Abstract: A method of determining a maximum permissible key frame distance for use in encoding image frames in a video sequence comprising encoding a plurality of video test sequences, each video test sequence having a respective noise level, where each video test sequence is encoded using a respective quantization parameter and a plurality of key frame distances is disclosed. For each video test sequence, an output bitrate is determined for each key frame distance. For each combination of noise level, quantization parameter, and key frame distance, the determined output bitrate is stored and a maximum key frame distance at which output bitrate decreases in response to an increase in key frame distance is identified as maximum permissible key frame distance. A method of encoding image frames in a video sequence is also disclosed, as well as a system, a camera and a computer program product for performing the methods.

Abstract: A method, system, and apparatus related to the field of background subtraction in images is disclosed. In particular, the method, system, and apparatus is related to determining whether pixel positions in an image frame of a video sequence belongs to a background or a foreground of a captured scene using a determined level of dynamics of the pixel position.

Abstract: A method for generating an alert signal in a surveillance system comprising: detecting a targeted individual in a video stream, selecting the targeted individual, and tracking the targeted individual, as first steps. The method also comprises classifying actions of the detected individual over a plurality of image frames in the video stream in response to the identification of the detected object as being a targeted person, and generating an alert signal if the classified action of the object is classified as a predefined alert-generating action.

Abstract: A system comprising a video camera and a client device and a method performed therein. The video camera captures a plurality of images concurrently using a plurality of image sensors having partly overlapping fields of views. Overlapping portions of the images are identified, and the images are joined to generate a panorama image. When joining the images, image data is included from only one of the images in overlapping portions, and image data from the other images in the overlapping portions is ignored. The panorama image and the ignored image data is encoded and transmitted to the client device in an encoded video stream. The client device decodes the video stream and, if the client device is customized, it updates the panorama image in portions corresponding to overlapping portions of the plurality of images using the image data that was ignored by the video camera when generating the panorama image.

Abstract: A method for estimating a sub-pixel position of an extreme point in an image uses a parametric function. The parametric function is fitted locally to a group of neighboring pixels in the image, and a spatial position of an extreme point of the parametric function is identified. If the extreme point of the parametric function is of a different type than the extreme point in the image, or the position of the extreme point of the parametric function is located outside an area defined by the pixel positions in the group of neighboring pixels, a pixel is removed from the group of neighboring pixels and the fitting of the parametric function is repeated. In the end, the sub-pixel position is estimated as the position of the extreme point of the parametric function. A level of uncertainty of the estimated sub-pixel position is estimated as the number of repetitions needed before arriving at the estimate of the sub-pixel position.

Abstract: A method, a controller, and a system for encoding a sequence of video frames captured by a camera mounted to a moving object. The method comprises receiving input indicating an amount of movement of the camera, receiving input regarding a predetermined distance, and selecting between intra-coding and inter-coding of the video frames of the sequence based on the amount of movement of the camera and the predetermined distance, such that the camera moves at most the predetermined distance between capturing video frames which are intra-coded.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for displaying a video. A video stream including a plurality of image frames, wherein at least some image frames include an overlay, is received by a video management system. The video management system determines a position of the overlay within an image frame. The video management system applies an image adjustment function to the image frame to create an adjusted image frame. The image adjustment function uses the determined position of the overlay to adjust the image while keeping the appearance of the overlay essentially unchanged, and the video stream including the adjusted image frame is displayed.

Abstract: A method of focusing a camera with a movable field of view includes obtaining a current field of view setting corresponding to a current field of view of the camera, retrieving, based on the obtained current field of view setting, focusing data pertaining to the focusing method that was previously used to focus the camera for a previous field of view, at least partly overlapping the obtained current field of view, by accessing a focusing assisting database comprising a plurality of camera focusing entries. wherein each camera focusing entry includes a respective previous field of view setting, corresponding to a respective previous field of view and thereto associated focusing data pertaining to the focusing method that was previously used to focus the camera for the respective previous field of view.

Abstract: A method, computer program, computer and system for training a neural network that receives a plurality of input digital images and, for each specific input digital image, outputs data for determining a relevance level of groups of pixels in the specific input digital image.

Abstract: There is provided a method and an apparatus for updating a background model used for background subtraction of an image. An image is received and each pixel in the image is classified as being foreground or background by performing background subtraction using a background model which comprises a collection of background samples for each pixel in the image. For each pixel in the image being classified as background, the background model is updated by selecting a background sample in the collection of background samples associated with the pixel which fulfills a similarity condition, and replacing the background sample which fulfills the similarity condition with image data of the pixel.

Abstract: An assembly for securing an electronic device to a support surface, comprises an anchoring unit and a mounting unit and is arranged to automatically connect the electronic device to a network when the mounting unit slides along the anchoring unit into a fully connected position. The assembly also is arranged to allow the electronic device to be securely held by the anchoring unit in an intermediate connection position without network connection.

Abstract: A camera arrangement comprises an optics unit and a sensor board with an image sensor attached to a first surface of the sensor board facing the optics unit. An alignment element formed by a thermoplastic material is fixedly attached to the optics unit, and a biasing element is configured to bias the alignment element into abutment with a contact area of the sensor board. A heating element is arranged in the contact area. Upon activation the heating element is configured to transfer heat to the alignment element, such that the alignment element is heated at least partly to a temperature of at least the glass transition temperature of the thermoplastic material, for enabling alignment of the sensor board relative the optics unit.