Abstract: A method for determining images plausible to have a false negative object detection comprises providing a group of historic trajectories, wherein each historic trajectory comprises a reference track that represents one or more historic tracks and comprises an object class of historic object detections that belong to the one or more historic tracks; performing tracking; performing object detection; for a determined track that does not match any determined object detection, comparing the determined track with reference tracks of historic trajectories for identifying a matching reference track; upon identifying a matching reference track, defining images of the determined track as being plausible to have a false negative object detection for the object class of the historic trajectory comprising the matching reference track; and upon not identifying a matching reference track, defining the determined track as a false positive track.

Abstract: A method and an image processing entity for applying a convolutional neural network to an image are disclosed. The image processing entity processes the image while using the convolutional kernel to render a feature map, whereby a second feature map size of the feature map is greater than a first feature map size of the feature maps with which the feature kernel was trained. Furthermore, the image processing entity repeatedly applies the feature kernel to the feature map in a stepwise manner, wherein the feature kernel was trained to identify the feature based on the feature maps of the first feature maps, wherein the feature kernel has the first feature map size.

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 and system for action recognition in a video sequence is disclosed. The system comprises a camera configured to capture the video sequence and a server configured to perform action recognition. The camera comprises an object identifier that identifies an object of interest in an object image frame of the video sequence; an action candidate recognizer configured to apply a first action recognition algorithm to the object image frame to detect presence of an action candidate; an video extractor configured to produce action image frames of an action video sequence by extracting video data pertaining to a plurality of image frames from the video sequence; and a network interface configured to transfer the action video sequence to the server. The server comprises an action verifier configured to apply a second action recognition algorithm to the action video sequence to verify or reject that the action candidate is an action.

Abstract: A method for finding one or more candidate digital images being likely candidates for depicting a specific object comprising: receiving an object digital image depicting the specific object; determining, using a classification subnet of a convolutional neural network, a class for the specific object depicted in the object digital image; selecting, based on the determined class for the specific object depicted in the object digital image, a feature vector generating subnet from a plurality of feature vector generating subnets; determining, by the selected feature vector generating subnet, a feature vector of the specific object depicted in the object digital image; locating one or more candidate digital images being likely candidates for depicting the specific object depicted in the object digital image by comparing the determined feature vector and feature vectors registered in a database, wherein each registered feature vector is associated with a digital image.

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 method and an image processing entity for applying a convolutional neural network to an image are disclosed. The image processing entity processes the image while using the convolutional kernel to render a feature map, whereby a second feature map size of the feature map is greater than a first feature map size of the feature maps with which the feature kernel was trained. Furthermore, the image processing entity repeatedly applies the feature kernel to the feature map in a stepwise manner, wherein the feature kernel was trained to identify the feature based on the feature maps of the first feature maps, wherein the feature kernel has the first feature map size.

Abstract: A method for finding one or more candidate digital images being likely candidates for depicting a specific object comprising: receiving an object digital image depicting the specific object; determining, using a classification subnet of a convolutional neural network, a class for the specific object depicted in the object digital image; selecting, based on the determined class for the specific object depicted in the object digital image, a feature vector generating subnet from a plurality of feature vector generating subnets; determining, by the selected feature vector generating subnet, a feature vector of the specific object depicted in the object digital image; locating one or more candidate digital images being likely candidates for depicting the specific object depicted in the object digital image by comparing the determined feature vector and feature vectors registered in a database, wherein each registered feature vector is associated with a digital image.

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 method and system for action recognition in a video sequence is disclosed. The system comprises a camera configured to capture the video sequence and a server configured to perform action recognition. The camera comprises an object identifier that identifies an object of interest in an object image frame of the video sequence; an action candidate recognizer configured to apply a first action recognition algorithm to the object image frame to detect presence of an action candidate; an video extractor configured to produce action image frames of an action video sequence by extracting video data pertaining to a plurality of image frames from the video sequence; and a network interface configured to transfer the action video sequence to the server. The server comprises an action verifier configured to apply a second action recognition algorithm to the action video sequence to verify or reject that the action candidate is an action.

Abstract: A camera and a method for selecting a focus region in a camera view have a plurality of focus regions that are defined in the camera view. A focus distance of the camera is repeatedly set to focus at different distances by setting a lens distance of the camera to different lens distance values. A focus value is determined for each focus region at the set lens distance value. A function for a plurality of focus regions is estimated based on a plurality of determined focus value and lens distance value pairs. A local maximum point of the function is calculated for each focus region for which a function has been estimated, where the local maximum point has a lens distance value. Focus regions are grouped, rated and selected based on the lens distance value of the local maximum point of the focus regions and spatial distances between the focus regions.

Abstract: A camera and a method for selecting a focus region in a camera view have a plurality of focus regions that are defined in the camera view. A focus distance of the camera is repeatedly set to focus at different distances by setting a lens distance of the camera to different lens distance values. A focus value is determined for each focus region at the set lens distance value. A function for a plurality of focus regions is estimated based on a plurality of determined focus value and lens distance value pairs. A local maximum point of the function is calculated for each focus region for which a function has been estimated, where the local maximum point has a lens distance value. Focus regions are grouped, rated and selected based on the lens distance value of the local maximum point of the focus regions and spatial distances between the focus regions.