Axis Patente

A device, a non-transitory computer, and a method for adapting encoding of image frames of a video are provided. The image frames are arranged in a sequence of groups of pictures, GOPs, and each GOP contains an intra frame and a plurality of successive inter frames. A start is determined of a second GOP subsequent to a first GOP in the sequence of GOPs, and encoding is adapted of each of, or a subset of, a predetermined number of inter frames of the first GOP which immediately precede the determined start of the second GOP. The encoding is adapted such that the total size of the predetermined number of inter frames of the first GOP with adapting encoding is smaller than the size of the predetermined number of inter frames of the first GOP would have been without adapting encoding.

Methods and a device for updating a track of an object in relation to a current image frame are disclosed. A first track of an object in a sequence of image frames preceding the current image frame is determined using a first computer implemented tracker. The first tracker is updated in at least a first subset of image frames of the sequence of image frames based on an object detection from a computer implemented object detector using an object detection algorithm. The first track includes a respective estimated location of the object in each image frame of the first subset of image frames of the sequence of image frames. A location of the object in the current image frame is predicted using a motion model of the first tracker, and determined respective locations of detected motion areas in the current image frame are received from a computer implemented motion detector using a motion detection algorithm. Using the first tracker, and based on the predicted location of the object in the current image frame and the determined respective locations of the detected motion areas, it is determined that a detected motion area of the detected motion areas is associated with the object in the current image frame. The predicted location of the object in the current image frame is updated using the first tracker and based on the determined location of the detected motion area determined to be associated with the object in the current image frame. Thereby an estimated location of the object in the current image frame is determined.

A TDM MIMO FMCW radar comprises at least one row of physical receivers with a first spacing in a first direction, and further comprises a plurality of physical transmitters arranged with a second spacing in said first direction. To determine whether a peak in an angle spectrum corresponds to a direct reflection or a first-order multipath artefact, a full-array angle spectrum (901) based on all elements of a virtual array signal, and a single-subarray angle spectrum (902) based on one subarray are computed. If a peak in the full-array angle spectrum and a corresponding baseline peak in the single-subarray angle spectrum are co-located, it is concluded that the peak represents a direct reflection in the scene. Otherwise, if the peak and the baseline peak are not co-located, it is concluded that the peak represents a first-order multipath artefact.

There is provided a method, device, and system for tracking an object in a sequence of video frames by using a tracking filter. In the method, costs are assigned for associating each object detection in a received set of object detections to the tracked object. The cost assigned to an object detection is a measure of deviation between a motion associated with the object detection and both of a first motion of the object estimated by the tracking filter and a second motion of the object indicated by motion vectors from a video encoder which encodes the sequence of video frames.

A method is disclosed for adapting a stream of image frames for display. A first stream of image frames acquired by a pan tilt zoom, PTZ, camera arranged to monitor a scene are obtained, a first criterion related to pan or tilt motion of the PTZ camera is evaluated, and a second stream of image frames generated based on a background model of the monitored scene is obtained. On condition that the first criterion is not met, image frames from the first stream of image frames are injected in the stream of image frames for display. On condition that the first criterion is met, image frames from the second stream of image frames are injected in the stream of image frames for display.

A dome camera arrangement comprising one or more camera heads, arranged in a transparent dome is disclosed. Each camera head comprises an optics unit (118), a panning device, for moving the camera head in a panning movement, and a tilting device (110) for moving the camera head (104) in a tilting movement. The tilting device (110) has a pivot portion (116) and a cradle portion (112). The camera head further has a roll device (124) for rotating the optics unit (118) in a roll movement. A compensation lens (122) is arranged in a compensation lens fitting (120) in front of the optics unit, and the compensation lens fitting is connected to the panning device and the tilting device (110), such that the compensation lens (122) will move with the camera head in panning movement and tilting movement. However, the compensation lens fitting is disconnected from the same features such that the compensation lens (122) will not follow the optics unit (118) in roll movement, thus enabling an adequate optical compensation by means of the compensation lens.

