Abstract: An automated system and method for retaining images in a smart phone are disclosed. The system may then determine a no-reference quality score of the image using a PIQUE module. The PIQUE module utilizes block level features of the image to determine the no-reference quality score. The system may present the image and the no-reference quality score to the user and accept a feedback towards quality of the image. The system may utilize a supervised learning model for continually learning a user's perception of quality of the image, the no-reference quality score determined by the PIQUE module, and the user feedback. Based on the learning, the supervised learning model may adapt the no-reference quality score and successively the image may either be retained or isolated for deletion, based on the adapted quality score and a predefined threshold range.

Abstract: Method and system for tracking moving objects in a video with non-stationary background is provided. The method comprises estimation of non-stationary background and determining an approximate foreground for each image that learns the background model over time by incorporating various constraints on image pixels. Then, weights based upon spatio-temporal statistical properties of the extracted foreground blobs and blob edge overlap are used to identify and track with bounding boxes displayed for one or more true objects.

Abstract: An automated system and method for retaining images in a smart phone are disclosed. The system may then determine a no-reference quality score of the image using a PIQUE module. The PIQUE module utilizes block level features of the image to determine the no-reference quality score. The system may present the image and the no-reference quality score to the user and accept a feedback towards quality of the image. The system may utilize a supervised learning model for continually learning a user's perception of quality of the image, the no-reference quality score determined by the PIQUE module, and the user feedback. Based on the learning, the supervised learning model may adapt the no-reference quality score and successively the image may either be retained or isolated for deletion, based on the adapted quality score and a predefined threshold range.

Abstract: Method and system for tracking moving objects in a video with non-stationary background is provided. The method comprises estimation of non-stationary background and determining an approximate foreground for each image that learns the background model over time by incorporating various constraints on image pixels. Then, weights based upon spatio-temporal statistical properties of the extracted foreground blobs and blob edge overlap are used to identify and track with bounding boxes displayed for one or more true objects.

Abstract: A method for localizing and estimating a pose of a known object in a field of view of a vision system is described, and includes developing a processor-based model of the known object, capturing a bitmap image file including an image of the field of view including the known object, extracting features from the bitmap image file, matching the extracted features with features associated with the model of the known object, localizing an object in the bitmap image file based upon the extracted features, clustering the extracted features of the localized object, merging the clustered extracted features, detecting the known object in the field of view based upon a comparison of the merged clustered extracted features and the processor-based model of the known object, and estimating a pose of the detected known object in the field of view based upon the detecting of the known object.

Abstract: Described is a system for dynamic background estimation which utilizes Particle Swarm Optimization (PSO). The present invention comprises a system, method, and computer program product for accurate estimation of a background mask corresponding to a dynamically changing scene. The system is configured to construct a background template model of a scene, and then capture an image of a current view of the scene with a camera. Thereafter, the system generates an image-based template matching cost function as an optimization problem, where the objective is to identify and fit a corresponding subregion of the background template model to the current camera view. The cost function is optimized using a PSO search algorithm. Finally, the system is configured to generate the corresponding subregion of the background template model for display. The inherent efficiency of PSO makes this system conducive for use in applications requiring real-time background estimation.

Abstract: A method for localizing and estimating a pose of a known object in a field of view of a vision system is described, and includes developing a processor-based model of the known object, capturing a bitmap image file including an image of the field of view including the known object, extracting features from the bitmap image file, matching the extracted features with features associated with the model of the known object, localizing an object in the bitmap image file based upon the extracted features, clustering the extracted features of the localized object, merging the clustered extracted features, detecting the known object in the field of view based upon a comparison of the merged clustered extracted features and the processor-based model of the known object, and estimating a pose of the detected known object in the field of view based upon the detecting of the known object.

Abstract: The present invention relates to a classifier cascade object detection system. The system operates by inputting an image patch into parallel feature generation modules, each of the feature generation modules operable for extracting features from the image patch. The features are provided to an opportunistic classifier cascade, the opportunistic classifier cascade having a series of classifier stages. The opportunistic classifier cascade is executed by progressively evaluating, in each classifier in the classifier cascade, the features to produce a response, with each response progressively utilized by a decision function to generate a stage response for each classifier stage. If each stage response exceeds a stage threshold then the image patch is classified as a target object, and if the stage response from any of the decision functions does not exceed the stage threshold, then the image patch is classified as a non-target object.

Abstract: A method and system for video-content based retrieval is described. A query video depicting an activity is processed using interest point selection to find locations in the video that are relevant to that activity. A set of spatio-temporal descriptors such as self-similarity and 3-D SIFT are calculated within a local neighborhood of the set of interest points. An indexed video database containing videos similar to the query video is searched using the set of descriptors to obtain a set of candidate videos. The videos in the video database are indexed hierarchically using a vocabulary tree or other hierarchical indexing mechanism.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and determine an integrity score for each respective image frame. The processor may then isolate a foreground section from two or more of the views, determine a principle body axis for each respective foreground section, and determine a location point according to a weighted least squares function amongst the various principle body axes.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and determine an integrity score for each respective image frame. The processor may then isolate a foreground section from two or more of the views, determine a principle body axis for each respective foreground section, and determine a location point according to a weighted least squares function amongst the various principle body axes.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to identify the presence of a human within the workspace area from the plurality of image frames, generate a motion track of the human within the workspace area, generate an activity log of one or more activities performed by the human throughout the motion track, and compare the motion track and activity log to an activity template that defines a plurality of required actions. The processor then provides an alert if one or more actions within the activity template are not performed within the workspace area.

