Abstract: A video processing pipeline comprises: a video frame partitioning module configured to divide video frames into frame portions; a change module configured to, for each frame portion of a second video frame, determine a difference between video data of the frame portion of the second video frame and video data of a corresponding frame portion of a first video frame; a probability module configured to determine a probability, that decreases with an increasing size of the difference, for individually suppressing each of the determined differences; a suppress module configured to decide whether to suppress each determined difference or not based on a respective determined probability, and to suppress the difference in case it is decided to suppress the difference; and an encode module configured to inter-encode the frame portions of the second video frame in relation to the first video frame.

Abstract: Video encoding, and specifically to a method and an encoder which can adapt the probability of intra refresh of image frame subdivisions based on a count of image frames since a previous refresh and modulated through convex or concave shaped distribution functions are set forth herein.

Abstract: A method encodes an image of a video sequence by analyzing motion in the video sequence to identify a coherent region in the image that has moved with a distance vector which is longer than a threshold since a previously encoded image in the video sequence. A cost for inter-coding the block is calculated as a combination of a cost for encoding a motion vector and a residual. For at least one block of pixels in the coherent region, the cost for encoding the motion vector is calculated relative to the distance vector of the coherent region instead of being calculated relative to a motion vector of a neighbouring block of pixels in the image. The block is then inter-coded if the combined cost for encoding the motion vector and the cost for encoding the residual when combined are below a cost for intra-coding the block of pixels.

Abstract: A method for encoding and transmitting a plurality of image frames of a video stream includes: intra refresh encoding the plurality of image frames; encoding one image frame of the plurality of image frames to produce encoded image data of the one image frame, the encoded image data being organized in a plurality of data packets, wherein the encoding comprises intra frame encoding the one image frame; transmitting, over a time period, the intra refresh encoded image frames; transmitting the plurality of data packets, wherein the transmission of the plurality of data packets is distributed over the time period during which the intra refresh encoded image frames are transmitted. An interrelated method for receiving and storing the plurality of image frames, as well as devices and computer program products for performing the methods, are also provided.

Abstract: A lens arrangement of a camera device includes a lens holder and a lens member, the lens member being slidingly received by the cavity by axial insertion of the lens member into the cavity such that the longitudinal lens holder axis coincides with the longitudinal lens member axis, wherein a locking force is applied by the locking member in a direction from the first lens holder surface section, the locking force being perpendicular to the plane, wherein the lens holder protrusion and the lens member protrusion are such aligned that the locking force applied by the locking member in the direction from the first lens holder surface section is applied to the first lens member surface section. The second lens member surface section engage the second lens holder surface section in response to the locking force applied to the first lens member surface section.

Abstract: Video encoding is provided using periodic intra refresh, which can adapt padding of an intra encoding region between image frames based on a current level motion in the image frame. Upon a current level of motion not exceeding a first threshold, an intra encoding region of the image frame according to a predefined periodic intra refresh pattern is intra encoded. Upon the current level of motion exceeding the first threshold, the intra encoding region of the image frame is expanded to overlap to a determined extent with a previously encoded intra encoding region among the plurality of image frames, and the expanded intra encoding region of the image frame is intra encoded. Regions of the image different from the intra encoding regions and the expanded intra encoded region, respectively are inter frame encoded.

Abstract: In a method for tracking an object in video-monitoring scenes, multiple feature vectors are extracted (722) and assembled (724) in point clouds, wherein a point cloud may be assembled for each tracklet, i.e. for each separate part of a track. In order to determine if different tracklets relate to the same or different objects the point clouds of each tracklet is compared (734). Based on the outcome of the comparison it is deduced if the first object and the second object may be considered to be the same object and, if so, the first object is associated (738) with the second object.

Abstract: A camera device comprises a camera unit including an outer shell with a spherical shape and provided with an equatorial groove, a base member provided with a seating, and a cover provided with a pivot defining a tilting axis and an aperture for providing a free line of sight for the camera unit. The camera unit is arranged between the seating and the cover such that the pivot is received by the equatorial groove and such that the cover and the seating of the base member are pressed against the outer shell of the camera unit from opposing sides thereof. The pivot is arranged on a lug adjoining the cover via a lug transition and defined by a slit such that the lug is laterally displaceable in a direction parallel with the tilting axis in response to the pivot being subjected to a force having a component in said direction.

Abstract: Methods and techniques for configuring a monitoring device to communicate with a service server. The method includes sending, by the monitoring device to a control server, an initial connection message, authenticating, by the control server, the monitoring device using the initial connection message, in response to authenticating the monitoring device, sending, by the control server, a list of one or more addresses to the monitoring device, and establishing, by the monitoring device, a service connection between the monitoring device and a service server using the list of one or more addresses received from the control server.