This disclosure relates to a method (500), software and device for encoding a video sequence into an encoded video stream having a target resolution, comprising: encoding (S502) a first image frame of the video sequence using the base layer to encode the image frame in a first resolution being lower than the target resolution, and using the enhancement layer to encode at least a portion of image data of the first image frame to reach the target resolution; detecting (S504) an encoding scenario from a set of one or more predefined encoding scenarios; and encoding (S506) a second image frame of the video sequence using the base layer to encode the second image frame in the target resolution, and indicating in the encoded video stream that the second image frame is decodable in the target resolution using only the base layer.

A method and a device for stitching images and blending pixel data of respective images from each of at least three image sensors during a time period when an object passes through a combined view of the at least three image sensors. The combined view is a combination of a respective view of each of the at least three image sensors, and comprises a first region in which at least three of the views of the at least three image sensors overlap and through which the track passes. The method comprises obtaining a respective sequence of images from each of the at least three image sensors, detecting the object in the combined view, determining a location of the detected object, predicting a track of the object, identifying a minimal view set covering all portions of the track, and stitching and blending images captured at a same point in time from each of the sequences of images to a combined image corresponding to the combined view. The stitching and blending is such that, in a major proportion of a first portion of the combined image corresponding to the first region of the combined view, blending is performed using pixel data only from respective images from at most two image sensors and only from image sensors having views comprised in the minimal view set.

The present invention generally relates to a computer-implemented method for enabling video recreation, comprising: acquiring (S102), by a camera control unit (112), a video stream (300) comprising a set of image data packages (302, 303) each comprising coded image frames; transmitting (S104), by the control unit (112), at least a portion of the video stream to a client (116) across a communication network (114), receiving (S106), by the control unit (112), an acknowledgement message (306) for each image data package (303) that was successfully received by the client (116), storing (S108), in a digital memory (108) accessible to the control unit (112), the image data packages (303) for which an acknowledgement message (306) is received, and indications of successful receipt (308) at the client (116) of the corresponding image data packages (303).

A tracked state of a tracked object in a sequence of images is determined. A region of interest, ROI, is determined (210) in a current image. Based on at least one previous image from the sequence of images, motion information data of the current image is aggregated (220) to obtain an estimated current motion of the ROI. A predicted current state of the ROI is predicted, based on a previous state of the ROI, a plurality of object tracking models, and the estimated current motion of the ROI. The predicting (230) comprises selecting (232) at least one of the plurality of object tracking models to be used for predicting the predicted current state. The predicted current state of the ROI is associated (240) with the observed current state of the ROI to determine the tracked state of the tracked object.

This disclosure relates to methods 900, software, devices and systems for encoding an image frame in a video stream, such that a decoded version of the encoded image frame is provided with a first masked region. A block-aligned mask is applied S906 to the image frame being encoded and a pre-generated encoded image frame is used to transform the block-aligned masked region during decoding. The pre-generated encoded image frame contains motion vectors but no residual data, allowing for efficient transformation of a block-aligned masked region into the first masked region having an edge that cuts through coding blocks.

In an aspect, there is provided a method for performing digital image stabilization (DIS) on a sequence of video frames captured by an image capturing device, comprising: obtaining a sequence of motion values sampled from a motion signal while capturing the sequence of video frames such that each video frame is associated with a respective motion value; obtaining a sequence of position values sampled from a position signal while capturing the sequence of video frames such that each video frame is associated with a respective position value; determining, for each respective video frame, a residual motion value to obtain a sequence of residual motion values for the sequence of video frames; and performing DIS on the sequence of video frames, comprising: detecting an image feature in a reference video frame of the sequence of video frames; tracking the image feature in each further video frame of the sequence of video frames; determining frame motion data based on a displacement for the image feature in each further video frame in the sequence of video frames; and generating a stabilized sequence of video frames based on the frame motion data; wherein a size of a tracking window for tracking the image feature in each further video frame is set based on the sequence of residual motion values.

