Abstract: A method for use in processing of image data stream is described. The method comprising: providing input data comprising at least one sequence of image data pieces indicative of a region of interest. Processing one or more image frames for detection of one or more foreground pixels regions. Collecting adjacent foreground pixels and determining one or more blobs associated with one or more suspected foreground objects in the region of interest Selecting one or more blobs and generating image portion indicative of one or more suspected foreground objects. And processing said one or more image portions for detection of one or more foreground objects and corresponding one or more object classes. For generating output data comprising class probability for one or more objects detected in one or more frame images of said image data stream.

Abstract: A method for geo-spatial registration of one of more cameras. The method comprises: providing cameras located for collecting image data of a region; providing operators carrying positioning devices, moving in selected paths in the region. The positioning devices generating position data sets of said selected paths. The operators carry selected visible markings. Marking data of the selected visible markings is used. Providing input data comprising the image data collected by the cameras and position data sets, and processing the data. The processing comprises using marking data for processing the image data and identifying appearance of markings in the image data. Generating image path data indicative of paths of the operators in the image data, and processing the path data in accordance position data set for determining correlation between path of the operators and the position data set. Using the correlation determining registration mapping for the cameras in the region.

Abstract: A method for use in processing of image data stream is described. The method comprising: providing input data comprising at least one sequence of image data pieces indicative of a region of interest. Processing one or more image frames for detection of one or more foreground pixels regions. Collecting adjacent foreground pixels and determining one or more blobs associated with one or more suspected foreground objects in the region of interest Selecting one or more blobs and generating image portion indicative of one or more suspected foreground objects. And processing said one or more image portions for detection of one or more foreground objects and corresponding one or more object classes. For generating output data comprising class probability for one or more objects detected in one or more frame images of said image data stream.

Abstract: A method for use in generating training data set and in training a learning utility is provided. The method comprising: providing a first set of labeled data and an ensemble of second learning utilities; training the ensemble of second utilities to label data, using the first set of labeled data; providing a second set of unlabeled data; labeling at least one portion of the second set of unlabeled data using the ensemble in order to generate corresponding first labels for said at least one portion of the second set to thereby yield a third set of data pieces corresponding to said at least one portion of the second set and labels thereof; and training the first utility using said third set of data pieces.

Abstract: A system and method for use in data analysis are provided. The system comprises a data processing utility configured to receive and process input data, comprising: plurality of neural network modules capable for operating in a training mode and in a data processing mode in accordance with the training; a network training utility configured for operating the neural network modules in the training mode utilizing selected set of training data pieces for sequentially training of the neural network modules in a cascade order to reduce an error value with respect to the selected set of the training data pieces for each successive neural network module in the cascade; and an abnormality detection utility configured for sequentially operating said neural network modules for processing input data, and classifying said input data as abnormal upon identifying that all the neural network modules provide error values being above corresponding abnormality detection thresholds.

Abstract: A method is provided, suitable for use in extraction of foreground objects from image stream. The method comprises: providing input image data of a region of interest, providing background model of said region of interest, and utilizing said background model for processing each image of the input image data. The processing comprises: determining a background gradient map for pixels in said background model and an image gradient map for pixels in the image; defining a predetermined number of one or more segments in said image and corresponding one or more segments in the background model; determining, for each image segment, an edge density factor is a first relation between the image and background gradient maps for said segment; and calculating foreground detection threshold based on said certain relation, thereby enabling use of said foreground detection threshold for classifying each pixel in the segment as being a foreground or background pixel.

Abstract: A system and method for use in data analysis are provided. The system comprises a data processing utility configured to receive and process input data, comprising: plurality of neural network modules capable for operating in a training mode and in a data processing mode in accordance with the training; a network training utility configured for operating the neural network modules in the training mode utilizing selected set of training data pieces for sequentially training of the neural network modules in a cascade order to reduce an error value with respect to the selected set of the training data pieces for each successive neural network module in the cascade; and an abnormality detection utility configured for sequentially operating said neural network modules for processing input data, and classifying said input data as abnormal upon identifying that all the neural network modules provide error values being above corresponding abnormality detection thresholds.

Abstract: A method is provided, suitable for use in extraction of foreground objects from image stream. The method comprises: providing input image data of a region of interest, providing background model of said region of interest, and utilizing said background model for processing each image of the input image data. The processing comprises: determining a background gradient map for pixels in said background model and an image gradient map for pixels in the image; defining a predetermined number of one or more segments in said image and corresponding one or more segments in the background model; determining, for each image segment, an edge density factor is a first relation between the image and background gradient maps for said segment; and calculating foreground detection threshold based on said certain relation, thereby enabling use of said foreground detection threshold for classifying each pixel in the segment as being a foreground or background pixel.