Abstract: The present disclosure generally relates to a method for weighting of features in a feature vector of an object detected in a video stream capturing a scene, comprising: determining a feature vector comprising a set of features for a detected object in the video stream; acquiring a reference feature vector of a reference model of the scene; and assigning a weight to at least one feature of the determined feature vector, wherein the weight for a feature of the determined feature vector depends on a deviation measure indicative of a degree of deviation of the feature from a corresponding feature of the acquired reference feature vector of the reference model.

Abstract: A method for prioritization of video processing resources in a video processing and/or management system is provided. The method includes receiving video streams from multiple cameras and automatically ranking each camera as either a higher-priority or lower-priority camera. For higher-priority cameras, video content analysis is performed (as background processes), and the result is stored in storage. For lower-priority cameras, no such analysis is performed. The ranking is based on at least one of a historical usability, a historical cost, and a historical usability-to-cost ratio of a camera. A corresponding camera monitoring system, video processing and/or management system, computer program and computer program product are also provided.

Abstract: In a method for tracking an object in video-monitoring scenes, multiple feature vectors are extracted (722) and assembled (724) in point clouds, wherein a point cloud may be assembled for each tracklet, i.e. for each separate part of a track. In order to determine if different tracklets relate to the same or different objects the point clouds of each tracklet is compared (734). Based on the outcome of the comparison it is deduced if the first object and the second object may be considered to be the same object and, if so, the first object is associated (738) with the second object.

Abstract: A method of object re-identification in images of objects comprises providing a plurality of neural networks for object re-identification, wherein each of the plurality of neural networks is trained on image data with different sets of anatomical features, each set being represented by a reference vector; receiving a plurality of images of objects and an input vector representing anatomical features that are depicted in all of the plurality of images; comparing the input vector with the reference vectors for determining, according to a predefined condition, the most similar reference vector; and inputting image data of the plurality of objects to the neural network represented by the most similar reference vector for determining whether the plurality of objects have the same identity.

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 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: In a method for tracking an object in video-monitoring scenes, multiple feature vectors are extracted (722) and assembled (724) in point clouds, wherein a point cloud may be assembled for each tracklet, i.e. for each separate part of a track. In order to determine if different tracklets relate to the same or different objects the point clouds of each tracklet is compared (734). Based on the outcome of the comparison it is deduced if the first object and the second object may be considered to be the same object and, if so, the first object is associated (738) with the second object.

Abstract: Methods and apparatus, including computer program products, for creating a quality annotated training data set of images for training a quality estimating neural network. A set of images depicting a same object is received. The images in the set of images have varying image quality. A probe image whose quality is to be estimated is selected from the set of images. A gallery of images is selected from the set of images. The gallery of images does not include the probe image. The probe image is compared to each image in the gallery and a match score is generated for each image comparison. Based on the match scores, a quality value is determined for the probe image. The probe image and its associated quality value are added to a quality annotated training data set for the neural network.

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 and system for determining a position of a camera is disclosed. The method and system includes determining and registering geographical coordinates of a mobile device in the mobile device itself, presenting on a display of the mobile device a pattern representing the geographical coordinates of the mobile device, capturing by the camera an image of the display of the mobile device when presenting the geographical coordinates, translating in the camera the pattern in the captured image of the display of the mobile device into geographical coordinates, and determining in the camera the position of the camera based on the geographical coordinates translated from the pattern in the captured image.

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: Methods and apparatus, including computer program products, for creating a quality annotated training data set of images for training a quality estimating neural network. A set of images depicting a same object is received. The images in the set of images have varying image quality. A probe image whose quality is to be estimated is selected from the set of images. A gallery of images is selected from the set of images. The gallery of images does not include the probe image. The probe image is compared to each image in the gallery and a match score is generated for each image comparison. Based on the match scores, a quality value is determined for the probe image. The probe image and its associated quality value are added to a quality annotated training data set for the neural network.

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, 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 method and system are disclosed. The method may include receiving instructions in a hardware accelerator coupled to a computing device. The instructions may describe operations and data dependencies between the operations. The operations and the data dependencies may be predetermined. The method may include performing a splitter operation in the hardware accelerator, performing an operation in each of a plurality of branches, and performing a combiner operation in the hardware accelerator.

Abstract: A method and encoder for video encoding a sequence of frames is provided. The method comprises: receiving a sequence of frames depicting a moving object, predicting a movement of the moving object in the sequence of frames between a first time point and a second time point; defining, on basis of the predicted movement of the moving object, a region of interest (ROI) in the frames which covers the moving object during its entire predicted movement between the first time point and the second time point; and encoding a first frame, corresponding to the first time point, in the ROI and one or more intermediate frames, corresponding to time points being intermediate to the first and the second time point, in at least a subset of the ROI using a common encoding quality pattern defining which encoding quality to use in which portion of the ROI.

Abstract: A method and system are disclosed. The method may include receiving instructions in a hardware accelerator coupled to a computing device. The instructions may describe operations and data dependencies between the operations. The operations and the data dependencies may be predetermined. The method may include performing a splitter operation in the hardware accelerator, performing an operation in each of a plurality of branches, and performing a combiner operation in the hardware accelerator.

Abstract: A method of monitoring a scene by a camera (7) comprises marking a part (14) of the scene with light having a predefined spectral content and a spatial verification pattern. An analysis image is captured of the scene by a sensor sensitive to the predefined spectral content. The analysis image is segmented based on the predefined spectral content, to find a candidate image region. A spatial pattern is detected in the candidate image region, and a characteristic of the detected spatial pattern is compared to a corresponding characteristic of the spatial verification pattern. If the characteristics match, the candidate image region is identified as a verified image region corresponding to the marked part (14) of the scene. Image data representing the scene is obtained, and image data corresponding to the verified image region is processed in a first manner, and remaining image data is processed in a second manner.

Abstract: A method and system for determining a position of a camera is disclosed. The method and system includes determining and registering geographical coordinates of a mobile device in the mobile device itself, presenting on a display of the mobile device a pattern representing the geographical coordinates of the mobile device, capturing by the camera an image of the display of the mobile device when presenting the geographical coordinates, translating in the camera the pattern in the captured image of the display of the mobile device into geographical coordinates, and determining in the camera the position of the camera based on the geographical coordinates translated from the pattern in the captured image.

Abstract: A method and encoder for video encoding a sequence of frames is provided. The method comprises: receiving a sequence of frames depicting a moving object, predicting a movement of the moving object in the sequence of frames between a first time point and a second time point; defining, on basis of the predicted movement of the moving object, a region of interest (ROI) in the frames which covers the moving object during its entire predicted movement between the first time point and the second time point; and encoding a first frame, corresponding to the first time point, in the ROI and one or more intermediate frames, corresponding to time points being intermediate to the first and the second time point, in at least a subset of the ROI using a common encoding quality pattern defining which encoding quality to use in which portion of the ROI.