Abstract: A system is disclosed for facilitating free form dictation, including directed dictation and constrained recognition and/or structured transcription among users having heterogeneous native (legacy) protocols for generating, transcribing, and exchanging recognized and transcribed speech. The system includes at least one system transaction manager having a “system protocol,” to receive a verified, streamed speech information request from at least one authorized user employing a first legacy user protocol. The speech information request which includes spoken text and system commands is generated using a user interface capable of bi-directional communication with the system transaction manager and supporting dictation applications, including prompts to direct user dictation in response to user system protocol commands and systems transaction manager commands.

Abstract: Embodiments presented herein describe a method for processing streams of data of one or more networked computer systems. According to one embodiment of the present disclosure, an ordered stream of normalized vectors corresponding to information security data obtained from one or more sensors monitoring a computer network is received. A neuro-linguistic model of the information security data is generated by clustering the ordered stream of vectors and assigning a letter to each cluster, outputting an ordered sequence of letters based on a mapping of the ordered stream of normalized vectors to the clusters, building a dictionary of words from of the ordered output of letters, outputting an ordered stream of words based on the ordered output of letters, and generating a plurality of phrases based on the ordered output of words.

Abstract: Techniques are disclosed for creating a background model of a scene using both a pixel based approach and a context based approach. The combined approach provides an effective technique for segmenting scene foreground from background in frames of a video stream. Further, this approach can scale to process large numbers of camera feeds simultaneously, e.g., using parallel processing architectures, while still generating an accurate background model. Further, using both a pixel based approach and context based approach ensures that the video analytics system can effectively and efficiently respond to changes in a scene, without overly increasing computational complexity. In addition, techniques are disclosed for updating the background model, from frame-to-frame, by absorbing foreground pixels into the background model via an absorption window, and dynamically updating background/foreground thresholds.

Abstract: Techniques are disclosed for creating a background model of a scene using both a pixel based approach and a context based approach. The combined approach provides an effective technique for segmenting scene foreground from background in frames of a video stream. Further, this approach can scale to process large numbers of camera feeds simultaneously, e.g., using parallel processing architectures, while still generating an accurate background model. Further, using both a pixel based approach and context based approach ensures that the video analytics system can effectively and efficiently respond to changes in a scene, without overly increasing computational complexity. In addition, techniques are disclosed for updating the background model, from frame-to-frame, by absorbing foreground pixels into the background model via an absorption window, and dynamically updating background/foreground thresholds.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to detect and evaluate the presence of sea-surface oil on the water surrounding an offshore oil platform. The computer vision engine may be configured to segment image data into detected patches or blobs of surface oil (foreground) present in the field of view of an infrared camera (or cameras). A machine learning engine may evaluate the detected patches of surface oil to learn to distinguish between sea-surface oil incident to the operation of an offshore platform and the appearance of surface oil that should be investigated by platform personnel.

Abstract: Techniques are disclosed for detecting sudden illumination changes using radiance consistency within a spatial neighborhood. A background/foreground (BG/FG) component of a behavior recognition system may be configured to generate a background image depicting a scene background. Further, the (BG/FG) component may periodically evaluate a current video frame to determine whether a sudden illumination change has occurred. A sudden illumination change occurs when scene lighting changes dramatically from one frame to the next (or over a small number of frames).

Abstract: Techniques are disclosed for normalizing and publishing alerts using a behavioral recognition-based video surveillance system configured with an alert normalization module. Certain embodiments allow a user of the behavioral recognition system to provide the normalization module with a set of relative weights for alert types and a maximum publication value. Using these values, the normalization module evaluates an alert and determines whether its rareness value exceed a threshold. Upon determining that the alert exceeds the threshold, the module normalizes and publishes the alert.

Abstract: Techniques are disclosed for creating a background model of a scene using both a pixel based approach and a context based approach. The combined approach provides an effective technique for segmenting scene foreground from background in frames of a video stream. Further, this approach can scale to process large numbers of camera feeds simultaneously, e.g., using parallel processing architectures, while still generating an accurate background model. Further, using both a pixel based approach and context based approach ensures that the video analytics system can effectively and efficiently respond to changes in a scene, without overly increasing computational complexity. In addition, techniques are disclosed for updating the background model, from frame-to-frame, by absorbing foreground pixels into the background model via an absorption window, and dynamically updating background/foreground thresholds.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may provide image stabilization of a video stream obtained from a camera. An image stabilization module in the behavioral recognition system obtains a reference image from the video stream. The image stabilization module identifies alignment regions within the reference image based on the regions of the image that are dense with features. Upon determining that the tracked features of a current image is out of alignment with the reference image, the image stabilization module uses the most feature dense alignment region to estimate an affine transformation matrix to apply to the entire current image to warp the image into proper alignment.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to learn patterns of behavior consistent with a person loitering and generate alerts for same. Upon receiving information of a foreground object remaining in a scene over a threshold period of time, a loitering detection module evaluates the whether the object trajectory corresponds to a random walk. Upon determining that the trajectory does correspond, the loitering detection module generates a loitering alert.