Abstract: A method of constructing a probabilistic representation of the location of an object within a workspace includes obtaining a plurality of 2D images of the workspace, with each respective 2D image being acquired from a camera disposed at a different location within the workspace. A foreground portion is identified within at least two of the plurality of 2D images, and each foreground portion is projected to each of a plurality of parallel spaced planes. An area is identified within each of the plurality of planes where a plurality of projected foreground portions overlap. These identified areas are combined to form a 3D bounding envelope of an object. This bounding envelope is a probabilistic representation of the location of the object within the workspace.

Abstract: Described is a method and system for embedding unsupervised learning into three critical processing stages of the spatio-temporal visual stream. The system first receives input video comprising input video pixels representing at least one action and at least one object having a location. Microactions are generated from the input image using a set of motion sensitive filters. A relationship between the input video pixels and the microactions is then learned, and a set of spatio-temporal concepts is learned from the microactions. The system then learns to acquire new knowledge from the spatio-temporal concepts using mental imagery processes. Finally, a visual output is presented to a user based on the learned set of spatio-temporal concepts and the new knowledge to aid the user in visually comprehending the at least one action in the input video.

Abstract: The present invention relates to an object detection and behavior recognition system using three-dimensional motion data. The system receives three-dimensional (3D) motion data of a scene from at least one sensor, such as a LIDAR sensor. An object is identified in the 3D motion data. Thereafter, an object track is extracted, the object track being indicative of object motion in the scene over time. Through Dynamic Time Warping (DTW) or other comparison techniques, the object track is compared to a database to identify the behavior of the object based on its object track.

Abstract: Described is a system for object and behavior recognition which utilizes a collection of modules which, when integrated, can automatically recognize, learn, and adapt to simple and complex visual behaviors. An object recognition module utilizes a cooperative swarm algorithm to classify an object in a domain. A graph-based object representation module is configured to use a graphical model to represent a spatial organization of the object within the domain. Additionally, a reasoning and recognition engine module consists of two sub-modules: a knowledge sub-module and a behavior recognition sub-module. The knowledge sub-module utilizes a Bayesian network, while the behavior recognition sub-module consists of layers of adaptive resonance theory clustering networks and a layer of a sustained temporal order recurrent temporal order network. The described invention has applications in video forensics, data mining, and intelligent video archiving.

Abstract: Described is a system for content recognition, search, and retrieval in visual data. The system is configured to perform operations of receiving visual data as an input, processing the visual data, and extracting distinct activity-agnostic content descriptors from the visual data at each level of a hierarchical content descriptor module. The resulting content descriptors are then indexed with a hierarchical content indexing module, wherein each level of the content indexing module comprises a distinct set of indexed content descriptors. The visual data, generated content descriptors, and indexed content descriptors are then stored in a storage module. Finally, based on a content-based query by a user, the storage module is searched, and visual data containing the content of interest is retrieved and presented to the user. A method and computer program product for content recognition, search, and retrieval in visual data are also described.

Abstract: Described is a system for registering a viewpoint of an imaging sensor with respect to a geospatial model or map. An image of a scene of a geospatial region comprising an object is received as input. The image of the scene is captured by a sensor having a current sensor state. Observation data related to the object's state is received, wherein the observation data comprises an object behavior of the object given the geospatial region. An estimate of the current sensor state is generated using a probability of an observation from the observation data given the current sensor state x. Finally, the image of the scene is registered with a geospatial model or map based on the estimate of the current sensor state.

Abstract: Described is a system and method for detecting elevated structures, such as bridges and overpasses, in point cloud data. A set of data from a three-dimensional point cloud of a landscape is received by the system. The set of data points comprises inlier data points and outlier data points. The inlier data points in the three-dimensional point cloud data are identified and combined into at least one segment. The segment is converted into an image comprising at least one image level. Each image level is processed with an edge detection algorithm to detect elevated edges. The elevated edges are vectorized to identify an elevated structure of interest in the landscape. The present invention is useful in applications that require three-dimensional sensing systems, such as autonomous navigation and surveillance applications.

Abstract: Described is a method for particle swarm optimization (PSO) utilizing a random walk process. A plurality of software agents is configured to operate as a cooperative swarm to locate an optimum of an objective function. The method described herein comprises two phases. In a first phase, the plurality of software agents randomly explores the multi-dimensional solution space by undergoing a Brownian motion style random walk process. In a second phase, the velocity and position vectors for each particle are updated probabilistically according to a PSO algorithm. By allowing the particles to undergo a random walk phase, the particles have an increased opportunity to explore their neighborhood, land in the neighborhood of a true optimum, and avoid prematurely converging on a sub-optimum. The present invention improves on what is currently known by increasing the success rate of the PSO algorithm in addition to reducing the required computation.