Abstract: A video encoding method for encoding a series of images of original video data into an encoded video, comprises setting a periodic intra refresh pattern for the encoding of the series of images; setting a number of delta frames to be added between consecutive intra refresh frames of the periodic intra refresh pattern, thereby adjusting the intra refresh periodicity of the encoded video stream; and encoding the series of images of original video data into the encoded video stream using the set periodic intra refresh pattern and the set number of delta frames to be added between consecutive intra refresh frames. During the encoding, a current intra refresh frame is set to directly refer to a previous intra refresh frame and each delta frame added in between two consecutive intra refresh frames is set to only refer to a previous one of the two consecutive intra refresh frames.

Abstract: A method for encoding video is disclosed wherein information representative of pixels in an image frame is received, and a spatial statistical measure of said information is calculated for groups of neighbouring pixels to form a group value for each group of pixels. A set of available quantization steps is determined comprising a first predetermined quantization step. For a first group of neighbouring pixels, the method comprises: for each available quantization step calculating a remainder after division of the group value of the first group of pixels by the respective available quantization step. The quantization step of the set that results in the smallest remainder is selected as selected quantization step. The first group of pixels is encoded using the selected quantization step. A method of encoding differences between image frames is also disclosed, as well as encoding systems.

Abstract: Apparatus are provided for generating an object classification for an object, the apparatus comprising an image sensor, a radar sensor, and a processing unit, the processing unit configured to perform the steps of: receiving image data for the object from the image sensor, operating an image-based object classifier on the image data to generate an image-based object classification, receiving radar data for the object from the radar sensor, operating a radar-based object classifier on the radar data to generate a radar-based object classification, selecting between the image-based object classification and the radar-based object classification to output as the object classification for the object, determining if a training condition is met by the radar-based object classification, and training the radar-based object classifier using the image-based object classification when the training condition is met by the radar-based object classification.

Abstract: A method (200) of determining a transformation matrix for transformation of ranging data from a first coordinate system for the ranging sensor to a second coordinate system for an image sensor is disclosed. The method comprises providing (201) a ranging sensor and an image sensor; acquiring (202) a ranging frame sequence, and an image frame sequence; determining (203) points of motion in frames of each acquired frame sequence; for each frame in one of the frame sequences: evaluating (204) if a single motion point has been determined in the frame, and if a single motion point has been determined, evaluating (206) if a single motion point has been determined in a temporally corresponding frame of the other frame sequence and, in that case, pairing (207) the temporally corresponding frames, whereby a set of frame pairs is formed, and determining (209) the transformation matrix based on the set of frame pairs.

Abstract: A method for, in a map of background objects, registering presence of a stationary object exhibiting motion at a location in a scene monitored by a radar detector comprising detecting over time radar echoes at a radar detector monitoring a scene. The moving object is one of a true moving object or a stationary object exhibiting motion. The over time detected radar echoes are evaluated for finding a stationary object exhibiting motion. The presence of the stationary object exhibiting motion is registered at a location, corresponding to the location of the stationary object exhibiting motion, in a map of background objects. A method for detecting moving objects using a radar detector is also presented wherein the map of background objects is used as input.

Abstract: A method, device, and computer program product related to the field of image encoding. In particular, the method, device, and computer program product uses multiple image sensors and multiple encoders for outputting a single encoded image, where image data captured by a first image sensor is added to the encoded image as a first tile or slice, and where image data captured by a second image sensor is added to the encoded image as a second tile or slice.

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: A method includes defining a background model of the video sequence by applying a first algorithm, the background model defining whether that spatial area belongs to a background or a foreground in the video sequence, wherein a detected significant change in image data in a spatial area in an image frame relative image data in said spatial area in a preceding image frame is indicative of said spatial area belonging to the foreground; indicating that an idle area of the defined foreground areas is to be transitioned from foreground to background; and determining whether the idle area is to be transitioned by applying a second algorithm to image data of an image frame of the video sequence, the image data at least partly corresponding to the idle area; wherein if the idle area is not to be transitioned, maintaining the idle area as a foreground area in the background model.

Abstract: A dome camera has a base, two camera heads and a dome cover. The base is configured for mounting the dome camera to a surface. The two camera heads are arranged on the base. The dome cover is arranged over the camera heads and the base. The dome cover includes at least two dome-shaped sections, wherein each dome-shaped section covers a camera head, and a center section joining the dome-shaped sections. The dome cover is formed in a single piece.