A computer-implemented method (1000) for tampering detection of a microphone device (100), the microphone device (100) comprising a microphone (110) arranged in a cavity (120) open to surroundings of the microphone device (110) via a microphone hole (122), the method (1000) comprising: receiving (1100) an audio signal (112) from the microphone (110); sampling (1200) the audio signal (112) for a low frequency band; detecting (1300) an event (140) comprising an exponentially decreasing absolute amplitude of the sampled audio signal (130) during a time period (P) of at least one second; and when detecting the event (140), outputting (1400) a tampering detection signal.

In an aspect there is provided a method for controlling an image stabilization, system of an image capturing device, wherein the IS system comprises an optical image stabilization, OIS, system compensating for vibrational movement of the image capturing device based on a motion signal output by a motion sensor of the image capturing device, and wherein the OIS system has at least a first control parameter with a value being adjustable to adapt a responsiveness of the OIS system to vibrational movement, the value being adjustable between a first value causing a lower responsiveness of the OIS system, and a second value causing a higher responsiveness of the OIS system; the method comprising, while the OIS system is in an active state and performs OIS; determining a signal-to-noise estimate for the motion signal; and determining the value of the first control parameter based on the signal-to-noise estimate, comprising setting the first control parameter to the first value responsive to determining that the signal-to-noise estimate is in a lower range, and to the second value responsive to determining that the signal-to-noise estimate is in an upper range.

This disclosure relates to methods 400, software, devices and systems for video scrubbing that enables a client device to retrieve images for scrubbing based on a user-requested time along a video timeline of a video stored in a server. The client device checks S404 if a cached image meets specified conditions, including a timestamp within a precision margin around the requested time. The precision margin scales with the timeline length, providing a smaller margin for shorter timelines and a larger margin for longer timelines. If a relevant cached image is found, it is retrieved S416; if not, an image with a highest relevance score within the precision margin is fetched S418 from the server and stored in memory.

In an aspect there is provided a method for controlling an OIS system of an image capturing device, the method comprising: obtaining a first and a second time-series of samples derived from a motion signal of a motion sensor of the image capturing device, wherein the motion signal indicates a motion of the image capturing device, and wherein the first time-series spans a longer time period of the motion signal than the second time-series; determining a current dominant frequency for the motion signal based on a frequency analysis of the first time-series; and determining a setpoint for the OIS system by: fitting to the second time-series a model function based on a sine and/or cosine function and the current dominant frequency, extrapolating the fitted model function past a last sample of the second time-series to predict a successive sample, and determining the setpoint based on the predicted successive sample.

Provided is a device (100), and method as implemented by the device, for configuring a visual appearance of output images (123) from a camera (120) capturing a scene. The device is configured to obtain a first image (121) depicting the scene captured by the camera; obtain a second image (122) depicting the scene (as modified e.g. by a user using an image manipulation/creation software 140); extract a set of one or more visual differences between the first and second images, and determine, based on the extracted set of visual differences, one or more postprocessing operations, such that a third image (123) depicting the scene captured by the camera and subjected to the one or more image postprocessing operations is more visually equal (or similar) to the second image than the first image. A corresponding system, computer program and computer program product are also provided.

A method (300) for streaming live coded video to one or more clients is disclosed. The method comprises: detecting (S302) a plurality of video stream requests; obtaining (S304) maximum bitrate values that return video streams are allowed to have; calculating (S306) requested quality of experience, QoE, values; determining (S308) a number of return video streams being lower than the plurality of video stream requests, and having bitrates such that each of the video stream requests can be matched with a return video stream, wherein the bitrates of the return video streams are determined such that a cumulative difference between the QoE value of each video stream request and a calculated return QoE of a matching return video stream is minimized; obtaining (S312) the return video streams; and streaming (S314) the return video streams. A streaming controller (20) for controlling streaming of live coded video is also disclosed.