Abstract: A system for facilitating free form dictation, including directed dictation and constrained recognition and/or structured transcription among users having heterogeneous protocols for generating, transcribing, and exchanging recognized and transcribed speech. The system includes a system transaction manager having a “system protocol,” to receive a speech information request from an authorized user. The speech information request is generated using a user interface capable of bi-directional communication with the system transaction manager and supporting dictation applications. A speech recognition and/or transcription engine (ASR), in communication with the system transaction manager, receives the speech information request, generates a transcribed response, and transmits the response to the system transaction manager. The system transaction manager routes the response to one or more of the users. In another embodiment, the system employs a virtual sound driver for streaming free form dictation to any ASR.

Abstract: Techniques are disclosed for analyzing a scene depicted in an input stream of video frames captured by a video camera. In one embodiment, e.g., a machine learning engine may include statistical engines for generating topological feature maps based on observations and a detection module for detecting feature anomalies. The statistical engines may include adaptive resonance theory (ART) networks which cluster observed position-feature characteristics. The statistical engines may further reinforce, decay, merge, and remove clusters. The detection module may calculate a rareness value relative to recurring observations and data in the ART networks. Further, the sensitivity of detection may be adjusted according to the relative importance of recently observed anomalies.

Abstract: Techniques are disclosed for detecting an out-of-focus camera in a video analytics system. In one embodiment, a preprocessor component performs a pyramid image decomposition on a video frame captured by a camera. The preprocessor further determines sharp edge areas, candidate blurry edge areas, and actual blurry edge areas, in each level of the pyramid image decomposition. Based on the sharp edge areas, the candidate blurry edge areas, and actual blurry edge areas, the preprocessor determines a sharpness value and a blurriness value which indicate the overall sharpness and blurriness of the video frame, respectively. Based on the sharpness value and the blurriness value, the preprocessor further determines whether the video frame is out-of-focus and whether to send the video frame to components of a computer vision engine and/or a machine learning engine.

Abstract: Techniques are disclosed for removing false-positive foreground pixels resulting from environmental illumination effects. The techniques include receiving a foreground image and a background model, and determining an approximated reflectance component of the foreground image based on the foreground image itself and a background model image which is used as a proxy for an illuminance component of the foreground image. Pixels of the foreground image having approximated reflectance values less than a threshold value may be classified as false-positive foreground pixels and removed from the foreground image. Further, the threshold value used may be adjusted based on various factors to account for, e.g., different illumination conditions indoors and outdoors.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to detect and evaluate the presence of sea-surface oil on the water surrounding an offshore oil platform. The computer vision engine may be configured to segment image data into detected patches or blobs of surface oil (foreground) present in the field of view of an infrared camera (or cameras). A machine learning engine may evaluate the detected patches of surface oil to learn to distinguish between sea-surface oil incident to the operation of an offshore platform and the appearance of surface oil that should be investigated by platform personnel.

Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.

Abstract: Techniques are disclosed for visually conveying classifications derived from pixel-level micro-features extracted from image data. The image data may include an input stream of video frames depicting one or more foreground objects. The classifications represent information learned by a video surveillance system. A request may be received to view a classification. A visual representation of the classification may be generated. A user interface may be configured to display the visual representation of the classification and to allow a user to view and/or modify properties associated with the classification.

Abstract: Techniques are disclosed for visually conveying a percept. The percept may represent information learned by a video surveillance system. A request may be received to view a percept for a specified scene. The percept may have been derived from data streams generated from a sequence of video frames depicting the specified scene captured by a video camera. A visual representation of the percept may be generated. A user interface may be configured to display the visual representation of the percept and to allow a user to view and/or modify metadata attributes with the percept. For example, the user may label a percept and set events matching the percept to always (or never) result in alert being generated for users of the video surveillance system.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may provide image stabilization of a video stream obtained from a camera. An image stabilization module in the behavioral recognition system obtains a reference image from the video stream. The image stabilization module identifies alignment regions within the reference image based on the regions of the image that are dense with features. Upon determining that the tracked features of a current image is out of alignment with the reference image, the image stabilization module uses the most feature dense alignment region to estimate an affine transformation matrix to apply to the entire current image to warp the image into proper alignment.

Abstract: Embodiments of the present invention provide a method and a system for mapping a scene depicted in an acquired stream of video frames that may be used by a machine-learning behavior-recognition system. A background image of the scene is segmented into plurality of regions representing various objects of the background image. Statistically similar regions may be merged and associated. The regions are analyzed to determine their z-depth order in relation to a video capturing device providing the stream of the video frames and other regions, using occlusions between the regions and data about foreground objects in the scene. An annotated map describing the identified regions and their properties is created and updated.