Axis Ab

Gasoptics Sweden Ab

Björn Ardö

Song Yuan

Fredrik Pihl

Igor Gurovski

Viktor Edpalm

Johan Nystrom

Stefan Lundberg

Markus Skans

Jonas Sandsten

Johan Nyström

Sebastian Hultqvist

Toivo Henningsson

Anton Jakobsson

Henning Gredegård

Niklas Lindman

Dawid Studzinski

Timo Sachse

Tomas Christiansson

Stefan Sandström

Johan David Philip Nystrom

Johan NYSTRÖM

The present disclosure relates to a method performed by a monitoring camera () for handling a first and a second video stream (). The monitoring camera () obtains a first video stream () from a first image sensor () and a second video stream () from a second image sensor (). A field of view of the first video stream () partly overlaps with the second video stream (). The monitoring camera () identifies a moving object () in the overlap area (). The monitoring camera () divides the moving object () into a plurality of sub objects (). The monitoring camera () performs a hard handover of the sub objects () from the first to the second video stream () when the sub object () is within the overlap area () and when a point of the sub object () passes a border ().

Method and monitoring camera for handling video streams

A method includes aligning a first image frame of a first stream of images from a first image sensor and a further first image frame of a second stream of images from a second image sensor according to a first alignment, aligning a second image frame of the first stream of images and a further second image frame of the second stream of images according to the first alignment, obtaining a first stitched image frame by blending the aligned first image frame and further first image frame in a first blending area according to a first blending function, obtaining second stitched image frame by blending the aligned second image frame and the further second image frame in a second blending area according to a second blending function, and evaluating the first alignment from a difference pattern calculated from pixel values of the first stitched frame and the second stitched frame.

Method and image-processing device for evaluating an alignment of stitched images

A method (), a device () and a system () 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 (S), 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 (S) to form a combined output, and the combined output is processed (S) 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.

Method, device, and system for processing image data representing a scene for extracting features

There is provided techniques for setting frame rates of a camera. The camera comprises a plurality of image sensors arranged to capture images to be stitched into a panorama image of a scene. Information of a respective angle between the optical axis of each of the plurality of image sensors and a direction along which a straight path structure, to be monitored by the camera, extends through the scene is obtained. The plurality of image sensors are divided into at least two groups as a function of the angles. All the angles of the image sensors within each of the at least two groups are part of its own continuous angle interval. One frame rate is set per each of the at least two groups. The frame rate decreases from the group with highest continuous angle interval towards the group with lowest continuous angle interval.

Differential frame rate settings

A method for determining whether or not a transparent protective cover of a video camera comprising a lens-based optical imaging system is partly covered by a foreign object is disclosed. The method comprises:

Method and image-processing device for detecting foreign objects on a transparent protective cover of a video camera

A method and device for encoding a plurality of image frames uses two separate encoders, where each image frame is divided into two portions to each be encoded by one of the two encoders, where the image frame is divided to minimize motion across the boundary between the two portions, such that the two encoders may operate independently of each other without a substantial bit rate penalty or reduced encoding quality.

Method and device for encoding a sequence of image frames using a first and a second encoder

A method and an apparatus for forming a video stream based on images of a scene captured by a camera. The method comprises: encoding image frames based on images captured by the camera, forming an encoded portion; determining a length of motion for a sample image frame, the length of motion being indicative of the amount of relative motion between the camera and the scene in the sample image frame relative a temporally preceding image frame; setting a motion length threshold based on a motion vector search range of the encoder; comparing the determined length of motion with the set motion length threshold; based on the outcome of the comparison, adjusting a chosen temporal frame distance of at least an adjustment portion (P) of the video stream, wherein the adjustment portion is comprised in the encoded portion or in a temporally later encoded portion.

Method and image processing unit for forming a video stream

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.

Image capturing device, a method and a computer program product for forming an encoded image

A method and device for encoding a plurality of image frames uses two separate encoders, where each image frame is divided into two portions to each be encoded by one of the two encoders, where a boundary between the two portions is offset between the image frames according to a size of a search window of one of the encoders. Consequently, copying of pixel data for the purpose of motion search is only required in one direction between a first and a second encoder.

Method and device for encoding a plurality of image frames

The present teachings relate to the field of video encoding. In particular, the present teachings relate to a method, device, and system for encoding a sequence of frames wherein a motion level of image data of an initial frame in the sequence of frames is determined to be below a motion level threshold. The encoding method described herein may reduce the bit rate for the encoded sequence of frames, while avoiding that the encoded video stream looks unnatural or frozen when decoded and displayed.

Method, device and system for method of encoding a sequence of frames in a video stream

The present invention relates to the field of image encoding. In particular, it relates to methods and devices where the concept of auxiliary frames may be employed to reduce or remove the need of copying data, for reference encoding purposes, between encoders which encode different parts of an image frame. This purpose is achieved by spatially modifying (S) original image data before encoding (S, S) it using the encoders, and using (S) the encoded image data as image data of an auxiliary frame. The auxiliary frame is referenced by an inter frame comprising motion vectors corresponding to a restoration of the auxiliary frame image data back to a spatial arrangement of the original image data.

Methods and devices for encoding a video stream using a first and a second encoder

Methods and devices for protecting personal privacy in captured image data by controlling privacy masking of an image, where the degree of blurring to be applied to a privacy area of the image depends on a threshold distance from the image capturing device, and the spatial resolution of content of the scene at this distance in the image.

Method, device and system for a degree of blurring to be applied to image data in a privacy area of an image

A method and system for monitoring video data based on gaze is disclosed. The method may include receiving a video stream generated by a camera and presenting the received video stream on a display. The method may further include receiving a notification signal triggered by an event and determining that the video stream is associated with the notification signal. The method may further include detecting a gaze point of an operator viewing the display and determining at least one parameter associated with the gaze point. The method may include controlling a state of an alarm associated with the notification signal based upon the at least one parameter associated with the gaze point.

Alarm masking based on gaze in video management system

A method and apparatus are disclosed. The method may include determining a current zoom value of a camera and determining a first modulation transfer function of a transparent dome of the camera. The method may include applying a first low-pass filter to an image captured by the camera based on the current zoom value and the first modulation transfer function of the transparent dome.

Image noise reduction based on a modulation transfer function of a camera dome

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.

Growing community of inventors

Lund, Sweden

Björn Ardö