The present disclosure relates to a computer-implemented method (100) for segmentation and/or object detection in images captured by a camera (201) having zoom capability, the method comprising: obtaining one or more images from the camera (201) (101); obtaining a zoom factor of the camera (201), wherein the zoom factor represents a measure of a current zoom level applied by the camera (201) when capturing the one or more images (102); selecting, based on the zoom factor, one neural network (204) from a plurality of neural networks (204) configured to segment the one or more images and/or detect one or more objects (206) in the one or more images, wherein the plurality of neural networks (204) are configured to operate at different image resolutions (103), wherein a higher zoom factor corresponds to selecting a neural network (204) configured to operate at a lower image resolution, and a lower zoom factor corresponds to selecting a neural network (204) configured to operate at a higher image resolution; down-scaling the one or more images to the image resolution required by the selected neural network (204) (104); applying the selected neural network (204) to segment the down-scaled one or more images and/or detect the one or more objects (206) in the down-scaled one or more images (105). The disclosure further relates to a corresponding camera system (200).

The present relates to a computer-implemented method to adjust a process noise of an object tracker in a camera (100) configured to monitor a scene (200) including moving objects (102a-c), the object tracker (107) uses a motion model (134) associated with process noise (132), the method comprising: determining (S100), using the object tracker, object tracks (136, 202a-c, 204a-b, 301) of moving objects travelling along a path in the scene for a time period using a level of process noise, evaluating (S105) at least one spatial parameter of the determined object tracks in relation to a predetermined criterion (140), repeating the steps of determining (S100) object tracks and evaluating (S105) at least one spatial parameter for object tracks during subsequent time periods using increased process noise for each iteration until the predetermined criterion is fulfilled or a maximum process noise limit is reached, and storing (S110) data (144) indicating the final process noise.

A method (500) for intra refresh encoding of a video stream is provided. The method includes encoding (S510) the video stream using a first intra refresh pattern; determining (S520) that a time-variation of bits-per-frame for encoding the video stream using a second intra refresh pattern different from the first intra refresh pattern is lower than that for encoding the video stream using the first intra refresh pattern, and switching (S530) to encoding the video stream using the second intra refresh pattern. A corresponding device configured to perform the method is also provided, as well as a corresponding computer program and computer program product.

A method for indicating clock drift of an internal clock comprised in a sensor device, the method comprising: capturing S302, by the sensor device, first data frame; associating S304, by the sensor device, the first data frame with a first point in time indicating a point in time of the internal clock when the first data frame being captured; receiving S306, by the sensor device via a network protocol for clock synchronization, time synchronisation data; determining S308, by the sensor device using the time synchronisation data, a reference point in time indicating a point in time of a reference clock when the first data frame being captured; determining S310, by the sensor device, an offset between the first point in time and the reference point in time; and upon the offset exceeding a threshold offset, associating S312, by the sensor device, the first data frame with data indicating the offset.

There is provided a method for determining occupied positions in a space. The method starts by receiving detections of object movement from a radar monitoring the space. Each detection is associated with a position in the space and a time point when the detection was made. The method accumulates detections that have a time point within a first time period of predefined duration, and identifies a set of clusters of detections in the space by analyzing similarity in position of the accumulated detections. Any cluster whose detections are temporally distributed within a proportion of the first time period which is below a predefined proportion threshold are then removed from the set of clusters. The positions in the space that correspond to the set of clusters are determined to be occupied during the first time period.

The present disclosure relates to anchor-based object detection systems and methods that identify potential false positive detections among three detection boxes in a same image frame. Each detection box has a predicted IoU score representing confidence that it captures an object. The system determines S502 overlap of a second box with a first and third box, where the second is positioned between them. It identifies S504 the second box as a potential false positive if it determines S506 the IoU score of the second box is below a set threshold and if corresponding reference points within each box is determined S508 to be substantially aligned, with the second box's reference point close to an alignment line defined by the first and third boxes.