Abstract: A method, device and system for generating a transformation function, mapping position detections of objects in a scene, detected with a positioning device, to a graphical representation of the scene. The teachings enable the detected positions by the positioning device to be mapped to the graphical representation of the monitored scene without the need of previous references to geographical coordinate systems for the positioning device and the graphical representation of the scene. Virtually any type of image may hence be used as a graphical representation of the scene, even hand-drawn sketches.

Abstract: A method for producing an interference reduced radar image comprises receiving a measured sequence of beat signals; identifying one or more interference segments within the measured sequence of beat signals, an interference segment being a segment subject to an interference; doctoring the measured sequence of beat signals by creating a doctored representation of the measured sequence of beat signals in the form of a matrix Y; creating a doctoring mask representing the doctoring of the measured sequence of beat signals, the doctoring mask being a matrix M; and estimating a reconstructed range-doppler image {circumflex over (X)} from Y and M, wherein the reconstructed range-doppler image is a range-doppler image of Y which is deconvolved using M; such that doctoring the measured sequence of beat signals at least partially removes interference effects and estimating a reconstructed range-doppler image at least partially removes image artefacts created by the doctoring.

Abstract: A method for displaying a video stream of a scene captured by a monitoring camera on a display of a remote client device comprises receiving, at the client device, the video stream and information indicating an on/off status for an IR-illuminator illuminating the scene; setting a display setting of the display differently based on upon the on/off status for the IR-illuminator; and displaying the video stream on the display using the display setting. The client device comprises a display, a receiver which receives a video stream from the monitoring camera, and a control circuit. The control circuit executes an IR-illuminator status function to extract information indicating on/off status for the IR-illuminator illuminating the scene, a display setting function of the display differently upon the on/off status for the IR-illuminator, and a displaying function displays the video stream on the display using the setting set by the display setting function.

Abstract: A method of object re-identification in images of objects comprises providing a plurality of neural networks for object re-identification, wherein each of the plurality of neural networks is trained on image data with different sets of anatomical features, each set being represented by a reference vector; receiving a plurality of images of objects and an input vector representing anatomical features that are depicted in all of the plurality of images; comparing the input vector with the reference vectors for determining, according to a predefined condition, the most similar reference vector; and inputting image data of the plurality of objects to the neural network represented by the most similar reference vector for determining whether the plurality of objects have the same identity.

Abstract: The present invention relates to a method for adding a graphical object to image data of one or more image frames comprising a first image frame, the graphical object being added during encoding of the one or more image frames using an encoder, wherein the image data generator is converting the graphical object into a first set of discrete frequency transform, DFT, blocks each DFT block being associated with a position in the one or more image frames to which the DFT block corresponds. The encoder is performing DFT on a plurality of block of pixels of the first image frame, to output a second set of DFT blocks and then replacing a subset of DFT blocks of the second set of DFT blocks with the first set of DFT blocks according to the positions associated with the first set of DFT blocks.

Abstract: An electrical coupling transfers electrical signals between a camera head and a cable and comprises a first part associated with the camera head and a second part associated with the cable and connectable to the first part. The coupling establishes contact between connectors of the first and second parts. The first part comprises a first connection position for reception of the second part, and a second connection position for reception of the second part. The connectors of the first and second parts comprise dot shaped connectors and elongated connectors. One of the first and second parts comprise the dot shaped connectors, and the other one comprises the elongated connectors. Each dot shaped connector is associated with one of the elongated connectors, and the connectors are arranged such that each dot shaped connector connects with an associated elongated connector in both the first connection position and the second connection position.

Abstract: A method and system for composing a video of a course of actions along a track in an area monitored by a plurality of video cameras. A first sequence of user inputs defining the track is received. Each user input in the first sequence is associated with a time stamp and is received as an indication of a position in a map of the area being monitored. For each user input in the first sequence, video recordings from those that have a field-of-view covering the position indicated by the user input are collected. The collected video recordings are recorded in a time period starting at the time stamp associated with the user input and ending at a time stamp associated with a next user input in the first sequence or when an indication to stop the collecting is received. A video material is then composed from the collected video recordings.

Abstract: A method of reducing purple fringing in images captured by a camera, comprises: acquiring a raw image of a scene with an image sensor of the camera, demosaicing the raw image, and applying an adjusted color correction matrix to the demosaiced raw image. The adjusted color correction matrix is deduced by calibrating the spectral response of the image sensor to a color rendition chart to which the color data of a purple fringe has been added, and furthermore the color correction matrix is adjusted such that the image sensor response for color values of the purple fringe is transformed into color values of a predetermined replacement color following application of the color correction matrix.