Abstract: Systems and methods are described herein that provide a three-tier intelligent video surveillance management system. An example of a system described herein includes a gateway configured to obtain video content and metadata relating to the video content from a plurality of network devices, a metadata processing module communicatively coupled to the gateway and configured to filter the metadata according to one or more criteria to obtain a filtered set of metadata, a video processing module communicatively coupled to the gateway and the metadata processing module and configured to isolate video portions, of video the content, associated with respective first portions of the filtered set of metadata, and a cloud services interface communicatively coupled to the gateway, the metadata processing module and the video processing module and configured to provide at least some of the filtered set of metadata or the isolated video portions to a cloud computing service.

Abstract: Embodiments of the disclosure provide for systems and methods for creating metadata associated with a video data. The metadata can include data about objects viewed within a video scene and/or events that occur within the video scene. Some embodiments allow users to search for specific objects and/or events by searching the recorded metadata. In some embodiments, metadata is created by receiving a video frame and developing a background model for the video frame. Foreground object(s) can then be identified in the video frame using the background model. Once these objects are identified they can be classified and/or an event associated with the foreground object may be detected. The event and the classification of the foreground object can then be recorded as metadata.

Abstract: A method of video coding includes receiving a video image having a plurality of pixels, selecting a plurality of Gaussian models for each pixel, classifying each pixel as a background or foreground pixel, determining if an object is always moving locally by detecting if an object is always moving within a predetermined distance and changing the direction of moving frequently for a second predetermined period of time, removing an object from classification as an object and ignoring motion of the object if the object is always moving locally, marking the area that the object moves within as a noisy area on a noise mask buffer, updating background models based on motion detection and noise filtering, updating current and evolving background images, and coding the current background image, background update blocks and objects for transmission.

Abstract: An image display method includes: receiving, from a single camera, first and second image information for first and second captured images captured from different perspectives, the first image information having a first data density; selecting a portion of the first captured image for display with a higher level of detail than other portions of the first captured image, the selected portion corresponding to a first area of the first captured image; displaying the selected portion in a first displayed image, using a second data density relative to the selected portion of the first captured image; and displaying another portion of the first captured image, in a second displayed image, using a third data density; where the another portion of the first captured image is other than the selected portion of the first captured image; and where the third data density is lower than the second data density.

Abstract: Techniques are described for tracking moving objects using a plurality of security cameras. Multiple cameras may capture frames that contain images of a moving object. These images may be processed by the cameras to create metadata associated with the images of the objects. Frames of each camera's video feed and metadata may be transmitted to a host computer system. The host computer system may use the metadata received from each camera to determine whether the moving objects imaged by the cameras represent the same moving object. Based upon properties of the images of the objects described in the metadata received from each camera, the host computer system may select a preferable video feed containing images of the moving object for display to a user.

Abstract: An image capture system includes: an image capture unit configured to capture a first image frame comprising a set of pixels; and a processor coupled to the image capture unit and configured to: determine a normalized distance of a pixel characteristic between the first image frame and a second image frame for each pixel in the first image frame; compare the normalized distance for each pixel in the first image frame against a pixel sensitivity value for that pixel; determine that a particular pixel of the first image frame is a foreground or background pixel based on the normalized distance of the particular pixel relative to the pixel sensitivity value for the particular pixel; and adapt the pixel sensitivity value for each pixel over a range of allowable pixel sensitivity values.

Abstract: An example method for processing visual communications at a video camera according to the disclosure includes analyzing video content captured by the video camera to identify a visual command presented to the camera by a user in the field of view of the camera, executing the visual command identified from the video content captured by the video camera, wherein executing the visual command includes setting one or more operating parameters of the video camera, determining a command completion indication corresponding to whether the command was successfully executed, and providing a command completion indication, corresponding to the command completion indication, to the user.

Abstract: Disclosed are methods, systems, computer readable media and other implementations, including a method to calibrate a camera that includes capturing by the camera a frame of a scene, identifying features appearing in the captured frame, the features associated with pre-determined values representative of physical attributes of one or more objects, and determining parameters of the camera based on the identified features appearing in the captured frame and the pre-determined values associated with the identified features.

Abstract: Embodiments of the disclosure provide for systems and methods for searching video data for events and/or behaviors. An inference engine can be used to aide in the searching. In some embodiments, a user can specify various search criteria, for example, a video source(s), an event(s) or behavior(s) to search, and an action(s) to perform in the event of a successful search. The search can be performed by analyzing an object(s) found within scenes of the video data. An object can be identified by a number of attributes specified by the user. Once the search criteria has been received from the user, the video data can be received (or extracted from storage), the data analyzed for the specified events (or behaviors), and the specified action performed in the event a successful search occurs.

Abstract: Embodiments of the disclosure provide for systems and methods for creating metadata associated with a video data. The metadata can include data about objects viewed within a video scene and/or events that occur within the video scene. Some embodiments allow users to search for specific objects and/or events by searching the recorded metadata. In some embodiments, metadata is created by receiving a video frame and developing a background model for the video frame. Foreground object(s) can then be identified in the video frame using the background model. Once these objects are identified they can be classified and/or an event associated with the foreground object may be detected. The event and the classification of the foreground object can then be recorded as metadata.