The present disclosure relates to an image-capturing system (100) comprising: an image sensor (101) configured to capture images of a scene at a periodic rate; an illumination source (102) for illuminating the scene; measurement and control circuitry (108) configured to: continuously measure a current (200) to/from the image sensor (101); continuously detect periodically alternating high and low levels (202; 203) of the measured current (200); and control the illumination source (102) to alternate between an on state and an off state with an illumination frequency equal to a switching frequency of the detected periodically alternating high and low levels (202; 203) of the measured current (200) such that the illumination source (102) is in the on state during exposure of the image sensor (101). The disclosure further relates to a method (300) of controlling an illumination source for illuminating a scene during image sensor exposures.

There is provided techniques for updating background layers during encoding of scene, performed by an image processing device. The scene is encoded based on classifying objects depicted in the scene as either foreground or background. The background is divided into ordered background layers where each background layer is associated with a respective depth model. The method comprises detecting (S102) a change in an image portion of one background layer. The method comprises calculating (S104) a difference between the image portion and a corresponding image portion of a background layer ordered behind said one background layer. The method comprises selecting (S106a), when the difference is smaller than a threshold, said background layer ordered behind said one background layer to represent the image portion.

A shock absorber (100) comprising: a housing (110) having an inner wall surface (112) defining a cavity (114) extending along a longitudinal axis (115) and comprising an open top end (116) and an opposing bottom end (118), the inner wall surface (112) being provided with a recess (113); a body (120) comprising a portion (122) housed in the cavity (114); a shock absorbing element (130) arranged in the cavity (114) between the portion (122) of the body (120) and the bottom end (118) of the cavity (114); and a biasing element (124) and a locking element (126) arranged in the portion (122) of the body (120), wherein the biasing element (124) is configured to press the locking element (126) with a biasing force against the inner wall surface (112) of the housing (110), wherein the portion (122) of the body (120) is displaceable against counteraction of the shock absorbing element (130), along the longitudinal axis (115) of the cavity (114), from a first position, in which the locking element (126) extends into the recess (113) of the inner wall surface (112), to a second position located between the first position and the bottom end (118) of the housing (110), and wherein the shock absorbing element (130) is configured to counteract displacement of the portion (122) of the body (120) from the first position to the second position.

A screw joint arrangement comprising: a first member (100) provided with at least one screw receiving portion (101); a second member (200) provided with a bore (201) comprising a first threaded bore portion (202), a second threaded bore portion (203), and a non-threaded bore portion (204) separating the first threaded bore portion (202) and the second threaded bore portion (203); and a screw (300) comprising a screw head (301) and a screw shaft (302) provided with a threaded screw portion (303). The first member (100) is arranged next to the second member (200) with the first threaded bore portion (202) being proximal to the first member (100). The screw joint arrangement is settable, by rotation of the screw (300), between a first state in which the second member (200) is fixed relative to the first member (100), and a second state in which the second member (200) is movable relative to the first member (100). In said first state, one of the at least one screw receiving portion (101) and the bore (201) are aligned, and the screw shaft (302) extends through said one of the at least one screw receiving portion (101) and into the bore (201) with the threaded screw portion (303) engaging the second threaded bore portion (203) such that the first member (100) is clamped between the screw head (301) and the second member (200). In said second state, the screw shaft (302) extends through the first threaded bore portion (202) and the threaded screw portion (303) (302) is positioned in the non-threaded bore portion (204) of the bore (201).

A method and a device for estimating available transmission bandwidth on a network connection over which data files are to be transmitted within a predetermined transmission time. A data file size is determined for a first data file to be transmitted over the network connection and a lowest average bitrate required to transmit the first data file within the predetermined transmission time is determined by dividing the data file size by the predetermined transmission time. A transmission time of the first data file is divided into one or more first time intervals and one or more second time intervals, wherein each of the one or more first time intervals is followed by a second time interval of the one or more second time intervals unless the first time interval is a last time interval. Data of the first data file are transmitted over the network connection during the one or more first time intervals at a bitrate higher than the determined lowest average bitrate. Remaining data of the first data file are transmitted over the network connection during the one or more second time intervals at a bitrate lower than the bitrate during the one or more first time intervals. The bitrate during the one or more second time intervals is such that a resulting average bitrate of the transmission of the first data file is equal to or higher than the determined lowest average bitrate but lower than a bitrate threshold. An available transmission bandwidth over the network connection is estimated based on feedback on the transmission of data of the first data file over the network connection during the one or more first time intervals at the bitrate higher than the determined lowest average bitrate.