Abstract: A method encodes a sequence of image frames depicting an object whose privacy is to be protected. A first and a second version of the sequence of image frames is generated. Image frames of the first version, but not the second version, of the sequence are provided with a privacy mask to protect the privacy of the object depicted therein. The first version of the sequence is encoded as a first encoded sequence of intra-coded image frames and inter-coded image frames. A second version of the sequence is encoded as a second encoded sequence of inter-coded image frames. The inter-coded image frames of the second encoded sequence are encoded by using the intra-coded image frames of the first encoded sequence. The inter-coded image frames of the second encoded sequence are encrypted, and thereafter the first and the second encoded sequence are merged into a single output sequence.

Abstract: A method and a digital video camera for reducing intensity variations in a video stream depicting a scene comprising capturing, using a first sensor setting, a first frame; detecting a change in intensity in a portion of the first frame, the portion represents a first area of the scene; determining a second sensor setting based on the first frame; capturing, using the second sensor setting, a second frame; creating a local tone mapping mask, wherein a local tone mapping in the first area of the scene is different from a local tone mapping in an area outside the first area, and wherein the local tone mapping in the area outside the first area is based on a relation between the first sensor setting and the second sensor setting; and applying the local tone mapping mask to the second frame.

Abstract: An display installation hinge includes pivot arms extending from a lower portion of a housing, for enabling pivoting between an open position in which the pivot arms may engage with the display, and a closed position in which the display has been moved to a closed position in relation to the wall-mounted housing. The pivot arms have a distal free end configured to engage with the display, wherein a proximal end of the pivot arms is associated with a pivot axis. The installation hinge further comprises a physical guide configured to support the display when the display is in engagement with the pivot arms in the open position, so as to prevent it from moving down the pivot arms. The physical guide is configured to release the support as the pivot arms are in the closed position, enabling for the display to travel further down the pivot arms.

Abstract: A video encoding method comprises encoding a series of images of original video data into an encoded video stream comprising key frames and delta frames, wherein the delta frames are organized in a hierarchical prediction pattern comprising a plurality of temporal layers. The video encoding method further comprises adding to the encoded video stream a hidden delta frame for at least some of the key frames. Each hidden delta frame corresponds to a key frame, is based on same original video data as the corresponding key frame and is referring to a previous key frame in the encoded video stream. Also, a method of reducing a file size of the video stream encoded according to the video encoding method is disclosed.

Abstract: A method, device and computer program product for training neural networks being adapted to process image data and output a vector of values forming a feature vector for the processed image data. The training is performed using feature vectors from a reference neural network as ground truth. A system of devices for tracking an object using feature vectors outputted by neural networks running on the devices.

Abstract: A camera device includes an optics unit and a sensor unit releasably connectable to each other, and an electronic accessory releasably connectable to the optics unit by means of a threaded fitting associated with a rotation axis, wherein the optics unit comprises optics unit connectors, which in an assembled state of the camera device each is aligned and in contact with an associated electronic accessory connector of the electronic accessory thereby forming an electric connection between the electronic accessory and the sensor unit via the optics unit, wherein the optics unit connectors and the associated electronic accessory connectors form a first group consisting of at least one optics unit connector and associated electronic accessory connector arranged for power transfer and a second group consisting of at least one optics unit connector and associated electronic accessory connector arranged for signal transfer.

Abstract: A lens arrangement (200) for a camera device, the lens arrangement (200) comprising: a lens member (100) comprising a barrel (104) enclosing a lens unit (106) and extending along a longitudinal lens member axis (A), a lens holder (202) comprising a wall surrounding a cavity, wherein the lens member is at least partly inserted into the cavity, wherein the barrel (104) of the lens member (100) defines a channel (102) which extends inside a wall section of the barrel (104) of the lens member (100) in parallel with the longitudinal lens member axis (A) and which has a first end opening facing a field of view of the lens arrangement (200), and wherein the lens arrangement (200) comprises an emitter (110) arranged to emit electromagnetic radiation to an area located in the field of view of the lens arrangement (200) via the channel (102) and the first end opening.

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: A method, device, and computer-readable medium for synchronizing video are described. A wearable camera captures first video data. Also, the wearable camera timestamps the first video data and organizes the first video data using a hash table. The wearable camera transmits the first video data to a wireless hub via a wireless connection and captures second video data. When the wireless connection between the wearable camera and the wireless hub is unable to support full resolution video playback, the wearable camera down-converts the second video data, timestamps the second video data and organizes the second video data using the hash table. The wearable camera transmits the second video data to the wireless hub. Moreover, the first video data and the second video data are synchronizable according to gap synchronization based on one or more timestamps of the first video data and one or more timestamps of the second video data.

Abstract: An antenna (200) comprises an antenna body (212). The antenna body is integrally formed as a part of a PCB (210) and the antenna body is enclosed by metal. The antenna body may be enclosed by printed or plated metal on both top and bottom surfaces of the PCB and by edge plated metal along the circumference of the antenna body.