Abstract: A method of adjusting the color of images captured by a plurality of cameras comprises the steps of receiving a first image captured by a first camera from the plurality of cameras, analyzing the first image to separate the pixels in the first image into background pixels and foreground pixels, selecting pixels from the background pixels that have a color that is a shade of gray, determining the amount to adjust the colors of the selected pixels to move their colors towards true gray, and providing information for use in adjusting the color components of images from the plurality of cameras.

Abstract: Techniques are discussed for providing mechanisms for coding and transmitting high definition video, e.g., over low bandwidth connections. In particular, foreground-objects are identified as distinct from the background of a scene represented in a plurality of video frames received from a video source, such as a camera. In identifying foreground-objects, semantically significant and semantically insignificant movement (e.g., repetitive versus non-repetitive movement) is differentiated. Processing of the foreground-objects and background proceed at different update rates or frequencies.

Abstract: Systems and methods are described for determining device positions in a video surveillance system. A method described herein includes generating a reference sound; emitting, at a first device, the reference sound; detecting, at the first device, a responsive reference sound from one or more second devices in response to the emitted reference sound; identifying a position of each of the one or more second devices; obtaining information relating to latency of the one or more second devices; computing a round trip time associated with each of the one or more second devices based on at least a timing of detecting the one or more responsive reference sounds and the latency of each of the one or more second devices; and estimating the position of the first device according to the round trip time and the position associated with each of the one or more second devices.

Abstract: Techniques for processing video content in a video camera are provided. The techniques include a method for processing video content in at video camera according to the disclosure includes capturing thermal video data using a thermal imaging sensor, determining quantization parameters for the thermal video data, quantizing the thermal video data to generate quantized thermal video data content and video quantization information, and transmitting the quantized thermal video data stream and the video quantization information to a video analytics server over a network.

Abstract: Trajectory information of objects appearing in a scene can be used to cluster trajectories into groups of trajectories according to each trajectory's relative distance between each other for scene activity analysis. By doing so, a database of trajectory data can be maintained that includes the trajectories to be clustered into trajectory groups. This database can be used to train a clustering system, and with extracted statistical features of resultant trajectory groups a new trajectory can be analyzed to determine whether the new trajectory is normal or abnormal. Embodiments described herein, can be used to determine whether a video scene is normal or abnormal. In the event that the new trajectory is identified as normal the new trajectory can be annotated with the extracted semantic data. In the event that the new trajectory is determined to be abnormal a user can be notified that an abnormal behavior has occurred.

Abstract: An example of a method for identifying objects in video content according to the disclosure includes receiving video content of a scene captured by a video camera, detecting an object in the video content, identifying a track that the object follows over a series of frames of the video content, extracting object features for the object from the video content, and classifying the object based on the object features. Classifying the object further comprises: determining a track-level classification for the object using spatially invariant object features, determining a global-clustering classification for the object using spatially variant features, and determining an object type for the object based on the track-level classification and the global-clustering classification for the object.

Abstract: Systems and methods of sorting electronic color images of objects are provided. One method includes receiving an input representation of an object, the representation including pixels defined in a first color space, converting the input image into a second color space, determining a query feature vector including multiple parameters associated with color of the input representation, the query feature vector parameters including at least a first parameter of the first color space and at least a first parameter of the second color space and comparing the query feature vector to multiple candidate feature vectors. Each candidate feature vector includes multiple parameters associated with color of multiple stored candidate images, the candidate feature vector parameters including at least the first parameter from the first color space and at least the first parameter from the second color space.

Abstract: An image capture system includes: an image capture unit configured to capture a first image frame comprising a set of pixels; and a processor coupled to the image capture unit and configured to: determine a normalized distance of a pixel characteristic between the first image frame and a second image frame for each pixel in the first image frame; compare the normalized distance for each pixel in the first image frame against a pixel sensitivity value for that pixel; determine that a particular pixel of the first image frame is a foreground or background pixel based on the normalized distance of the particular pixel relative to the pixel sensitivity value for the particular pixel; and adapt the pixel sensitivity value for each pixel over a range of allowable pixel sensitivity values.

Abstract: Techniques are discussed herein for providing mechanisms for coding and transmitting high definition video, e.g., over low bandwidth connections. In particular, foreground-objects are identified as distinct from the background of a scene represented by a plurality of video frames. In identifying foreground-objects, semantically significant and semantically insignificant movement (e.g., non-repetitive versus repetitive movement) is differentiated. For example, the swaying motion of a tree's leaves being minor and repetitive, can be determined to be semantically insignificant and to belong in a scene's background. Processing of the foreground-objects and background proceed at different update rates or frequencies. For example, foreground-objects can be updated 30 or 60 times per second. By contrast, a background is updated less frequently, e.g., once every 10 seconds. In some implementations, if no foreground-objects are identified, no live video is transmitted (e.g.

Abstract: An example of a method for identifying objects in video content according to the disclosure includes receiving video content of a scene captured by a video camera, detecting an object in the video content, identifying a track that the object follows over a series of frames of the video content, extracting object features for the object from the video content, and classifying the object based on the object features. Classifying the object further comprises: determining a track-level classification for the object using spatially invariant object features, determining a global-clustering classification for the object using spatially variant features, and determining an object type for the object based on the track-level classification and the global-clustering classification for the object.