A method (100) of detecting objects in radar data, comprising:obtaining (no) radar data from a radar measurement of a scene, wherein the radar data includes intensities pertaining to a plurality of points in a range-Doppler plane or a range-angle plane;parametrizing (112) a one-dimensional subset of the range-Doppler plane or the range-angle plane, as the case may be, by one parameter;extracting (113), from the radar data pertaining to the subset, intensities which are below a preconfigured clutter threshold;regularizing (114) the extracted intensities as a function of the parameter to obtain a signal mask;deriving (115) a detection threshold from the signal mask; andperforming object detection (116), wherein the detection threshold is applied to the radar data pertaining to the subset.

There is provided techniques for encoding pixel blocks (220a) of a video sequence (200). A method is performed by an image processing device (110, 900). The method comprises obtaining (S102) video sequence (200) composed of a sequence of image frames (210a, 210b). The method for each of the image frames (210a, 210b) further comprises calculating (S104) statistics per pixel block (220a). The method for each of the image frames (210a, 210b) further comprises categorizing (S106) the pixel block (220a) into three different motion categories based on their statistics. The method for each of the image frames (210a, 210b) further comprises encoding (S108) each of the pixel blocks (220a) with a compression rate that depends on which motion category each of the pixel blocks (220a) belongs.

In an aspect there is provided a method for controlling an image processing stage for processing image data captured by a surveillance camera having a field-of-view greater than 180 degrees and being mounted in a downward looking configuration to monitor a scene, the method comprising: obtaining image data captured by the surveillance camera, wherein the image data includes a first set of pixels depicting a central scene portion located below a horizon in the scene, and a second set of pixels depicting a peripheral scene portion located above the horizon, performing a ceiling detection procedure comprising analyzing pixels of the second set of pixels, to determine whether to configure the image processing stage to operate in accordance with a ceiling operational mode, and in response to determining to configure the image processing stage to operate in accordance with the ceiling operational mode, configuring the image processing stage to operate in accordance with the ceiling operational mode while processing subsequently captured image data, wherein the subsequently captured image data comprises a first set of pixels depicting the central scene portion and a second set of pixels depicting the peripheral scene portion, wherein the image processing stage comprises at least one image processing operation, and wherein the ceiling operational mode includes applying the at least one image processing operation to the first set of pixels of the captured image data but not to the second set of pixels of the captured image data.

An apparatus and a method for tracking a temporarily occluded object in image frames of objects and associating detected instances into tracks. An active first track of a first object and an active second track of a second object are identified, which objects are moving together. Upon determination that the first track, but not the second track, has become inactive connecting it to the second track. Thereafter, a detected object instance is associated with an inactive track when a similarity score between the detected instance and the inactive track fulfills a similarity requirement. The requirement is less strict when the instance is spatially proximate to the second track and when the detected instance is compared to the inactive first track connected to the second track as compared to when the detected instance is compared to an unconnected inactive track.

A method (200) for object detection (post-processing) in an image is provided, and includes obtaining (S210), from one or more artificial neural network (ANN) entities trained to localize objects and one or more subparts of such objects in images, a plurality of object proposals and one or more subpart proposals in a same image; performing (S220) a first filtering of the object proposals; matching (S230) subpart proposals with corresponding object proposals remaining after the first filtering, and performing (S240) a second filtering of the unmatched object proposals remaining after the first filtering. The first and second filtering are based on classification confidence scores and proximity scores of the object proposals, and the second filtering is statistically more aggressive than the first filtering. A corresponding device, computer program and computer program product are also provided.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …