass filter; and performing image stabilization on the video stream based on a difference between the combined signal, Y, and the reference signal.

Abstract: A mounting bracket for the mounting of an electronic device, such as a camera, on a support surface is provided. The mounting bracket comprises a mounting plate configured to attach the mounting bracket to the support surface, and a device attachment portion configured to receive the electronic device. The mounting plate comprises a recess which is formed at a peripheral edge portion of the mounting bracket. In a condition when the mounting bracket is attached to the support surface, the recess allows insertion of a user's finger in an interspace being formed between the mounting plate and the support surface.

Abstract: A method (100), a device (600;700) and a system (800) for processing image data representing a scene for extracting features related to objects in the scene using a convolutional neural network are disclosed. Two or more portions of the image data representing a respective one of two or more portions of the scene are processed (S110), by means of a respective one of two or more circuitries, through a first number of layers of the convolutional neural network to form two or more outputs, wherein the two or more portions of the scene are partially overlapping. The two or more outputs are combined (S120) to form a combined output, and the combined output is processed (S130) through a second number of layers of the convolutional neural network by means of one of the two or more circuitries for extracting features related to objects in the scene.

Abstract: Systems and methods of managing a certificate associated with a component located at a remote location from a certificate authority system are provided. A certificate request is received, wherein the certificate request comprises a key associated with the component. A certificate is generated corresponding to the key received in the certificate request, and a validity status of the certificate is caused to be set to invalid. The certificate is provided to the component and it is determined whether the component matches the certificate. Upon determining that the component matches the certificate, the validity status is caused to be set to valid.

Abstract: Methods and apparatus, including computer program products, for detecting a problem with a thermal camera. A current contrast value is determined for the thermal camera. It is determined whether the current contrast value deviates from a reference contrast value by more than a predetermined value. In response to determining that the current contrast value deviates from the reference contrast value by more than a predetermined value and for more than a predetermined period of time, an indication of a problem with the thermal camera is provided.

Abstract: A portable device, and a method performed in a portable device, for associating media captured by the portable device to one or more parties having requested the media to be captured at one or more locations. The method comprises: receiving information associating each of the one or more parties with a location; dynamically determining a location of the portable device; dynamically associating the media captured by the portable device to the one or more parties, such that media currently being captured by the portable device is associated with a party that according to the received information is associated with a current location of the portable device.

Abstract: A method includes controlling a light source to output a first intensity of light while an image-capturing device captures a scene in a first upcoming image frame with a first exposure value setting, controlling the light source to switch from the first to a second intensity of light so the light source outputs the second intensity of light while capturing the scene with a second upcoming image frame with a second exposure value setting, wherein the second intensity of light is higher than the first intensity of light when the second exposure value setting is higher than the first exposure value setting, and the second intensity of light is lower than the first when the second exposure value setting is lower than the first exposure value setting, and stitching the first upcoming image frame with the second upcoming image frame into a high-dynamic range image frame.